nit

* first cut at slack oauth flow

* fix usage of hooks

* fix button spacing

* add additional error logging

* no dev redirect

* cleanup

* comment work in progress

* move some stuff to ee, add some playwright tests for the oauth callback edge cases

* fix ee, fix test name

* fix tests

* code review fixes

backend/alembic/versions/9f696734098f_combine_search_and_chat.py

@@ -0,0 +1,36 @@
+"""Combine Search and Chat
+
+Revision ID: 9f696734098f
+Revises: a8c2065484e6
+Create Date: 2024-11-27 15:32:19.694972
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+# revision identifiers, used by Alembic.
+revision = "9f696734098f"
+down_revision = "a8c2065484e6"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    op.alter_column("chat_session", "description", nullable=True)
+    op.drop_column("chat_session", "one_shot")
+    op.drop_column("slack_channel_config", "response_type")
+
+
+def downgrade() -> None:
+    op.execute("UPDATE chat_session SET description = '' WHERE description IS NULL")
+    op.alter_column("chat_session", "description", nullable=False)
+    op.add_column(
+        "chat_session",
+        sa.Column("one_shot", sa.Boolean(), nullable=False, server_default=sa.false()),
+    )
+    op.add_column(
+        "slack_channel_config",
+        sa.Column(
+            "response_type", sa.String(), nullable=False, server_default="citations"
+        ),
+    )

backend/alembic/versions/f7a894b06d02_non_nullbale_slack_bot_id_in_channel_.py

@@ -0,0 +1,40 @@
+"""non-nullbale slack bot id in channel config
+
+Revision ID: f7a894b06d02
+Revises: 9f696734098f
+Create Date: 2024-12-06 12:55:42.845723
+
+"""
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = "f7a894b06d02"
+down_revision = "9f696734098f"
+branch_labels = None
+depends_on = None
+
+
+def upgrade() -> None:
+    # Delete all rows with null slack_bot_id
+    op.execute("DELETE FROM slack_channel_config WHERE slack_bot_id IS NULL")
+
+    # Make slack_bot_id non-nullable
+    op.alter_column(
+        "slack_channel_config",
+        "slack_bot_id",
+        existing_type=sa.Integer(),
+        nullable=False,
+    )
+
+
+def downgrade() -> None:
+    # Make slack_bot_id nullable again
+    op.alter_column(
+        "slack_channel_config",
+        "slack_bot_id",
+        existing_type=sa.Integer(),
+        nullable=True,
+    )

backend/danswer/access/models.py

@@ -18,6 +18,11 @@ class ExternalAccess:
 
 @dataclass(frozen=True)
 class DocExternalAccess:
+    """
+    This is just a class to wrap the external access and the document ID
+    together. It's used for syncing document permissions to Redis.
+    """
+
     external_access: ExternalAccess
     # The document ID
     doc_id: str

backend/danswer/auth/users.py

@@ -58,7 +58,6 @@ from danswer.auth.schemas import UserRole
 from danswer.auth.schemas import UserUpdate
 from danswer.configs.app_configs import AUTH_TYPE
 from danswer.configs.app_configs import DISABLE_AUTH
-from danswer.configs.app_configs import DISABLE_VERIFICATION
 from danswer.configs.app_configs import EMAIL_FROM
 from danswer.configs.app_configs import REQUIRE_EMAIL_VERIFICATION
 from danswer.configs.app_configs import SESSION_EXPIRE_TIME_SECONDS
@@ -87,6 +86,7 @@ from danswer.db.models import AccessToken
 from danswer.db.models import OAuthAccount
 from danswer.db.models import User
 from danswer.db.users import get_user_by_email
+from danswer.server.utils import BasicAuthenticationError
 from danswer.utils.logger import setup_logger
 from danswer.utils.telemetry import optional_telemetry
 from danswer.utils.telemetry import RecordType
@@ -99,11 +99,6 @@ from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
 logger = setup_logger()
 
 
-class BasicAuthenticationError(HTTPException):
-    def __init__(self, detail: str):
-        super().__init__(status_code=status.HTTP_403_FORBIDDEN, detail=detail)
-
-
 def is_user_admin(user: User | None) -> bool:
     if AUTH_TYPE == AuthType.DISABLED:
         return True
@@ -136,11 +131,12 @@ def get_display_email(email: str | None, space_less: bool = False) -> str:
 
 
 def user_needs_to_be_verified() -> bool:
-    # all other auth types besides basic should require users to be
-    # verified
-    return not DISABLE_VERIFICATION and (
-        AUTH_TYPE != AuthType.BASIC or REQUIRE_EMAIL_VERIFICATION
-    )
+    if AUTH_TYPE == AuthType.BASIC:
+        return REQUIRE_EMAIL_VERIFICATION
+
+    # For other auth types, if the user is authenticated it's assumed that
+    # the user is already verified via the external IDP
+    return False
 
 
 def verify_email_is_invited(email: str) -> None:

backend/danswer/background/celery/apps/primary.py

@@ -39,7 +39,6 @@ from danswer.redis.redis_usergroup import RedisUserGroup
 from danswer.utils.logger import setup_logger
 from shared_configs.configs import MULTI_TENANT
 
-
 logger = setup_logger()
 
 celery_app = Celery(__name__)
@@ -117,9 +116,13 @@ def on_worker_init(sender: Any, **kwargs: Any) -> None:
     # it is planned to use this lock to enforce singleton behavior on the primary
     # worker, since the primary worker does redis cleanup on startup, but this isn't
     # implemented yet.
+
+    # set thread_local=False since we don't control what thread the periodic task might
+    # reacquire the lock with
     lock: RedisLock = r.lock(
         DanswerRedisLocks.PRIMARY_WORKER,
         timeout=CELERY_PRIMARY_WORKER_LOCK_TIMEOUT,
+        thread_local=False,
     )
 
     logger.info("Primary worker lock: Acquire starting.")

backend/danswer/background/celery/tasks/doc_permission_syncing/tasks.py

@@ -22,6 +22,7 @@ from danswer.configs.constants import DanswerCeleryTask
 from danswer.configs.constants import DanswerRedisLocks
 from danswer.configs.constants import DocumentSource
 from danswer.db.connector_credential_pair import get_connector_credential_pair_from_id
+from danswer.db.document import upsert_document_by_connector_credential_pair
 from danswer.db.engine import get_session_with_tenant
 from danswer.db.enums import AccessType
 from danswer.db.enums import ConnectorCredentialPairStatus
@@ -218,7 +219,7 @@ def connector_permission_sync_generator_task(
 
     r = get_redis_client(tenant_id=tenant_id)
 
-    lock = r.lock(
+    lock: RedisLock = r.lock(
         DanswerRedisLocks.CONNECTOR_DOC_PERMISSIONS_SYNC_LOCK_PREFIX
         + f"_{redis_connector.id}",
         timeout=CELERY_PERMISSIONS_SYNC_LOCK_TIMEOUT,
@@ -262,7 +263,12 @@ def connector_permission_sync_generator_task(
                 f"RedisConnector.permissions.generate_tasks starting. cc_pair={cc_pair_id}"
             )
             tasks_generated = redis_connector.permissions.generate_tasks(
-                self.app, lock, document_external_accesses, source_type
+                celery_app=self.app,
+                lock=lock,
+                new_permissions=document_external_accesses,
+                source_string=source_type,
+                connector_id=cc_pair.connector.id,
+                credential_id=cc_pair.credential.id,
             )
             if tasks_generated is None:
                 return None
@@ -298,6 +304,8 @@ def update_external_document_permissions_task(
     tenant_id: str | None,
     serialized_doc_external_access: dict,
     source_string: str,
+    connector_id: int,
+    credential_id: int,
 ) -> bool:
     document_external_access = DocExternalAccess.from_dict(
         serialized_doc_external_access
@@ -306,18 +314,28 @@ def update_external_document_permissions_task(
     external_access = document_external_access.external_access
     try:
         with get_session_with_tenant(tenant_id) as db_session:
-            # Then we build the update requests to update vespa
+            # Add the users to the DB if they don't exist
             batch_add_ext_perm_user_if_not_exists(
                 db_session=db_session,
                 emails=list(external_access.external_user_emails),
             )
-            upsert_document_external_perms(
+            # Then we upsert the document's external permissions in postgres
+            created_new_doc = upsert_document_external_perms(
                 db_session=db_session,
                 doc_id=doc_id,
                 external_access=external_access,
                 source_type=DocumentSource(source_string),
             )
 
+            if created_new_doc:
+                # If a new document was created, we associate it with the cc_pair
+                upsert_document_by_connector_credential_pair(
+                    db_session=db_session,
+                    connector_id=connector_id,
+                    credential_id=credential_id,
+                    document_ids=[doc_id],
+                )
+
             logger.debug(
                 f"Successfully synced postgres document permissions for {doc_id}"
             )

backend/danswer/background/celery/tasks/external_group_syncing/tasks.py

@@ -32,10 +32,14 @@ from danswer.redis.redis_connector_ext_group_sync import (
 from danswer.redis.redis_pool import get_redis_client
 from danswer.utils.logger import setup_logger
 from ee.danswer.db.connector_credential_pair import get_all_auto_sync_cc_pairs
+from ee.danswer.db.connector_credential_pair import get_cc_pairs_by_source
 from ee.danswer.db.external_perm import ExternalUserGroup
 from ee.danswer.db.external_perm import replace_user__ext_group_for_cc_pair
 from ee.danswer.external_permissions.sync_params import EXTERNAL_GROUP_SYNC_PERIODS
 from ee.danswer.external_permissions.sync_params import GROUP_PERMISSIONS_FUNC_MAP
+from ee.danswer.external_permissions.sync_params import (
+    GROUP_PERMISSIONS_IS_CC_PAIR_AGNOSTIC,
+)
 
 logger = setup_logger()
 
@@ -107,6 +111,22 @@ def check_for_external_group_sync(self: Task, *, tenant_id: str | None) -> None:
         with get_session_with_tenant(tenant_id) as db_session:
             cc_pairs = get_all_auto_sync_cc_pairs(db_session)
 
+            # We only want to sync one cc_pair per source type in
+            # GROUP_PERMISSIONS_IS_CC_PAIR_AGNOSTIC
+            for source in GROUP_PERMISSIONS_IS_CC_PAIR_AGNOSTIC:
+                # These are ordered by cc_pair id so the first one is the one we want
+                cc_pairs_to_dedupe = get_cc_pairs_by_source(
+                    db_session, source, only_sync=True
+                )
+                # We only want to sync one cc_pair per source type
+                # in GROUP_PERMISSIONS_IS_CC_PAIR_AGNOSTIC so we dedupe here
+                for cc_pair_to_remove in cc_pairs_to_dedupe[1:]:
+                    cc_pairs = [
+                        cc_pair
+                        for cc_pair in cc_pairs
+                        if cc_pair.id != cc_pair_to_remove.id
+                    ]
+
             for cc_pair in cc_pairs:
                 if _is_external_group_sync_due(cc_pair):
                     cc_pair_ids_to_sync.append(cc_pair.id)

backend/danswer/background/celery/tasks/indexing/tasks.py

@@ -789,9 +789,12 @@ def connector_indexing_task(
         )
         break
 
+    # set thread_local=False since we don't control what thread the indexing/pruning
+    # might run our callback with
     lock: RedisLock = r.lock(
         redis_connector_index.generator_lock_key,
         timeout=CELERY_INDEXING_LOCK_TIMEOUT,
+        thread_local=False,
     )
 
     acquired = lock.acquire(blocking=False)

backend/danswer/background/celery/tasks/pruning/tasks.py

@@ -8,6 +8,7 @@ from celery import shared_task
 from celery import Task
 from celery.exceptions import SoftTimeLimitExceeded
 from redis import Redis
+from redis.lock import Lock as RedisLock
 from sqlalchemy.orm import Session
 
 from danswer.background.celery.apps.app_base import task_logger
@@ -239,9 +240,12 @@ def connector_pruning_generator_task(
 
     r = get_redis_client(tenant_id=tenant_id)
 
-    lock = r.lock(
+    # set thread_local=False since we don't control what thread the indexing/pruning
+    # might run our callback with
+    lock: RedisLock = r.lock(
         DanswerRedisLocks.PRUNING_LOCK_PREFIX + f"_{redis_connector.id}",
         timeout=CELERY_PRUNING_LOCK_TIMEOUT,
+        thread_local=False,
     )
 
     acquired = lock.acquire(blocking=False)

backend/danswer/chat/answer.py

@@ -6,33 +6,27 @@ from langchain.schema.messages import BaseMessage
 from langchain_core.messages import AIMessageChunk
 from langchain_core.messages import ToolCall
 
+from danswer.chat.llm_response_handler import LLMResponseHandlerManager
 from danswer.chat.models import AnswerQuestionPossibleReturn
+from danswer.chat.models import AnswerStyleConfig
 from danswer.chat.models import CitationInfo
 from danswer.chat.models import DanswerAnswerPiece
-from danswer.file_store.utils import InMemoryChatFile
-from danswer.llm.answering.llm_response_handler import LLMCall
-from danswer.llm.answering.llm_response_handler import LLMResponseHandlerManager
-from danswer.llm.answering.models import AnswerStyleConfig
-from danswer.llm.answering.models import PreviousMessage
-from danswer.llm.answering.models import PromptConfig
-from danswer.llm.answering.prompts.build import AnswerPromptBuilder
-from danswer.llm.answering.prompts.build import default_build_system_message
-from danswer.llm.answering.prompts.build import default_build_user_message
-from danswer.llm.answering.stream_processing.answer_response_handler import (
-    AnswerResponseHandler,
-)
-from danswer.llm.answering.stream_processing.answer_response_handler import (
+from danswer.chat.models import PromptConfig
+from danswer.chat.prompt_builder.build import AnswerPromptBuilder
+from danswer.chat.prompt_builder.build import default_build_system_message
+from danswer.chat.prompt_builder.build import default_build_user_message
+from danswer.chat.prompt_builder.build import LLMCall
+from danswer.chat.stream_processing.answer_response_handler import (
     CitationResponseHandler,
 )
-from danswer.llm.answering.stream_processing.answer_response_handler import (
+from danswer.chat.stream_processing.answer_response_handler import (
     DummyAnswerResponseHandler,
 )
-from danswer.llm.answering.stream_processing.answer_response_handler import (
-    QuotesResponseHandler,
-)
-from danswer.llm.answering.stream_processing.utils import map_document_id_order
-from danswer.llm.answering.tool.tool_response_handler import ToolResponseHandler
+from danswer.chat.stream_processing.utils import map_document_id_order
+from danswer.chat.tool_handling.tool_response_handler import ToolResponseHandler
+from danswer.file_store.utils import InMemoryChatFile
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.natural_language_processing.utils import get_tokenizer
 from danswer.tools.force import ForceUseTool
 from danswer.tools.models import ToolResponse
@@ -214,18 +208,23 @@ class Answer:
 
         search_result = SearchTool.get_search_result(current_llm_call) or []
 
-        answer_handler: AnswerResponseHandler
-        if self.answer_style_config.citation_config:
-            answer_handler = CitationResponseHandler(
-                context_docs=search_result,
-                doc_id_to_rank_map=map_document_id_order(search_result),
-            )
-        elif self.answer_style_config.quotes_config:
-            answer_handler = QuotesResponseHandler(
-                context_docs=search_result,
-            )
-        else:
-            raise ValueError("No answer style config provided")
+        # Quotes are no longer supported
+        # answer_handler: AnswerResponseHandler
+        # if self.answer_style_config.citation_config:
+        #     answer_handler = CitationResponseHandler(
+        #         context_docs=search_result,
+        #         doc_id_to_rank_map=map_document_id_order(search_result),
+        #     )
+        # elif self.answer_style_config.quotes_config:
+        #     answer_handler = QuotesResponseHandler(
+        #         context_docs=search_result,
+        #     )
+        # else:
+        #     raise ValueError("No answer style config provided")
+        answer_handler = CitationResponseHandler(
+            context_docs=search_result,
+            doc_id_to_rank_map=map_document_id_order(search_result),
+        )
 
         response_handler_manager = LLMResponseHandlerManager(
             tool_call_handler, answer_handler, self.is_cancelled

backend/danswer/chat/chat_utils.py

@@ -2,20 +2,79 @@ import re
 from typing import cast
 from uuid import UUID
 
+from fastapi import HTTPException
 from fastapi.datastructures import Headers
 from sqlalchemy.orm import Session
 
+from danswer.auth.users import is_user_admin
 from danswer.chat.models import CitationInfo
 from danswer.chat.models import LlmDoc
+from danswer.chat.models import PersonaOverrideConfig
+from danswer.chat.models import ThreadMessage
+from danswer.configs.constants import DEFAULT_PERSONA_ID
+from danswer.configs.constants import MessageType
 from danswer.context.search.models import InferenceSection
+from danswer.context.search.models import RerankingDetails
+from danswer.context.search.models import RetrievalDetails
+from danswer.db.chat import create_chat_session
 from danswer.db.chat import get_chat_messages_by_session
+from danswer.db.llm import fetch_existing_doc_sets
+from danswer.db.llm import fetch_existing_tools
 from danswer.db.models import ChatMessage
-from danswer.llm.answering.models import PreviousMessage
+from danswer.db.models import Persona
+from danswer.db.models import Prompt
+from danswer.db.models import Tool
+from danswer.db.models import User
+from danswer.db.persona import get_prompts_by_ids
+from danswer.llm.models import PreviousMessage
+from danswer.natural_language_processing.utils import BaseTokenizer
+from danswer.server.query_and_chat.models import CreateChatMessageRequest
+from danswer.tools.tool_implementations.custom.custom_tool import (
+    build_custom_tools_from_openapi_schema_and_headers,
+)
 from danswer.utils.logger import setup_logger
 
 logger = setup_logger()
 
 
+def prepare_chat_message_request(
+    message_text: str,
+    user: User | None,
+    persona_id: int | None,
+    # Does the question need to have a persona override
+    persona_override_config: PersonaOverrideConfig | None,
+    prompt: Prompt | None,
+    message_ts_to_respond_to: str | None,
+    retrieval_details: RetrievalDetails | None,
+    rerank_settings: RerankingDetails | None,
+    db_session: Session,
+) -> CreateChatMessageRequest:
+    # Typically used for one shot flows like SlackBot or non-chat API endpoint use cases
+    new_chat_session = create_chat_session(
+        db_session=db_session,
+        description=None,
+        user_id=user.id if user else None,
+        # If using an override, this id will be ignored later on
+        persona_id=persona_id or DEFAULT_PERSONA_ID,
+        danswerbot_flow=True,
+        slack_thread_id=message_ts_to_respond_to,
+    )
+
+    return CreateChatMessageRequest(
+        chat_session_id=new_chat_session.id,
+        parent_message_id=None,  # It's a standalone chat session each time
+        message=message_text,
+        file_descriptors=[],  # Currently SlackBot/answer api do not support files in the context
+        prompt_id=prompt.id if prompt else None,
+        # Can always override the persona for the single query, if it's a normal persona
+        # then it will be treated the same
+        persona_override_config=persona_override_config,
+        search_doc_ids=None,
+        retrieval_options=retrieval_details,
+        rerank_settings=rerank_settings,
+    )
+
+
 def llm_doc_from_inference_section(inference_section: InferenceSection) -> LlmDoc:
     return LlmDoc(
         document_id=inference_section.center_chunk.document_id,
@@ -35,6 +94,45 @@ def llm_doc_from_inference_section(inference_section: InferenceSection) -> LlmDo
     )
 
 
+def combine_message_thread(
+    messages: list[ThreadMessage],
+    max_tokens: int | None,
+    llm_tokenizer: BaseTokenizer,
+) -> str:
+    """Used to create a single combined message context from threads"""
+    if not messages:
+        return ""
+
+    message_strs: list[str] = []
+    total_token_count = 0
+
+    for message in reversed(messages):
+        if message.role == MessageType.USER:
+            role_str = message.role.value.upper()
+            if message.sender:
+                role_str += " " + message.sender
+            else:
+                # Since other messages might have the user identifying information
+                # better to use Unknown for symmetry
+                role_str += " Unknown"
+        else:
+            role_str = message.role.value.upper()
+
+        msg_str = f"{role_str}:\n{message.message}"
+        message_token_count = len(llm_tokenizer.encode(msg_str))
+
+        if (
+            max_tokens is not None
+            and total_token_count + message_token_count > max_tokens
+        ):
+            break
+
+        message_strs.insert(0, msg_str)
+        total_token_count += message_token_count
+
+    return "\n\n".join(message_strs)
+
+
 def create_chat_chain(
     chat_session_id: UUID,
     db_session: Session,
@@ -197,3 +295,71 @@ def extract_headers(
             if lowercase_key in headers:
                 extracted_headers[lowercase_key] = headers[lowercase_key]
     return extracted_headers
+
+
+def create_temporary_persona(
+    persona_config: PersonaOverrideConfig, db_session: Session, user: User | None = None
+) -> Persona:
+    if not is_user_admin(user):
+        raise HTTPException(
+            status_code=403,
+            detail="User is not authorized to create a persona in one shot queries",
+        )
+
+    """Create a temporary Persona object from the provided configuration."""
+    persona = Persona(
+        name=persona_config.name,
+        description=persona_config.description,
+        num_chunks=persona_config.num_chunks,
+        llm_relevance_filter=persona_config.llm_relevance_filter,
+        llm_filter_extraction=persona_config.llm_filter_extraction,
+        recency_bias=persona_config.recency_bias,
+        llm_model_provider_override=persona_config.llm_model_provider_override,
+        llm_model_version_override=persona_config.llm_model_version_override,
+    )
+
+    if persona_config.prompts:
+        persona.prompts = [
+            Prompt(
+                name=p.name,
+                description=p.description,
+                system_prompt=p.system_prompt,
+                task_prompt=p.task_prompt,
+                include_citations=p.include_citations,
+                datetime_aware=p.datetime_aware,
+            )
+            for p in persona_config.prompts
+        ]
+    elif persona_config.prompt_ids:
+        persona.prompts = get_prompts_by_ids(
+            db_session=db_session, prompt_ids=persona_config.prompt_ids
+        )
+
+    persona.tools = []
+    if persona_config.custom_tools_openapi:
+        for schema in persona_config.custom_tools_openapi:
+            tools = cast(
+                list[Tool],
+                build_custom_tools_from_openapi_schema_and_headers(schema),
+            )
+            persona.tools.extend(tools)
+
+    if persona_config.tools:
+        tool_ids = [tool.id for tool in persona_config.tools]
+        persona.tools.extend(
+            fetch_existing_tools(db_session=db_session, tool_ids=tool_ids)
+        )
+
+    if persona_config.tool_ids:
+        persona.tools.extend(
+            fetch_existing_tools(
+                db_session=db_session, tool_ids=persona_config.tool_ids
+            )
+        )
+
+    fetched_docs = fetch_existing_doc_sets(
+        db_session=db_session, doc_ids=persona_config.document_set_ids
+    )
+    persona.document_sets = fetched_docs
+
+    return persona

backend/danswer/chat/llm_response_handler.py

@@ -1,60 +1,22 @@
 from collections.abc import Callable
 from collections.abc import Generator
 from collections.abc import Iterator
-from typing import TYPE_CHECKING
 
 from langchain_core.messages import BaseMessage
-from pydantic.v1 import BaseModel as BaseModel__v1
 
-from danswer.chat.models import CitationInfo
-from danswer.chat.models import DanswerAnswerPiece
-from danswer.chat.models import DanswerQuotes
+from danswer.chat.models import ResponsePart
 from danswer.chat.models import StreamStopInfo
 from danswer.chat.models import StreamStopReason
-from danswer.file_store.models import InMemoryChatFile
-from danswer.llm.answering.prompts.build import AnswerPromptBuilder
-from danswer.tools.force import ForceUseTool
-from danswer.tools.models import ToolCallFinalResult
-from danswer.tools.models import ToolCallKickoff
-from danswer.tools.models import ToolResponse
-from danswer.tools.tool import Tool
-
-
-if TYPE_CHECKING:
-    from danswer.llm.answering.stream_processing.answer_response_handler import (
-        AnswerResponseHandler,
-    )
-    from danswer.llm.answering.tool.tool_response_handler import ToolResponseHandler
-
-
-ResponsePart = (
-    DanswerAnswerPiece
-    | CitationInfo
-    | DanswerQuotes
-    | ToolCallKickoff
-    | ToolResponse
-    | ToolCallFinalResult
-    | StreamStopInfo
-)
-
-
-class LLMCall(BaseModel__v1):
-    prompt_builder: AnswerPromptBuilder
-    tools: list[Tool]
-    force_use_tool: ForceUseTool
-    files: list[InMemoryChatFile]
-    tool_call_info: list[ToolCallKickoff | ToolResponse | ToolCallFinalResult]
-    using_tool_calling_llm: bool
-
-    class Config:
-        arbitrary_types_allowed = True
+from danswer.chat.prompt_builder.build import LLMCall
+from danswer.chat.stream_processing.answer_response_handler import AnswerResponseHandler
+from danswer.chat.tool_handling.tool_response_handler import ToolResponseHandler
 
 
 class LLMResponseHandlerManager:
     def __init__(
         self,
-        tool_handler: "ToolResponseHandler",
-        answer_handler: "AnswerResponseHandler",
+        tool_handler: ToolResponseHandler,
+        answer_handler: AnswerResponseHandler,
         is_cancelled: Callable[[], bool],
     ):
         self.tool_handler = tool_handler

backend/danswer/chat/models.py

@@ -1,17 +1,30 @@
+from collections.abc import Callable
 from collections.abc import Iterator
 from datetime import datetime
 from enum import Enum
 from typing import Any
+from typing import TYPE_CHECKING
 
 from pydantic import BaseModel
+from pydantic import ConfigDict
+from pydantic import Field
+from pydantic import model_validator
 
 from danswer.configs.constants import DocumentSource
+from danswer.configs.constants import MessageType
 from danswer.context.search.enums import QueryFlow
+from danswer.context.search.enums import RecencyBiasSetting
 from danswer.context.search.enums import SearchType
 from danswer.context.search.models import RetrievalDocs
-from danswer.context.search.models import SearchResponse
+from danswer.llm.override_models import PromptOverride
+from danswer.tools.models import ToolCallFinalResult
+from danswer.tools.models import ToolCallKickoff
+from danswer.tools.models import ToolResponse
 from danswer.tools.tool_implementations.custom.base_tool_types import ToolResultType
 
+if TYPE_CHECKING:
+    from danswer.db.models import Prompt
+
 
 class LlmDoc(BaseModel):
     """This contains the minimal set information for the LLM portion including citations"""
@@ -118,20 +131,6 @@ class StreamingError(BaseModel):
     stack_trace: str | None = None
 
 
-class DanswerQuote(BaseModel):
-    # This is during inference so everything is a string by this point
-    quote: str
-    document_id: str
-    link: str | None
-    source_type: str
-    semantic_identifier: str
-    blurb: str
-
-
-class DanswerQuotes(BaseModel):
-    quotes: list[DanswerQuote]
-
-
 class DanswerContext(BaseModel):
     content: str
     document_id: str
@@ -147,14 +146,20 @@ class DanswerAnswer(BaseModel):
     answer: str | None
 
 
-class QAResponse(SearchResponse, DanswerAnswer):
-    quotes: list[DanswerQuote] | None
-    contexts: list[DanswerContexts] | None
-    predicted_flow: QueryFlow
-    predicted_search: SearchType
-    eval_res_valid: bool | None = None
+class ThreadMessage(BaseModel):
+    message: str
+    sender: str | None = None
+    role: MessageType = MessageType.USER
+
+
+class ChatDanswerBotResponse(BaseModel):
+    answer: str | None = None
+    citations: list[CitationInfo] | None = None
+    docs: QADocsResponse | None = None
     llm_selected_doc_indices: list[int] | None = None
     error_msg: str | None = None
+    chat_message_id: int | None = None
+    answer_valid: bool = True  # Reflexion result, default True if Reflexion not run
 
 
 class FileChatDisplay(BaseModel):
@@ -166,9 +171,41 @@ class CustomToolResponse(BaseModel):
     tool_name: str
 
 
+class ToolConfig(BaseModel):
+    id: int
+
+
+class PromptOverrideConfig(BaseModel):
+    name: str
+    description: str = ""
+    system_prompt: str
+    task_prompt: str = ""
+    include_citations: bool = True
+    datetime_aware: bool = True
+
+
+class PersonaOverrideConfig(BaseModel):
+    name: str
+    description: str
+    search_type: SearchType = SearchType.SEMANTIC
+    num_chunks: float | None = None
+    llm_relevance_filter: bool = False
+    llm_filter_extraction: bool = False
+    recency_bias: RecencyBiasSetting = RecencyBiasSetting.AUTO
+    llm_model_provider_override: str | None = None
+    llm_model_version_override: str | None = None
+
+    prompts: list[PromptOverrideConfig] = Field(default_factory=list)
+    prompt_ids: list[int] = Field(default_factory=list)
+
+    document_set_ids: list[int] = Field(default_factory=list)
+    tools: list[ToolConfig] = Field(default_factory=list)
+    tool_ids: list[int] = Field(default_factory=list)
+    custom_tools_openapi: list[dict[str, Any]] = Field(default_factory=list)
+
+
 AnswerQuestionPossibleReturn = (
     DanswerAnswerPiece
-    | DanswerQuotes
     | CitationInfo
     | DanswerContexts
     | FileChatDisplay
@@ -184,3 +221,109 @@ AnswerQuestionStreamReturn = Iterator[AnswerQuestionPossibleReturn]
 class LLMMetricsContainer(BaseModel):
     prompt_tokens: int
     response_tokens: int
+
+
+StreamProcessor = Callable[[Iterator[str]], AnswerQuestionStreamReturn]
+
+
+class DocumentPruningConfig(BaseModel):
+    max_chunks: int | None = None
+    max_window_percentage: float | None = None
+    max_tokens: int | None = None
+    # different pruning behavior is expected when the
+    # user manually selects documents they want to chat with
+    # e.g. we don't want to truncate each document to be no more
+    # than one chunk long
+    is_manually_selected_docs: bool = False
+    # If user specifies to include additional context Chunks for each match, then different pruning
+    # is used. As many Sections as possible are included, and the last Section is truncated
+    # If this is false, all of the Sections are truncated if they are longer than the expected Chunk size.
+    # Sections are often expected to be longer than the maximum Chunk size but Chunks should not be.
+    use_sections: bool = True
+    # If using tools, then we need to consider the tool length
+    tool_num_tokens: int = 0
+    # If using a tool message to represent the docs, then we have to JSON serialize
+    # the document content, which adds to the token count.
+    using_tool_message: bool = False
+
+
+class ContextualPruningConfig(DocumentPruningConfig):
+    num_chunk_multiple: int
+
+    @classmethod
+    def from_doc_pruning_config(
+        cls, num_chunk_multiple: int, doc_pruning_config: DocumentPruningConfig
+    ) -> "ContextualPruningConfig":
+        return cls(num_chunk_multiple=num_chunk_multiple, **doc_pruning_config.dict())
+
+
+class CitationConfig(BaseModel):
+    all_docs_useful: bool = False
+
+
+class QuotesConfig(BaseModel):
+    pass
+
+
+class AnswerStyleConfig(BaseModel):
+    citation_config: CitationConfig | None = None
+    quotes_config: QuotesConfig | None = None
+    document_pruning_config: DocumentPruningConfig = Field(
+        default_factory=DocumentPruningConfig
+    )
+    # forces the LLM to return a structured response, see
+    # https://platform.openai.com/docs/guides/structured-outputs/introduction
+    # right now, only used by the simple chat API
+    structured_response_format: dict | None = None
+
+    @model_validator(mode="after")
+    def check_quotes_and_citation(self) -> "AnswerStyleConfig":
+        if self.citation_config is None and self.quotes_config is None:
+            raise ValueError(
+                "One of `citation_config` or `quotes_config` must be provided"
+            )
+
+        if self.citation_config is not None and self.quotes_config is not None:
+            raise ValueError(
+                "Only one of `citation_config` or `quotes_config` must be provided"
+            )
+
+        return self
+
+
+class PromptConfig(BaseModel):
+    """Final representation of the Prompt configuration passed
+    into the `Answer` object."""
+
+    system_prompt: str
+    task_prompt: str
+    datetime_aware: bool
+    include_citations: bool
+
+    @classmethod
+    def from_model(
+        cls, model: "Prompt", prompt_override: PromptOverride | None = None
+    ) -> "PromptConfig":
+        override_system_prompt = (
+            prompt_override.system_prompt if prompt_override else None
+        )
+        override_task_prompt = prompt_override.task_prompt if prompt_override else None
+
+        return cls(
+            system_prompt=override_system_prompt or model.system_prompt,
+            task_prompt=override_task_prompt or model.task_prompt,
+            datetime_aware=model.datetime_aware,
+            include_citations=model.include_citations,
+        )
+
+    model_config = ConfigDict(frozen=True)
+
+
+ResponsePart = (
+    DanswerAnswerPiece
+    | CitationInfo
+    | ToolCallKickoff
+    | ToolResponse
+    | ToolCallFinalResult
+    | StreamStopInfo
+)

backend/danswer/chat/process_message.py

@@ -6,16 +6,24 @@ from typing import cast
 
 from sqlalchemy.orm import Session
 
+from danswer.chat.answer import Answer
 from danswer.chat.chat_utils import create_chat_chain
+from danswer.chat.chat_utils import create_temporary_persona
 from danswer.chat.models import AllCitations
+from danswer.chat.models import AnswerStyleConfig
+from danswer.chat.models import ChatDanswerBotResponse
+from danswer.chat.models import CitationConfig
 from danswer.chat.models import CitationInfo
 from danswer.chat.models import CustomToolResponse
 from danswer.chat.models import DanswerAnswerPiece
+from danswer.chat.models import DanswerContexts
+from danswer.chat.models import DocumentPruningConfig
 from danswer.chat.models import FileChatDisplay
 from danswer.chat.models import FinalUsedContextDocsResponse
 from danswer.chat.models import LLMRelevanceFilterResponse
 from danswer.chat.models import MessageResponseIDInfo
 from danswer.chat.models import MessageSpecificCitations
+from danswer.chat.models import PromptConfig
 from danswer.chat.models import QADocsResponse
 from danswer.chat.models import StreamingError
 from danswer.chat.models import StreamStopInfo
@@ -54,16 +62,11 @@ from danswer.document_index.factory import get_default_document_index
 from danswer.file_store.models import ChatFileType
 from danswer.file_store.models import FileDescriptor
 from danswer.file_store.utils import load_all_chat_files
-from danswer.file_store.utils import save_files_from_urls
-from danswer.llm.answering.answer import Answer
-from danswer.llm.answering.models import AnswerStyleConfig
-from danswer.llm.answering.models import CitationConfig
-from danswer.llm.answering.models import DocumentPruningConfig
-from danswer.llm.answering.models import PreviousMessage
-from danswer.llm.answering.models import PromptConfig
+from danswer.file_store.utils import save_files
 from danswer.llm.exceptions import GenAIDisabledException
 from danswer.llm.factory import get_llms_for_persona
 from danswer.llm.factory import get_main_llm_from_tuple
+from danswer.llm.models import PreviousMessage
 from danswer.llm.utils import litellm_exception_to_error_msg
 from danswer.natural_language_processing.utils import get_tokenizer
 from danswer.server.query_and_chat.models import ChatMessageDetail
@@ -102,6 +105,7 @@ from danswer.tools.tool_implementations.internet_search.internet_search_tool imp
 from danswer.tools.tool_implementations.search.search_tool import (
     FINAL_CONTEXT_DOCUMENTS_ID,
 )
+from danswer.tools.tool_implementations.search.search_tool import SEARCH_DOC_CONTENT_ID
 from danswer.tools.tool_implementations.search.search_tool import (
     SEARCH_RESPONSE_SUMMARY_ID,
 )
@@ -113,7 +117,10 @@ from danswer.tools.tool_implementations.search.search_tool import (
 from danswer.tools.tool_runner import ToolCallFinalResult
 from danswer.utils.logger import setup_logger
 from danswer.utils.long_term_log import LongTermLogger
+from danswer.utils.timing import log_function_time
 from danswer.utils.timing import log_generator_function_time
+from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
+
 
 logger = setup_logger()
 
@@ -256,6 +263,7 @@ def _get_force_search_settings(
 ChatPacket = (
     StreamingError
     | QADocsResponse
+    | DanswerContexts
     | LLMRelevanceFilterResponse
     | FinalUsedContextDocsResponse
     | ChatMessageDetail
@@ -286,6 +294,8 @@ def stream_chat_message_objects(
     custom_tool_additional_headers: dict[str, str] | None = None,
     is_connected: Callable[[], bool] | None = None,
     enforce_chat_session_id_for_search_docs: bool = True,
+    bypass_acl: bool = False,
+    include_contexts: bool = False,
 ) -> ChatPacketStream:
     """Streams in order:
     1. [conditional] Retrieved documents if a search needs to be run
@@ -293,6 +303,7 @@ def stream_chat_message_objects(
     3. [always] A set of streamed LLM tokens or an error anywhere along the line if something fails
     4. [always] Details on the final AI response message that is created
     """
+    tenant_id = CURRENT_TENANT_ID_CONTEXTVAR.get()
     use_existing_user_message = new_msg_req.use_existing_user_message
     existing_assistant_message_id = new_msg_req.existing_assistant_message_id
 
@@ -322,17 +333,31 @@ def stream_chat_message_objects(
             metadata={"user_id": str(user_id), "chat_session_id": str(chat_session_id)}
         )
 
-        # use alternate persona if alternative assistant id is passed in
         if alternate_assistant_id is not None:
+            # Allows users to specify a temporary persona (assistant) in the chat session
+            # this takes highest priority since it's user specified
             persona = get_persona_by_id(
                 alternate_assistant_id,
                 user=user,
                 db_session=db_session,
                 is_for_edit=False,
             )
+        elif new_msg_req.persona_override_config:
+            # Certain endpoints allow users to specify arbitrary persona settings
+            # this should never conflict with the alternate_assistant_id
+            persona = persona = create_temporary_persona(
+                db_session=db_session,
+                persona_config=new_msg_req.persona_override_config,
+                user=user,
+            )
         else:
             persona = chat_session.persona
 
+        if not persona:
+            raise RuntimeError("No persona specified or found for chat session")
+
+        # If a prompt override is specified via the API, use that with highest priority
+        # but for saving it, we are just mapping it to an existing prompt
         prompt_id = new_msg_req.prompt_id
         if prompt_id is None and persona.prompts:
             prompt_id = sorted(persona.prompts, key=lambda x: x.id)[-1].id
@@ -555,19 +580,34 @@ def stream_chat_message_objects(
             reserved_message_id=reserved_message_id,
         )
 
-        if not final_msg.prompt:
-            raise RuntimeError("No Prompt found")
-
-        prompt_config = (
-            PromptConfig.from_model(
-                final_msg.prompt,
-                prompt_override=(
-                    new_msg_req.prompt_override or chat_session.prompt_override
-                ),
+        prompt_override = new_msg_req.prompt_override or chat_session.prompt_override
+        if new_msg_req.persona_override_config:
+            prompt_config = PromptConfig(
+                system_prompt=new_msg_req.persona_override_config.prompts[
+                    0
+                ].system_prompt,
+                task_prompt=new_msg_req.persona_override_config.prompts[0].task_prompt,
+                datetime_aware=new_msg_req.persona_override_config.prompts[
+                    0
+                ].datetime_aware,
+                include_citations=new_msg_req.persona_override_config.prompts[
+                    0
+                ].include_citations,
             )
-            if not persona
-            else PromptConfig.from_model(persona.prompts[0])
-        )
+        elif prompt_override:
+            if not final_msg.prompt:
+                raise ValueError(
+                    "Prompt override cannot be applied, no base prompt found."
+                )
+            prompt_config = PromptConfig.from_model(
+                final_msg.prompt,
+                prompt_override=prompt_override,
+            )
+        elif final_msg.prompt:
+            prompt_config = PromptConfig.from_model(final_msg.prompt)
+        else:
+            prompt_config = PromptConfig.from_model(persona.prompts[0])
+
         answer_style_config = AnswerStyleConfig(
             citation_config=CitationConfig(
                 all_docs_useful=selected_db_search_docs is not None
@@ -587,11 +627,13 @@ def stream_chat_message_objects(
                 answer_style_config=answer_style_config,
                 document_pruning_config=document_pruning_config,
                 retrieval_options=retrieval_options or RetrievalDetails(),
+                rerank_settings=new_msg_req.rerank_settings,
                 selected_sections=selected_sections,
                 chunks_above=new_msg_req.chunks_above,
                 chunks_below=new_msg_req.chunks_below,
                 full_doc=new_msg_req.full_doc,
                 latest_query_files=latest_query_files,
+                bypass_acl=bypass_acl,
             ),
             internet_search_tool_config=InternetSearchToolConfig(
                 answer_style_config=answer_style_config,
@@ -638,7 +680,8 @@ def stream_chat_message_objects(
 
         reference_db_search_docs = None
         qa_docs_response = None
-        ai_message_files = None  # any files to associate with the AI message e.g. dall-e generated images
+        # any files to associate with the AI message e.g. dall-e generated images
+        ai_message_files = []
         dropped_indices = None
         tool_result = None
 
@@ -693,8 +736,14 @@ def stream_chat_message_objects(
                         list[ImageGenerationResponse], packet.response
                     )
 
-                    file_ids = save_files_from_urls(
-                        [img.url for img in img_generation_response]
+                    file_ids = save_files(
+                        urls=[img.url for img in img_generation_response if img.url],
+                        base64_files=[
+                            img.image_data
+                            for img in img_generation_response
+                            if img.image_data
+                        ],
+                        tenant_id=tenant_id,
                     )
                     ai_message_files = [
                         FileDescriptor(id=str(file_id), type=ChatFileType.IMAGE)
@@ -720,15 +769,19 @@ def stream_chat_message_objects(
                         or custom_tool_response.response_type == "csv"
                     ):
                         file_ids = custom_tool_response.tool_result.file_ids
-                        ai_message_files = [
-                            FileDescriptor(
-                                id=str(file_id),
-                                type=ChatFileType.IMAGE
-                                if custom_tool_response.response_type == "image"
-                                else ChatFileType.CSV,
-                            )
-                            for file_id in file_ids
-                        ]
+                        ai_message_files.extend(
+                            [
+                                FileDescriptor(
+                                    id=str(file_id),
+                                    type=(
+                                        ChatFileType.IMAGE
+                                        if custom_tool_response.response_type == "image"
+                                        else ChatFileType.CSV
+                                    ),
+                                )
+                                for file_id in file_ids
+                            ]
+                        )
                         yield FileChatDisplay(
                             file_ids=[str(file_id) for file_id in file_ids]
                         )
@@ -737,6 +790,8 @@ def stream_chat_message_objects(
                             response=custom_tool_response.tool_result,
                             tool_name=custom_tool_response.tool_name,
                         )
+                elif packet.id == SEARCH_DOC_CONTENT_ID and include_contexts:
+                    yield cast(DanswerContexts, packet.response)
 
             elif isinstance(packet, StreamStopInfo):
                 pass
@@ -776,7 +831,8 @@ def stream_chat_message_objects(
                 citations_list=answer.citations,
                 db_docs=reference_db_search_docs,
             )
-            yield AllCitations(citations=answer.citations)
+            if not answer.is_cancelled():
+                yield AllCitations(citations=answer.citations)
 
         # Saving Gen AI answer and responding with message info
         tool_name_to_tool_id: dict[str, int] = {}
@@ -845,3 +901,30 @@ def stream_chat_message(
         )
         for obj in objects:
             yield get_json_line(obj.model_dump())
+
+
+@log_function_time()
+def gather_stream_for_slack(
+    packets: ChatPacketStream,
+) -> ChatDanswerBotResponse:
+    response = ChatDanswerBotResponse()
+
+    answer = ""
+    for packet in packets:
+        if isinstance(packet, DanswerAnswerPiece) and packet.answer_piece:
+            answer += packet.answer_piece
+        elif isinstance(packet, QADocsResponse):
+            response.docs = packet
+        elif isinstance(packet, StreamingError):
+            response.error_msg = packet.error
+        elif isinstance(packet, ChatMessageDetail):
+            response.chat_message_id = packet.message_id
+        elif isinstance(packet, LLMRelevanceFilterResponse):
+            response.llm_selected_doc_indices = packet.llm_selected_doc_indices
+        elif isinstance(packet, AllCitations):
+            response.citations = packet.citations
+
+    if answer:
+        response.answer = answer
+
+    return response

backend/danswer/chat/prompt_builder/build.py

@@ -4,20 +4,26 @@ from typing import cast
 from langchain_core.messages import BaseMessage
 from langchain_core.messages import HumanMessage
 from langchain_core.messages import SystemMessage
+from pydantic.v1 import BaseModel as BaseModel__v1
 
+from danswer.chat.models import PromptConfig
+from danswer.chat.prompt_builder.citations_prompt import compute_max_llm_input_tokens
+from danswer.chat.prompt_builder.utils import translate_history_to_basemessages
 from danswer.file_store.models import InMemoryChatFile
-from danswer.llm.answering.models import PreviousMessage
-from danswer.llm.answering.models import PromptConfig
-from danswer.llm.answering.prompts.citations_prompt import compute_max_llm_input_tokens
 from danswer.llm.interfaces import LLMConfig
+from danswer.llm.models import PreviousMessage
 from danswer.llm.utils import build_content_with_imgs
 from danswer.llm.utils import check_message_tokens
 from danswer.llm.utils import message_to_prompt_and_imgs
-from danswer.llm.utils import translate_history_to_basemessages
 from danswer.natural_language_processing.utils import get_tokenizer
 from danswer.prompts.chat_prompts import CHAT_USER_CONTEXT_FREE_PROMPT
 from danswer.prompts.prompt_utils import add_date_time_to_prompt
 from danswer.prompts.prompt_utils import drop_messages_history_overflow
+from danswer.tools.force import ForceUseTool
+from danswer.tools.models import ToolCallFinalResult
+from danswer.tools.models import ToolCallKickoff
+from danswer.tools.models import ToolResponse
+from danswer.tools.tool import Tool
 
 
 def default_build_system_message(
@@ -139,3 +145,15 @@ class AnswerPromptBuilder:
         return drop_messages_history_overflow(
             final_messages_with_tokens, self.max_tokens
         )
+
+
+class LLMCall(BaseModel__v1):
+    prompt_builder: AnswerPromptBuilder
+    tools: list[Tool]
+    force_use_tool: ForceUseTool
+    files: list[InMemoryChatFile]
+    tool_call_info: list[ToolCallKickoff | ToolResponse | ToolCallFinalResult]
+    using_tool_calling_llm: bool
+
+    class Config:
+        arbitrary_types_allowed = True

backend/danswer/chat/prompt_builder/citations_prompt.py

@@ -2,12 +2,12 @@ from langchain.schema.messages import HumanMessage
 from langchain.schema.messages import SystemMessage
 
 from danswer.chat.models import LlmDoc
+from danswer.chat.models import PromptConfig
 from danswer.configs.model_configs import GEN_AI_SINGLE_USER_MESSAGE_EXPECTED_MAX_TOKENS
 from danswer.context.search.models import InferenceChunk
 from danswer.db.models import Persona
 from danswer.db.persona import get_default_prompt__read_only
 from danswer.db.search_settings import get_multilingual_expansion
-from danswer.llm.answering.models import PromptConfig
 from danswer.llm.factory import get_llms_for_persona
 from danswer.llm.factory import get_main_llm_from_tuple
 from danswer.llm.interfaces import LLMConfig

backend/danswer/chat/prompt_builder/quotes_prompt.py

@@ -1,10 +1,10 @@
 from langchain.schema.messages import HumanMessage
 
 from danswer.chat.models import LlmDoc
+from danswer.chat.models import PromptConfig
 from danswer.configs.chat_configs import LANGUAGE_HINT
 from danswer.context.search.models import InferenceChunk
 from danswer.db.search_settings import get_multilingual_expansion
-from danswer.llm.answering.models import PromptConfig
 from danswer.llm.utils import message_to_prompt_and_imgs
 from danswer.prompts.direct_qa_prompts import CONTEXT_BLOCK
 from danswer.prompts.direct_qa_prompts import HISTORY_BLOCK

backend/danswer/chat/prompt_builder/utils.py

@@ -0,0 +1,62 @@
+from langchain.schema.messages import AIMessage
+from langchain.schema.messages import BaseMessage
+from langchain.schema.messages import HumanMessage
+
+from danswer.configs.constants import MessageType
+from danswer.db.models import ChatMessage
+from danswer.file_store.models import InMemoryChatFile
+from danswer.llm.models import PreviousMessage
+from danswer.llm.utils import build_content_with_imgs
+from danswer.prompts.direct_qa_prompts import PARAMATERIZED_PROMPT
+from danswer.prompts.direct_qa_prompts import PARAMATERIZED_PROMPT_WITHOUT_CONTEXT
+
+
+def build_dummy_prompt(
+    system_prompt: str, task_prompt: str, retrieval_disabled: bool
+) -> str:
+    if retrieval_disabled:
+        return PARAMATERIZED_PROMPT_WITHOUT_CONTEXT.format(
+            user_query="<USER_QUERY>",
+            system_prompt=system_prompt,
+            task_prompt=task_prompt,
+        ).strip()
+
+    return PARAMATERIZED_PROMPT.format(
+        context_docs_str="<CONTEXT_DOCS>",
+        user_query="<USER_QUERY>",
+        system_prompt=system_prompt,
+        task_prompt=task_prompt,
+    ).strip()
+
+
+def translate_danswer_msg_to_langchain(
+    msg: ChatMessage | PreviousMessage,
+) -> BaseMessage:
+    files: list[InMemoryChatFile] = []
+
+    # If the message is a `ChatMessage`, it doesn't have the downloaded files
+    # attached. Just ignore them for now.
+    if not isinstance(msg, ChatMessage):
+        files = msg.files
+    content = build_content_with_imgs(msg.message, files, message_type=msg.message_type)
+
+    if msg.message_type == MessageType.SYSTEM:
+        raise ValueError("System messages are not currently part of history")
+    if msg.message_type == MessageType.ASSISTANT:
+        return AIMessage(content=content)
+    if msg.message_type == MessageType.USER:
+        return HumanMessage(content=content)
+
+    raise ValueError(f"New message type {msg.message_type} not handled")
+
+
+def translate_history_to_basemessages(
+    history: list[ChatMessage] | list["PreviousMessage"],
+) -> tuple[list[BaseMessage], list[int]]:
+    history_basemessages = [
+        translate_danswer_msg_to_langchain(msg)
+        for msg in history
+        if msg.token_count != 0
+    ]
+    history_token_counts = [msg.token_count for msg in history if msg.token_count != 0]
+    return history_basemessages, history_token_counts

backend/danswer/chat/prune_and_merge.py

@@ -5,16 +5,16 @@ from typing import TypeVar
 
 from pydantic import BaseModel
 
+from danswer.chat.models import ContextualPruningConfig
 from danswer.chat.models import (
     LlmDoc,
 )
+from danswer.chat.models import PromptConfig
+from danswer.chat.prompt_builder.citations_prompt import compute_max_document_tokens
 from danswer.configs.constants import IGNORE_FOR_QA
 from danswer.configs.model_configs import DOC_EMBEDDING_CONTEXT_SIZE
 from danswer.context.search.models import InferenceChunk
 from danswer.context.search.models import InferenceSection
-from danswer.llm.answering.models import ContextualPruningConfig
-from danswer.llm.answering.models import PromptConfig
-from danswer.llm.answering.prompts.citations_prompt import compute_max_document_tokens
 from danswer.llm.interfaces import LLMConfig
 from danswer.natural_language_processing.utils import get_tokenizer
 from danswer.natural_language_processing.utils import tokenizer_trim_content

backend/danswer/chat/stream_processing/answer_response_handler.py

@@ -3,16 +3,11 @@ from collections.abc import Generator
 
 from langchain_core.messages import BaseMessage
 
+from danswer.chat.llm_response_handler import ResponsePart
 from danswer.chat.models import CitationInfo
 from danswer.chat.models import LlmDoc
-from danswer.llm.answering.llm_response_handler import ResponsePart
-from danswer.llm.answering.stream_processing.citation_processing import (
-    CitationProcessor,
-)
-from danswer.llm.answering.stream_processing.quotes_processing import (
-    QuotesProcessor,
-)
-from danswer.llm.answering.stream_processing.utils import DocumentIdOrderMapping
+from danswer.chat.stream_processing.citation_processing import CitationProcessor
+from danswer.chat.stream_processing.utils import DocumentIdOrderMapping
 from danswer.utils.logger import setup_logger
 
 logger = setup_logger()
@@ -70,28 +65,29 @@ class CitationResponseHandler(AnswerResponseHandler):
         yield from self.citation_processor.process_token(content)
 
 
-class QuotesResponseHandler(AnswerResponseHandler):
-    def __init__(
-        self,
-        context_docs: list[LlmDoc],
-        is_json_prompt: bool = True,
-    ):
-        self.quotes_processor = QuotesProcessor(
-            context_docs=context_docs,
-            is_json_prompt=is_json_prompt,
-        )
+# No longer in use, remove later
+# class QuotesResponseHandler(AnswerResponseHandler):
+#     def __init__(
+#         self,
+#         context_docs: list[LlmDoc],
+#         is_json_prompt: bool = True,
+#     ):
+#         self.quotes_processor = QuotesProcessor(
+#             context_docs=context_docs,
+#             is_json_prompt=is_json_prompt,
+#         )
 
-    def handle_response_part(
-        self,
-        response_item: BaseMessage | None,
-        previous_response_items: list[BaseMessage],
-    ) -> Generator[ResponsePart, None, None]:
-        if response_item is None:
-            yield from self.quotes_processor.process_token(None)
-            return
+#     def handle_response_part(
+#         self,
+#         response_item: BaseMessage | None,
+#         previous_response_items: list[BaseMessage],
+#     ) -> Generator[ResponsePart, None, None]:
+#         if response_item is None:
+#             yield from self.quotes_processor.process_token(None)
+#             return
 
-        content = (
-            response_item.content if isinstance(response_item.content, str) else ""
-        )
+#         content = (
+#             response_item.content if isinstance(response_item.content, str) else ""
+#         )
 
-        yield from self.quotes_processor.process_token(content)
+#         yield from self.quotes_processor.process_token(content)

backend/danswer/chat/stream_processing/citation_processing.py

@@ -4,8 +4,8 @@ from collections.abc import Generator
 from danswer.chat.models import CitationInfo
 from danswer.chat.models import DanswerAnswerPiece
 from danswer.chat.models import LlmDoc
+from danswer.chat.stream_processing.utils import DocumentIdOrderMapping
 from danswer.configs.chat_configs import STOP_STREAM_PAT
-from danswer.llm.answering.stream_processing.utils import DocumentIdOrderMapping
 from danswer.prompts.constants import TRIPLE_BACKTICK
 from danswer.utils.logger import setup_logger
 

backend/danswer/chat/stream_processing/quotes_processing.py

@@ -1,3 +1,4 @@
+# THIS IS NO LONGER IN USE
 import math
 import re
 from collections.abc import Generator
@@ -5,11 +6,10 @@ from json import JSONDecodeError
 from typing import Optional
 
 import regex
+from pydantic import BaseModel
 
 from danswer.chat.models import DanswerAnswer
 from danswer.chat.models import DanswerAnswerPiece
-from danswer.chat.models import DanswerQuote
-from danswer.chat.models import DanswerQuotes
 from danswer.chat.models import LlmDoc
 from danswer.configs.chat_configs import QUOTE_ALLOWED_ERROR_PERCENT
 from danswer.context.search.models import InferenceChunk
@@ -26,6 +26,20 @@ logger = setup_logger()
 answer_pattern = re.compile(r'{\s*"answer"\s*:\s*"', re.IGNORECASE)
 
 
+class DanswerQuote(BaseModel):
+    # This is during inference so everything is a string by this point
+    quote: str
+    document_id: str
+    link: str | None
+    source_type: str
+    semantic_identifier: str
+    blurb: str
+
+
+class DanswerQuotes(BaseModel):
+    quotes: list[DanswerQuote]
+
+
 def _extract_answer_quotes_freeform(
     answer_raw: str,
 ) -> tuple[Optional[str], Optional[list[str]]]:

backend/danswer/chat/tool_handling/tool_response_handler.py

@@ -4,8 +4,8 @@ from langchain_core.messages import AIMessageChunk
 from langchain_core.messages import BaseMessage
 from langchain_core.messages import ToolCall
 
-from danswer.llm.answering.llm_response_handler import LLMCall
-from danswer.llm.answering.llm_response_handler import ResponsePart
+from danswer.chat.models import ResponsePart
+from danswer.chat.prompt_builder.build import LLMCall
 from danswer.llm.interfaces import LLM
 from danswer.tools.force import ForceUseTool
 from danswer.tools.message import build_tool_message

backend/danswer/configs/app_configs.py

@@ -43,9 +43,6 @@ WEB_DOMAIN = os.environ.get("WEB_DOMAIN") or "http://localhost:3000"
 AUTH_TYPE = AuthType((os.environ.get("AUTH_TYPE") or AuthType.DISABLED.value).lower())
 DISABLE_AUTH = AUTH_TYPE == AuthType.DISABLED
 
-# Necessary for cloud integration tests
-DISABLE_VERIFICATION = os.environ.get("DISABLE_VERIFICATION", "").lower() == "true"
-
 # Encryption key secret is used to encrypt connector credentials, api keys, and other sensitive
 # information. This provides an extra layer of security on top of Postgres access controls
 # and is available in Danswer EE
@@ -84,7 +81,14 @@ OAUTH_CLIENT_SECRET = (
     or ""
 )
 
+# for future OAuth connector support
+# OAUTH_CONFLUENCE_CLIENT_ID = os.environ.get("OAUTH_CONFLUENCE_CLIENT_ID", "")
+# OAUTH_CONFLUENCE_CLIENT_SECRET = os.environ.get("OAUTH_CONFLUENCE_CLIENT_SECRET", "")
+# OAUTH_JIRA_CLIENT_ID = os.environ.get("OAUTH_JIRA_CLIENT_ID", "")
+# OAUTH_JIRA_CLIENT_SECRET = os.environ.get("OAUTH_JIRA_CLIENT_SECRET", "")
+
 USER_AUTH_SECRET = os.environ.get("USER_AUTH_SECRET", "")
+
 # for basic auth
 REQUIRE_EMAIL_VERIFICATION = (
     os.environ.get("REQUIRE_EMAIL_VERIFICATION", "").lower() == "true"
@@ -118,6 +122,8 @@ VESPA_HOST = os.environ.get("VESPA_HOST") or "localhost"
 VESPA_CONFIG_SERVER_HOST = os.environ.get("VESPA_CONFIG_SERVER_HOST") or VESPA_HOST
 VESPA_PORT = os.environ.get("VESPA_PORT") or "8081"
 VESPA_TENANT_PORT = os.environ.get("VESPA_TENANT_PORT") or "19071"
+# the number of times to try and connect to vespa on startup before giving up
+VESPA_NUM_ATTEMPTS_ON_STARTUP = int(os.environ.get("NUM_RETRIES_ON_STARTUP") or 10)
 
 VESPA_CLOUD_URL = os.environ.get("VESPA_CLOUD_URL", "")
 
@@ -522,3 +528,6 @@ API_KEY_HASH_ROUNDS = (
 
 POD_NAME = os.environ.get("POD_NAME")
 POD_NAMESPACE = os.environ.get("POD_NAMESPACE")
+
+
+DEV_MODE = os.environ.get("DEV_MODE", "").lower() == "true"

backend/danswer/configs/constants.py

@@ -31,6 +31,8 @@ DISABLED_GEN_AI_MSG = (
     "You can still use Danswer as a search engine."
 )
 
+DEFAULT_PERSONA_ID = 0
+
 # Postgres connection constants for application_name
 POSTGRES_WEB_APP_NAME = "web"
 POSTGRES_INDEXER_APP_NAME = "indexer"

backend/danswer/configs/danswerbot_configs.py

@@ -4,11 +4,8 @@ import os
 # Danswer Slack Bot Configs
 #####
 DANSWER_BOT_NUM_RETRIES = int(os.environ.get("DANSWER_BOT_NUM_RETRIES", "5"))
-DANSWER_BOT_ANSWER_GENERATION_TIMEOUT = int(
-    os.environ.get("DANSWER_BOT_ANSWER_GENERATION_TIMEOUT", "90")
-)
 # How much of the available input context can be used for thread context
-DANSWER_BOT_TARGET_CHUNK_PERCENTAGE = 512 * 2 / 3072
+MAX_THREAD_CONTEXT_PERCENTAGE = 512 * 2 / 3072
 # Number of docs to display in "Reference Documents"
 DANSWER_BOT_NUM_DOCS_TO_DISPLAY = int(
     os.environ.get("DANSWER_BOT_NUM_DOCS_TO_DISPLAY", "5")
@@ -47,17 +44,6 @@ DANSWER_BOT_DISPLAY_ERROR_MSGS = os.environ.get(
 DANSWER_BOT_RESPOND_EVERY_CHANNEL = (
     os.environ.get("DANSWER_BOT_RESPOND_EVERY_CHANNEL", "").lower() == "true"
 )
-# Add a second LLM call post Answer to verify if the Answer is valid
-# Throws out answers that don't directly or fully answer the user query
-# This is the default for all DanswerBot channels unless the channel is configured individually
-# Set/unset by "Hide Non Answers"
-ENABLE_DANSWERBOT_REFLEXION = (
-    os.environ.get("ENABLE_DANSWERBOT_REFLEXION", "").lower() == "true"
-)
-# Currently not support chain of thought, probably will add back later
-DANSWER_BOT_DISABLE_COT = True
-# if set, will default DanswerBot to use quotes and reference documents
-DANSWER_BOT_USE_QUOTES = os.environ.get("DANSWER_BOT_USE_QUOTES", "").lower() == "true"
 
 # Maximum Questions Per Minute, Default Uncapped
 DANSWER_BOT_MAX_QPM = int(os.environ.get("DANSWER_BOT_MAX_QPM") or 0) or None

backend/danswer/configs/tool_configs.py

@@ -2,6 +2,8 @@ import json
 import os
 
 
+IMAGE_GENERATION_OUTPUT_FORMAT = os.environ.get("IMAGE_GENERATION_OUTPUT_FORMAT", "url")
+
 # if specified, will pass through request headers to the call to API calls made by custom tools
 CUSTOM_TOOL_PASS_THROUGH_HEADERS: list[str] | None = None
 _CUSTOM_TOOL_PASS_THROUGH_HEADERS_RAW = os.environ.get(

backend/danswer/connectors/confluence/connector.py

@@ -15,6 +15,7 @@ from danswer.connectors.confluence.utils import attachment_to_content
 from danswer.connectors.confluence.utils import build_confluence_document_id
 from danswer.connectors.confluence.utils import datetime_from_string
 from danswer.connectors.confluence.utils import extract_text_from_confluence_html
+from danswer.connectors.confluence.utils import validate_attachment_filetype
 from danswer.connectors.interfaces import GenerateDocumentsOutput
 from danswer.connectors.interfaces import GenerateSlimDocumentOutput
 from danswer.connectors.interfaces import LoadConnector
@@ -276,9 +277,11 @@ class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
         ):
             # If the page has restrictions, add them to the perm_sync_data
             # These will be used by doc_sync.py to sync permissions
-            perm_sync_data = {
-                "restrictions": page.get("restrictions", {}),
-                "space_key": page.get("space", {}).get("key"),
+            page_restrictions = page.get("restrictions")
+            page_space_key = page.get("space", {}).get("key")
+            page_perm_sync_data = {
+                "restrictions": page_restrictions or {},
+                "space_key": page_space_key,
             }
 
             doc_metadata_list.append(
@@ -288,7 +291,7 @@ class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
                         page["_links"]["webui"],
                         self.is_cloud,
                     ),
-                    perm_sync_data=perm_sync_data,
+                    perm_sync_data=page_perm_sync_data,
                 )
             )
             attachment_cql = f"type=attachment and container='{page['id']}'"
@@ -298,6 +301,21 @@ class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
                 expand=restrictions_expand,
                 limit=_SLIM_DOC_BATCH_SIZE,
             ):
+                if not validate_attachment_filetype(attachment):
+                    continue
+                attachment_restrictions = attachment.get("restrictions")
+                if not attachment_restrictions:
+                    attachment_restrictions = page_restrictions
+
+                attachment_space_key = attachment.get("space", {}).get("key")
+                if not attachment_space_key:
+                    attachment_space_key = page_space_key
+
+                attachment_perm_sync_data = {
+                    "restrictions": attachment_restrictions or {},
+                    "space_key": attachment_space_key,
+                }
+
                 doc_metadata_list.append(
                     SlimDocument(
                         id=build_confluence_document_id(
@@ -305,7 +323,7 @@ class ConfluenceConnector(LoadConnector, PollConnector, SlimConnector):
                             attachment["_links"]["webui"],
                             self.is_cloud,
                         ),
-                        perm_sync_data=perm_sync_data,
+                        perm_sync_data=attachment_perm_sync_data,
                     )
                 )
             if len(doc_metadata_list) > _SLIM_DOC_BATCH_SIZE:

backend/danswer/connectors/confluence/utils.py

@@ -32,7 +32,11 @@ def get_user_email_from_username__server(
             response = confluence_client.get_mobile_parameters(user_name)
             email = response.get("email")
         except Exception:
-            email = None
+            # For now, we'll just return a string that indicates failure
+            # We may want to revert to returning None in the future
+            # email = None
+            email = f"FAILED TO GET CONFLUENCE EMAIL FOR {user_name}"
+            logger.warning(f"failed to get confluence email for {user_name}")
         _USER_EMAIL_CACHE[user_name] = email
     return _USER_EMAIL_CACHE[user_name]
 
@@ -173,19 +177,23 @@ def extract_text_from_confluence_html(
     return format_document_soup(soup)
 
 
-def attachment_to_content(
-    confluence_client: OnyxConfluence,
-    attachment: dict[str, Any],
-) -> str | None:
-    """If it returns None, assume that we should skip this attachment."""
-    if attachment["metadata"]["mediaType"] in [
+def validate_attachment_filetype(attachment: dict[str, Any]) -> bool:
+    return attachment["metadata"]["mediaType"] not in [
         "image/jpeg",
         "image/png",
         "image/gif",
         "image/svg+xml",
         "video/mp4",
         "video/quicktime",
-    ]:
+    ]
+
+
+def attachment_to_content(
+    confluence_client: OnyxConfluence,
+    attachment: dict[str, Any],
+) -> str | None:
+    """If it returns None, assume that we should skip this attachment."""
+    if not validate_attachment_filetype(attachment):
         return None
 
     download_link = confluence_client.url + attachment["_links"]["download"]
@@ -241,7 +249,7 @@ def build_confluence_document_id(
     return f"{base_url}{content_url}"
 
 
-def extract_referenced_attachment_names(page_text: str) -> list[str]:
+def _extract_referenced_attachment_names(page_text: str) -> list[str]:
     """Parse a Confluence html page to generate a list of current
         attachments in use
 

backend/danswer/context/search/pipeline.py

@@ -5,7 +5,11 @@ from typing import cast
 
 from sqlalchemy.orm import Session
 
+from danswer.chat.models import PromptConfig
 from danswer.chat.models import SectionRelevancePiece
+from danswer.chat.prune_and_merge import _merge_sections
+from danswer.chat.prune_and_merge import ChunkRange
+from danswer.chat.prune_and_merge import merge_chunk_intervals
 from danswer.configs.chat_configs import DISABLE_LLM_DOC_RELEVANCE
 from danswer.context.search.enums import LLMEvaluationType
 from danswer.context.search.enums import QueryFlow
@@ -27,10 +31,6 @@ from danswer.db.models import User
 from danswer.db.search_settings import get_current_search_settings
 from danswer.document_index.factory import get_default_document_index
 from danswer.document_index.interfaces import VespaChunkRequest
-from danswer.llm.answering.models import PromptConfig
-from danswer.llm.answering.prune_and_merge import _merge_sections
-from danswer.llm.answering.prune_and_merge import ChunkRange
-from danswer.llm.answering.prune_and_merge import merge_chunk_intervals
 from danswer.llm.interfaces import LLM
 from danswer.secondary_llm_flows.agentic_evaluation import evaluate_inference_section
 from danswer.utils.logger import setup_logger

backend/danswer/danswerbot/slack/blocks.py

@@ -16,7 +16,7 @@ from slack_sdk.models.blocks import SectionBlock
 from slack_sdk.models.blocks.basic_components import MarkdownTextObject
 from slack_sdk.models.blocks.block_elements import ImageElement
 
-from danswer.chat.models import DanswerQuote
+from danswer.chat.models import ChatDanswerBotResponse
 from danswer.configs.app_configs import DISABLE_GENERATIVE_AI
 from danswer.configs.app_configs import WEB_DOMAIN
 from danswer.configs.constants import DocumentSource
@@ -40,10 +40,7 @@ from danswer.danswerbot.slack.utils import translate_vespa_highlight_to_slack
 from danswer.db.chat import get_chat_session_by_message_id
 from danswer.db.engine import get_session_with_tenant
 from danswer.db.models import ChannelConfig
-from danswer.db.models import Persona
-from danswer.one_shot_answer.models import OneShotQAResponse
 from danswer.utils.text_processing import decode_escapes
-from danswer.utils.text_processing import replace_whitespaces_w_space
 
 _MAX_BLURB_LEN = 45
 
@@ -327,7 +324,7 @@ def _build_sources_blocks(
 
 
 def _priority_ordered_documents_blocks(
-    answer: OneShotQAResponse,
+    answer: ChatDanswerBotResponse,
 ) -> list[Block]:
     docs_response = answer.docs if answer.docs else None
     top_docs = docs_response.top_documents if docs_response else []
@@ -350,7 +347,7 @@ def _priority_ordered_documents_blocks(
 
 
 def _build_citations_blocks(
-    answer: OneShotQAResponse,
+    answer: ChatDanswerBotResponse,
 ) -> list[Block]:
     docs_response = answer.docs if answer.docs else None
     top_docs = docs_response.top_documents if docs_response else []
@@ -369,51 +366,8 @@ def _build_citations_blocks(
     return citations_block
 
 
-def _build_quotes_block(
-    quotes: list[DanswerQuote],
-) -> list[Block]:
-    quote_lines: list[str] = []
-    doc_to_quotes: dict[str, list[str]] = {}
-    doc_to_link: dict[str, str] = {}
-    doc_to_sem_id: dict[str, str] = {}
-    for q in quotes:
-        quote = q.quote
-        doc_id = q.document_id
-        doc_link = q.link
-        doc_name = q.semantic_identifier
-        if doc_link and doc_name and doc_id and quote:
-            if doc_id not in doc_to_quotes:
-                doc_to_quotes[doc_id] = [quote]
-                doc_to_link[doc_id] = doc_link
-                doc_to_sem_id[doc_id] = (
-                    doc_name
-                    if q.source_type != DocumentSource.SLACK.value
-                    else "#" + doc_name
-                )
-            else:
-                doc_to_quotes[doc_id].append(quote)
-
-    for doc_id, quote_strs in doc_to_quotes.items():
-        quotes_str_clean = [
-            replace_whitespaces_w_space(q_str).strip() for q_str in quote_strs
-        ]
-        longest_quotes = sorted(quotes_str_clean, key=len, reverse=True)[:5]
-        single_quote_str = "\n".join([f"```{q_str}```" for q_str in longest_quotes])
-        link = doc_to_link[doc_id]
-        sem_id = doc_to_sem_id[doc_id]
-        quote_lines.append(
-            f"<{link}|{sem_id}>:\n{remove_slack_text_interactions(single_quote_str)}"
-        )
-
-    if not doc_to_quotes:
-        return []
-
-    return [SectionBlock(text="*Relevant Snippets*\n" + "\n".join(quote_lines))]
-
-
 def _build_qa_response_blocks(
-    answer: OneShotQAResponse,
-    skip_quotes: bool = False,
+    answer: ChatDanswerBotResponse,
     process_message_for_citations: bool = False,
 ) -> list[Block]:
     retrieval_info = answer.docs
@@ -422,13 +376,10 @@ def _build_qa_response_blocks(
         raise RuntimeError("Failed to retrieve docs, cannot answer question.")
 
     formatted_answer = format_slack_message(answer.answer) if answer.answer else None
-    quotes = answer.quotes.quotes if answer.quotes else None
 
     if DISABLE_GENERATIVE_AI:
         return []
 
-    quotes_blocks: list[Block] = []
-
     filter_block: Block | None = None
     if (
         retrieval_info.applied_time_cutoff
@@ -471,16 +422,6 @@ def _build_qa_response_blocks(
         answer_blocks = [
             SectionBlock(text=text) for text in _split_text(answer_processed)
         ]
-        if quotes:
-            quotes_blocks = _build_quotes_block(quotes)
-
-        # if no quotes OR `_build_quotes_block()` did not give back any blocks
-        if not quotes_blocks:
-            quotes_blocks = [
-                SectionBlock(
-                    text="*Warning*: no sources were quoted for this answer, so it may be unreliable 😔"
-                )
-            ]
 
     response_blocks: list[Block] = []
 
@@ -489,9 +430,6 @@ def _build_qa_response_blocks(
 
     response_blocks.extend(answer_blocks)
 
-    if not skip_quotes:
-        response_blocks.extend(quotes_blocks)
-
     return response_blocks
 
 
@@ -567,10 +505,9 @@ def build_follow_up_resolved_blocks(
 
 
 def build_slack_response_blocks(
+    answer: ChatDanswerBotResponse,
     tenant_id: str | None,
     message_info: SlackMessageInfo,
-    answer: OneShotQAResponse,
-    persona: Persona | None,
     channel_conf: ChannelConfig | None,
     use_citations: bool,
     feedback_reminder_id: str | None,
@@ -587,7 +524,6 @@ def build_slack_response_blocks(
 
     answer_blocks = _build_qa_response_blocks(
         answer=answer,
-        skip_quotes=persona is not None or use_citations,
         process_message_for_citations=use_citations,
     )
 
@@ -617,8 +553,7 @@ def build_slack_response_blocks(
 
     citations_blocks = []
     document_blocks = []
-    if use_citations:
-        # if citations are enabled, only show cited documents
+    if use_citations and answer.citations:
         citations_blocks = _build_citations_blocks(answer)
     else:
         document_blocks = _priority_ordered_documents_blocks(answer)
@@ -637,4 +572,5 @@ def build_slack_response_blocks(
         + web_follow_up_block
         + follow_up_block
     )
+
     return all_blocks

backend/danswer/danswerbot/slack/handlers/handle_regular_answer.py

@@ -1,7 +1,6 @@
 import functools
 from collections.abc import Callable
 from typing import Any
-from typing import cast
 from typing import Optional
 from typing import TypeVar
 
@@ -9,46 +8,36 @@ from retry import retry
 from slack_sdk import WebClient
 from slack_sdk.models.blocks import SectionBlock
 
+from danswer.chat.chat_utils import prepare_chat_message_request
+from danswer.chat.models import ChatDanswerBotResponse
+from danswer.chat.process_message import gather_stream_for_slack
+from danswer.chat.process_message import stream_chat_message_objects
 from danswer.configs.app_configs import DISABLE_GENERATIVE_AI
-from danswer.configs.danswerbot_configs import DANSWER_BOT_ANSWER_GENERATION_TIMEOUT
-from danswer.configs.danswerbot_configs import DANSWER_BOT_DISABLE_COT
+from danswer.configs.constants import DEFAULT_PERSONA_ID
 from danswer.configs.danswerbot_configs import DANSWER_BOT_DISABLE_DOCS_ONLY_ANSWER
 from danswer.configs.danswerbot_configs import DANSWER_BOT_DISPLAY_ERROR_MSGS
 from danswer.configs.danswerbot_configs import DANSWER_BOT_NUM_RETRIES
-from danswer.configs.danswerbot_configs import DANSWER_BOT_TARGET_CHUNK_PERCENTAGE
-from danswer.configs.danswerbot_configs import DANSWER_BOT_USE_QUOTES
 from danswer.configs.danswerbot_configs import DANSWER_FOLLOWUP_EMOJI
 from danswer.configs.danswerbot_configs import DANSWER_REACT_EMOJI
-from danswer.configs.danswerbot_configs import ENABLE_DANSWERBOT_REFLEXION
+from danswer.configs.danswerbot_configs import MAX_THREAD_CONTEXT_PERCENTAGE
 from danswer.context.search.enums import OptionalSearchSetting
 from danswer.context.search.models import BaseFilters
-from danswer.context.search.models import RerankingDetails
 from danswer.context.search.models import RetrievalDetails
 from danswer.danswerbot.slack.blocks import build_slack_response_blocks
 from danswer.danswerbot.slack.handlers.utils import send_team_member_message
+from danswer.danswerbot.slack.handlers.utils import slackify_message_thread
 from danswer.danswerbot.slack.models import SlackMessageInfo
 from danswer.danswerbot.slack.utils import respond_in_thread
 from danswer.danswerbot.slack.utils import SlackRateLimiter
 from danswer.danswerbot.slack.utils import update_emote_react
 from danswer.db.engine import get_session_with_tenant
-from danswer.db.models import Persona
-from danswer.db.models import SlackBotResponseType
 from danswer.db.models import SlackChannelConfig
-from danswer.db.persona import fetch_persona_by_id
-from danswer.db.search_settings import get_current_search_settings
+from danswer.db.models import User
+from danswer.db.persona import get_persona_by_id
 from danswer.db.users import get_user_by_email
-from danswer.llm.answering.prompts.citations_prompt import (
-    compute_max_document_tokens_for_persona,
-)
-from danswer.llm.factory import get_llms_for_persona
-from danswer.llm.utils import check_number_of_tokens
-from danswer.llm.utils import get_max_input_tokens
-from danswer.one_shot_answer.answer_question import get_search_answer
-from danswer.one_shot_answer.models import DirectQARequest
-from danswer.one_shot_answer.models import OneShotQAResponse
+from danswer.server.query_and_chat.models import CreateChatMessageRequest
 from danswer.utils.logger import DanswerLoggingAdapter
 
-
 srl = SlackRateLimiter()
 
 RT = TypeVar("RT")  # return type
@@ -83,16 +72,14 @@ def handle_regular_answer(
     feedback_reminder_id: str | None,
     tenant_id: str | None,
     num_retries: int = DANSWER_BOT_NUM_RETRIES,
-    answer_generation_timeout: int = DANSWER_BOT_ANSWER_GENERATION_TIMEOUT,
-    thread_context_percent: float = DANSWER_BOT_TARGET_CHUNK_PERCENTAGE,
+    thread_context_percent: float = MAX_THREAD_CONTEXT_PERCENTAGE,
     should_respond_with_error_msgs: bool = DANSWER_BOT_DISPLAY_ERROR_MSGS,
     disable_docs_only_answer: bool = DANSWER_BOT_DISABLE_DOCS_ONLY_ANSWER,
-    disable_cot: bool = DANSWER_BOT_DISABLE_COT,
-    reflexion: bool = ENABLE_DANSWERBOT_REFLEXION,
 ) -> bool:
     channel_conf = slack_channel_config.channel_config if slack_channel_config else None
 
     messages = message_info.thread_messages
+
     message_ts_to_respond_to = message_info.msg_to_respond
     is_bot_msg = message_info.is_bot_msg
     user = None
@@ -102,9 +89,18 @@ def handle_regular_answer(
                 user = get_user_by_email(message_info.email, db_session)
 
     document_set_names: list[str] | None = None
-    persona = slack_channel_config.persona if slack_channel_config else None
     prompt = None
-    if persona:
+    # If no persona is specified, use the default search based persona
+    # This way slack flow always has a persona
+    persona = slack_channel_config.persona if slack_channel_config else None
+    if not persona:
+        with get_session_with_tenant(tenant_id) as db_session:
+            persona = get_persona_by_id(DEFAULT_PERSONA_ID, user, db_session)
+            document_set_names = [
+                document_set.name for document_set in persona.document_sets
+            ]
+            prompt = persona.prompts[0] if persona.prompts else None
+    else:
         document_set_names = [
             document_set.name for document_set in persona.document_sets
         ]
@@ -112,6 +108,26 @@ def handle_regular_answer(
 
     should_respond_even_with_no_docs = persona.num_chunks == 0 if persona else False
 
+    # TODO: Add in support for Slack to truncate messages based on max LLM context
+    # llm, _ = get_llms_for_persona(persona)
+
+    # llm_tokenizer = get_tokenizer(
+    #     model_name=llm.config.model_name,
+    #     provider_type=llm.config.model_provider,
+    # )
+
+    # # In cases of threads, split the available tokens between docs and thread context
+    # input_tokens = get_max_input_tokens(
+    #     model_name=llm.config.model_name,
+    #     model_provider=llm.config.model_provider,
+    # )
+    # max_history_tokens = int(input_tokens * thread_context_percent)
+    # combined_message = combine_message_thread(
+    #     messages, max_tokens=max_history_tokens, llm_tokenizer=llm_tokenizer
+    # )
+
+    combined_message = slackify_message_thread(messages)
+
     bypass_acl = False
     if (
         slack_channel_config
@@ -122,13 +138,6 @@ def handle_regular_answer(
         # with non-public document sets
         bypass_acl = True
 
-    # figure out if we want to use citations or quotes
-    use_citations = (
-        not DANSWER_BOT_USE_QUOTES
-        if slack_channel_config is None
-        else slack_channel_config.response_type == SlackBotResponseType.CITATIONS
-    )
-
     if not message_ts_to_respond_to and not is_bot_msg:
         # if the message is not "/danswer" command, then it should have a message ts to respond to
         raise RuntimeError(
@@ -141,75 +150,23 @@ def handle_regular_answer(
         backoff=2,
     )
     @rate_limits(client=client, channel=channel, thread_ts=message_ts_to_respond_to)
-    def _get_answer(new_message_request: DirectQARequest) -> OneShotQAResponse | None:
-        max_document_tokens: int | None = None
-        max_history_tokens: int | None = None
-
+    def _get_slack_answer(
+        new_message_request: CreateChatMessageRequest, danswer_user: User | None
+    ) -> ChatDanswerBotResponse:
         with get_session_with_tenant(tenant_id) as db_session:
-            if len(new_message_request.messages) > 1:
-                if new_message_request.persona_config:
-                    raise RuntimeError("Slack bot does not support persona config")
-                elif new_message_request.persona_id is not None:
-                    persona = cast(
-                        Persona,
-                        fetch_persona_by_id(
-                            db_session,
-                            new_message_request.persona_id,
-                            user=None,
-                            get_editable=False,
-                        ),
-                    )
-                else:
-                    raise RuntimeError(
-                        "No persona id provided, this should never happen."
-                    )
-
-                llm, _ = get_llms_for_persona(persona)
-
-                # In cases of threads, split the available tokens between docs and thread context
-                input_tokens = get_max_input_tokens(
-                    model_name=llm.config.model_name,
-                    model_provider=llm.config.model_provider,
-                )
-                max_history_tokens = int(input_tokens * thread_context_percent)
-
-                remaining_tokens = input_tokens - max_history_tokens
-
-                query_text = new_message_request.messages[0].message
-                if persona:
-                    max_document_tokens = compute_max_document_tokens_for_persona(
-                        persona=persona,
-                        actual_user_input=query_text,
-                        max_llm_token_override=remaining_tokens,
-                    )
-                else:
-                    max_document_tokens = (
-                        remaining_tokens
-                        - 512  # Needs to be more than any of the QA prompts
-                        - check_number_of_tokens(query_text)
-                    )
-
-            if DISABLE_GENERATIVE_AI:
-                return None
-
-            # This also handles creating the query event in postgres
-            answer = get_search_answer(
-                query_req=new_message_request,
-                user=user,
-                max_document_tokens=max_document_tokens,
-                max_history_tokens=max_history_tokens,
+            packets = stream_chat_message_objects(
+                new_msg_req=new_message_request,
+                user=danswer_user,
                 db_session=db_session,
-                answer_generation_timeout=answer_generation_timeout,
-                enable_reflexion=reflexion,
                 bypass_acl=bypass_acl,
-                use_citations=use_citations,
-                danswerbot_flow=True,
             )
 
-            if not answer.error_msg:
-                return answer
-            else:
-                raise RuntimeError(answer.error_msg)
+            answer = gather_stream_for_slack(packets)
+
+        if answer.error_msg:
+            raise RuntimeError(answer.error_msg)
+
+        return answer
 
     try:
         # By leaving time_cutoff and favor_recent as None, and setting enable_auto_detect_filters
@@ -239,26 +196,24 @@ def handle_regular_answer(
             enable_auto_detect_filters=auto_detect_filters,
         )
 
-        # Always apply reranking settings if it exists, this is the non-streaming flow
         with get_session_with_tenant(tenant_id) as db_session:
-            saved_search_settings = get_current_search_settings(db_session)
-
-        # This includes throwing out answer via reflexion
-        answer = _get_answer(
-            DirectQARequest(
-                messages=messages,
-                multilingual_query_expansion=saved_search_settings.multilingual_expansion
-                if saved_search_settings
-                else None,
-                prompt_id=prompt.id if prompt else None,
-                persona_id=persona.id if persona is not None else 0,
-                retrieval_options=retrieval_details,
-                chain_of_thought=not disable_cot,
-                rerank_settings=RerankingDetails.from_db_model(saved_search_settings)
-                if saved_search_settings
-                else None,
+            answer_request = prepare_chat_message_request(
+                message_text=combined_message,
+                user=user,
+                persona_id=persona.id,
+                # This is not used in the Slack flow, only in the answer API
+                persona_override_config=None,
+                prompt=prompt,
+                message_ts_to_respond_to=message_ts_to_respond_to,
+                retrieval_details=retrieval_details,
+                rerank_settings=None,  # Rerank customization supported in Slack flow
+                db_session=db_session,
             )
+
+        answer = _get_slack_answer(
+            new_message_request=answer_request, danswer_user=user
         )
+
     except Exception as e:
         logger.exception(
             f"Unable to process message - did not successfully answer "
@@ -359,7 +314,7 @@ def handle_regular_answer(
     top_docs = retrieval_info.top_documents
     if not top_docs and not should_respond_even_with_no_docs:
         logger.error(
-            f"Unable to answer question: '{answer.rephrase}' - no documents found"
+            f"Unable to answer question: '{combined_message}' - no documents found"
         )
         # Optionally, respond in thread with the error message
         # Used primarily for debugging purposes
@@ -380,18 +335,18 @@ def handle_regular_answer(
         )
         return True
 
-    only_respond_with_citations_or_quotes = (
+    only_respond_if_citations = (
         channel_conf
         and "well_answered_postfilter" in channel_conf.get("answer_filters", [])
     )
-    has_citations_or_quotes = bool(answer.citations or answer.quotes)
+
     if (
-        only_respond_with_citations_or_quotes
-        and not has_citations_or_quotes
+        only_respond_if_citations
+        and not answer.citations
         and not message_info.bypass_filters
     ):
         logger.error(
-            f"Unable to find citations or quotes to answer: '{answer.rephrase}' - not answering!"
+            f"Unable to find citations to answer: '{answer.answer}' - not answering!"
         )
         # Optionally, respond in thread with the error message
         # Used primarily for debugging purposes
@@ -409,9 +364,8 @@ def handle_regular_answer(
         tenant_id=tenant_id,
         message_info=message_info,
         answer=answer,
-        persona=persona,
         channel_conf=channel_conf,
-        use_citations=use_citations,
+        use_citations=True,  # No longer supporting quotes
         feedback_reminder_id=feedback_reminder_id,
     )
 

backend/danswer/danswerbot/slack/handlers/utils.py

@@ -1,8 +1,33 @@
 from slack_sdk import WebClient
 
+from danswer.chat.models import ThreadMessage
+from danswer.configs.constants import MessageType
 from danswer.danswerbot.slack.utils import respond_in_thread
 
 
+def slackify_message_thread(messages: list[ThreadMessage]) -> str:
+    # Note: this does not handle extremely long threads, every message will be included
+    # with weaker LLMs, this could cause issues with exceeeding the token limit
+    if not messages:
+        return ""
+
+    message_strs: list[str] = []
+    for message in messages:
+        if message.role == MessageType.USER:
+            message_text = (
+                f"{message.sender or 'Unknown User'} said in Slack:\n{message.message}"
+            )
+        elif message.role == MessageType.ASSISTANT:
+            message_text = f"AI said in Slack:\n{message.message}"
+        else:
+            message_text = (
+                f"{message.role.value.upper()} said in Slack:\n{message.message}"
+            )
+        message_strs.append(message_text)
+
+    return "\n\n".join(message_strs)
+
+
 def send_team_member_message(
     client: WebClient,
     channel: str,

backend/danswer/danswerbot/slack/listener.py

@@ -19,6 +19,8 @@ from slack_sdk.socket_mode.request import SocketModeRequest
 from slack_sdk.socket_mode.response import SocketModeResponse
 from sqlalchemy.orm import Session
 
+from danswer.chat.models import ThreadMessage
+from danswer.configs.app_configs import DEV_MODE
 from danswer.configs.app_configs import POD_NAME
 from danswer.configs.app_configs import POD_NAMESPACE
 from danswer.configs.constants import DanswerRedisLocks
@@ -74,7 +76,6 @@ from danswer.db.slack_bot import fetch_slack_bots
 from danswer.key_value_store.interface import KvKeyNotFoundError
 from danswer.natural_language_processing.search_nlp_models import EmbeddingModel
 from danswer.natural_language_processing.search_nlp_models import warm_up_bi_encoder
-from danswer.one_shot_answer.models import ThreadMessage
 from danswer.redis.redis_pool import get_redis_client
 from danswer.server.manage.models import SlackBotTokens
 from danswer.utils.logger import setup_logger
@@ -250,7 +251,7 @@ class SlackbotHandler:
                 nx=True,
                 ex=TENANT_LOCK_EXPIRATION,
             )
-            if not acquired:
+            if not acquired and not DEV_MODE:
                 logger.debug(f"Another pod holds the lock for tenant {tenant_id}")
                 continue
 

backend/danswer/danswerbot/slack/models.py

@@ -1,6 +1,6 @@
 from pydantic import BaseModel
 
-from danswer.one_shot_answer.models import ThreadMessage
+from danswer.chat.models import ThreadMessage
 
 
 class SlackMessageInfo(BaseModel):

backend/danswer/danswerbot/slack/utils.py

@@ -30,13 +30,13 @@ from danswer.configs.danswerbot_configs import (
 from danswer.connectors.slack.utils import make_slack_api_rate_limited
 from danswer.connectors.slack.utils import SlackTextCleaner
 from danswer.danswerbot.slack.constants import FeedbackVisibility
+from danswer.danswerbot.slack.models import ThreadMessage
 from danswer.db.engine import get_session_with_tenant
 from danswer.db.users import get_user_by_email
 from danswer.llm.exceptions import GenAIDisabledException
 from danswer.llm.factory import get_default_llms
 from danswer.llm.utils import dict_based_prompt_to_langchain_prompt
 from danswer.llm.utils import message_to_string
-from danswer.one_shot_answer.models import ThreadMessage
 from danswer.prompts.miscellaneous_prompts import SLACK_LANGUAGE_REPHRASE_PROMPT
 from danswer.utils.logger import setup_logger
 from danswer.utils.telemetry import optional_telemetry

backend/danswer/db/chat.py

@@ -145,16 +145,10 @@ def get_chat_sessions_by_user(
     user_id: UUID | None,
     deleted: bool | None,
     db_session: Session,
-    only_one_shot: bool = False,
     limit: int = 50,
 ) -> list[ChatSession]:
     stmt = select(ChatSession).where(ChatSession.user_id == user_id)
 
-    if only_one_shot:
-        stmt = stmt.where(ChatSession.one_shot.is_(True))
-    else:
-        stmt = stmt.where(ChatSession.one_shot.is_(False))
-
     stmt = stmt.order_by(desc(ChatSession.time_created))
 
     if deleted is not None:
@@ -226,12 +220,11 @@ def delete_messages_and_files_from_chat_session(
 
 def create_chat_session(
     db_session: Session,
-    description: str,
+    description: str | None,
     user_id: UUID | None,
     persona_id: int | None,  # Can be none if temporary persona is used
     llm_override: LLMOverride | None = None,
     prompt_override: PromptOverride | None = None,
-    one_shot: bool = False,
     danswerbot_flow: bool = False,
     slack_thread_id: str | None = None,
 ) -> ChatSession:
@@ -241,7 +234,6 @@ def create_chat_session(
         description=description,
         llm_override=llm_override,
         prompt_override=prompt_override,
-        one_shot=one_shot,
         danswerbot_flow=danswerbot_flow,
         slack_thread_id=slack_thread_id,
     )
@@ -287,8 +279,6 @@ def duplicate_chat_session_for_user_from_slack(
         description="",
         llm_override=chat_session.llm_override,
         prompt_override=chat_session.prompt_override,
-        # Chat sessions from Slack should put people in the chat UI, not the search
-        one_shot=False,
         # Chat is in UI now so this is false
         danswerbot_flow=False,
         # Maybe we want this in the future to track if it was created from Slack

backend/danswer/db/credentials.py

@@ -248,7 +248,6 @@ def create_credential(
     )
 
     db_session.commit()
-
     return credential
 
 

backend/danswer/db/engine.py

@@ -37,6 +37,7 @@ from danswer.configs.app_configs import POSTGRES_PORT
 from danswer.configs.app_configs import POSTGRES_USER
 from danswer.configs.app_configs import USER_AUTH_SECRET
 from danswer.configs.constants import POSTGRES_UNKNOWN_APP_NAME
+from danswer.server.utils import BasicAuthenticationError
 from danswer.utils.logger import setup_logger
 from shared_configs.configs import MULTI_TENANT
 from shared_configs.configs import POSTGRES_DEFAULT_SCHEMA
@@ -426,7 +427,9 @@ def get_session() -> Generator[Session, None, None]:
     """Generate a database session with the appropriate tenant schema set."""
     tenant_id = CURRENT_TENANT_ID_CONTEXTVAR.get()
     if tenant_id == POSTGRES_DEFAULT_SCHEMA and MULTI_TENANT:
-        raise HTTPException(status_code=401, detail="User must authenticate")
+        raise BasicAuthenticationError(
+            detail="User must authenticate",
+        )
 
     engine = get_sqlalchemy_engine()
 

backend/danswer/db/models.py

@@ -1,6 +1,5 @@
 import datetime
 import json
-from enum import Enum as PyEnum
 from typing import Any
 from typing import Literal
 from typing import NotRequired
@@ -964,9 +963,8 @@ class ChatSession(Base):
     persona_id: Mapped[int | None] = mapped_column(
         ForeignKey("persona.id"), nullable=True
     )
-    description: Mapped[str] = mapped_column(Text)
-    # One-shot direct answering, currently the two types of chats are not mixed
-    one_shot: Mapped[bool] = mapped_column(Boolean, default=False)
+    description: Mapped[str | None] = mapped_column(Text, nullable=True)
+    # This chat created by DanswerBot
     danswerbot_flow: Mapped[bool] = mapped_column(Boolean, default=False)
     # Only ever set to True if system is set to not hard-delete chats
     deleted: Mapped[bool] = mapped_column(Boolean, default=False)
@@ -1488,16 +1486,13 @@ class ChannelConfig(TypedDict):
     show_continue_in_web_ui: NotRequired[bool]  # defaults to False
 
 
-class SlackBotResponseType(str, PyEnum):
-    QUOTES = "quotes"
-    CITATIONS = "citations"
-
-
 class SlackChannelConfig(Base):
     __tablename__ = "slack_channel_config"
 
     id: Mapped[int] = mapped_column(primary_key=True)
-    slack_bot_id: Mapped[int] = mapped_column(ForeignKey("slack_bot.id"), nullable=True)
+    slack_bot_id: Mapped[int] = mapped_column(
+        ForeignKey("slack_bot.id"), nullable=False
+    )
     persona_id: Mapped[int | None] = mapped_column(
         ForeignKey("persona.id"), nullable=True
     )
@@ -1505,9 +1500,6 @@ class SlackChannelConfig(Base):
     channel_config: Mapped[ChannelConfig] = mapped_column(
         postgresql.JSONB(), nullable=False
     )
-    response_type: Mapped[SlackBotResponseType] = mapped_column(
-        Enum(SlackBotResponseType, native_enum=False), nullable=False
-    )
 
     enable_auto_filters: Mapped[bool] = mapped_column(
         Boolean, nullable=False, default=False

backend/danswer/db/slack_channel_config.py

@@ -10,7 +10,6 @@ from danswer.db.constants import SLACK_BOT_PERSONA_PREFIX
 from danswer.db.models import ChannelConfig
 from danswer.db.models import Persona
 from danswer.db.models import Persona__DocumentSet
-from danswer.db.models import SlackBotResponseType
 from danswer.db.models import SlackChannelConfig
 from danswer.db.models import User
 from danswer.db.persona import get_default_prompt
@@ -83,7 +82,6 @@ def insert_slack_channel_config(
     slack_bot_id: int,
     persona_id: int | None,
     channel_config: ChannelConfig,
-    response_type: SlackBotResponseType,
     standard_answer_category_ids: list[int],
     enable_auto_filters: bool,
 ) -> SlackChannelConfig:
@@ -115,7 +113,6 @@ def insert_slack_channel_config(
         slack_bot_id=slack_bot_id,
         persona_id=persona_id,
         channel_config=channel_config,
-        response_type=response_type,
         standard_answer_categories=existing_standard_answer_categories,
         enable_auto_filters=enable_auto_filters,
     )
@@ -130,7 +127,6 @@ def update_slack_channel_config(
     slack_channel_config_id: int,
     persona_id: int | None,
     channel_config: ChannelConfig,
-    response_type: SlackBotResponseType,
     standard_answer_category_ids: list[int],
     enable_auto_filters: bool,
 ) -> SlackChannelConfig:
@@ -170,7 +166,6 @@ def update_slack_channel_config(
     # will encounter `violates foreign key constraint` errors
     slack_channel_config.persona_id = persona_id
     slack_channel_config.channel_config = channel_config
-    slack_channel_config.response_type = response_type
     slack_channel_config.standard_answer_categories = list(
         existing_standard_answer_categories
     )

backend/danswer/document_index/vespa/app_config/schemas/danswer_chunk.sd

@@ -4,6 +4,8 @@ schema DANSWER_CHUNK_NAME {
         # Not to be confused with the UUID generated for this chunk which is called documentid by default
         field document_id type string {
             indexing: summary | attribute
+            attribute: fast-search
+            rank: filter
         }
         field chunk_id type int {
             indexing: summary | attribute

backend/danswer/file_processing/extract_file_text.py

@@ -6,6 +6,7 @@ import zipfile
 from collections.abc import Callable
 from collections.abc import Iterator
 from email.parser import Parser as EmailParser
+from io import BytesIO
 from pathlib import Path
 from typing import Any
 from typing import Dict
@@ -15,13 +16,17 @@ import chardet
 import docx  # type: ignore
 import openpyxl  # type: ignore
 import pptx  # type: ignore
+from docx import Document
+from fastapi import UploadFile
 from pypdf import PdfReader
 from pypdf.errors import PdfStreamError
 
 from danswer.configs.constants import DANSWER_METADATA_FILENAME
+from danswer.configs.constants import FileOrigin
 from danswer.file_processing.html_utils import parse_html_page_basic
 from danswer.file_processing.unstructured import get_unstructured_api_key
 from danswer.file_processing.unstructured import unstructured_to_text
+from danswer.file_store.file_store import FileStore
 from danswer.utils.logger import setup_logger
 
 logger = setup_logger()
@@ -375,3 +380,35 @@ def extract_file_text(
             ) from e
         logger.warning(f"Failed to process file {file_name or 'Unknown'}: {str(e)}")
         return ""
+
+
+def convert_docx_to_txt(
+    file: UploadFile, file_store: FileStore, file_path: str
+) -> None:
+    file.file.seek(0)
+    docx_content = file.file.read()
+    doc = Document(BytesIO(docx_content))
+
+    # Extract text from the document
+    full_text = []
+    for para in doc.paragraphs:
+        full_text.append(para.text)
+
+    # Join the extracted text
+    text_content = "\n".join(full_text)
+
+    txt_file_path = docx_to_txt_filename(file_path)
+    file_store.save_file(
+        file_name=txt_file_path,
+        content=BytesIO(text_content.encode("utf-8")),
+        display_name=file.filename,
+        file_origin=FileOrigin.CONNECTOR,
+        file_type="text/plain",
+    )
+
+
+def docx_to_txt_filename(file_path: str) -> str:
+    """
+    Convert a .docx file path to its corresponding .txt file path.
+    """
+    return file_path.rsplit(".", 1)[0] + ".txt"

backend/danswer/file_store/utils.py

@@ -1,6 +1,6 @@
+import base64
 from collections.abc import Callable
 from io import BytesIO
-from typing import Any
 from typing import cast
 from uuid import uuid4
 
@@ -13,8 +13,8 @@ from danswer.db.models import ChatMessage
 from danswer.file_store.file_store import get_default_file_store
 from danswer.file_store.models import FileDescriptor
 from danswer.file_store.models import InMemoryChatFile
+from danswer.utils.b64 import get_image_type
 from danswer.utils.threadpool_concurrency import run_functions_tuples_in_parallel
-from shared_configs.contextvars import CURRENT_TENANT_ID_CONTEXTVAR
 
 
 def load_chat_file(
@@ -75,11 +75,58 @@ def save_file_from_url(url: str, tenant_id: str) -> str:
         return unique_id
 
 
-def save_files_from_urls(urls: list[str]) -> list[str]:
-    tenant_id = CURRENT_TENANT_ID_CONTEXTVAR.get()
+def save_file_from_base64(base64_string: str, tenant_id: str) -> str:
+    with get_session_with_tenant(tenant_id) as db_session:
+        unique_id = str(uuid4())
+        file_store = get_default_file_store(db_session)
+        file_store.save_file(
+            file_name=unique_id,
+            content=BytesIO(base64.b64decode(base64_string)),
+            display_name="GeneratedImage",
+            file_origin=FileOrigin.CHAT_IMAGE_GEN,
+            file_type=get_image_type(base64_string),
+        )
+        return unique_id
 
-    funcs: list[tuple[Callable[..., Any], tuple[Any, ...]]] = [
-        (save_file_from_url, (url, tenant_id)) for url in urls
+
+def save_file(
+    tenant_id: str,
+    url: str | None = None,
+    base64_data: str | None = None,
+) -> str:
+    """Save a file from either a URL or base64 encoded string.
+
+    Args:
+        tenant_id: The tenant ID to save the file under
+        url: URL to download file from
+        base64_data: Base64 encoded file data
+
+    Returns:
+        The unique ID of the saved file
+
+    Raises:
+        ValueError: If neither url nor base64_data is provided, or if both are provided
+    """
+    if url is not None and base64_data is not None:
+        raise ValueError("Cannot specify both url and base64_data")
+
+    if url is not None:
+        return save_file_from_url(url, tenant_id)
+    elif base64_data is not None:
+        return save_file_from_base64(base64_data, tenant_id)
+    else:
+        raise ValueError("Must specify either url or base64_data")
+
+
+def save_files(urls: list[str], base64_files: list[str], tenant_id: str) -> list[str]:
+    # NOTE: be explicit about typing so that if we change things, we get notified
+    funcs: list[
+        tuple[
+            Callable[[str, str | None, str | None], str],
+            tuple[str, str | None, str | None],
+        ]
+    ] = [(save_file, (tenant_id, url, None)) for url in urls] + [
+        (save_file, (tenant_id, None, base64_file)) for base64_file in base64_files
     ]
-    # Must pass in tenant_id here, since this is called by multithreading
+
     return run_functions_tuples_in_parallel(funcs)

backend/danswer/llm/answering/models.py

@@ -1,163 +0,0 @@
-from collections.abc import Callable
-from collections.abc import Iterator
-from typing import TYPE_CHECKING
-
-from langchain.schema.messages import AIMessage
-from langchain.schema.messages import BaseMessage
-from langchain.schema.messages import HumanMessage
-from langchain.schema.messages import SystemMessage
-from pydantic import BaseModel
-from pydantic import ConfigDict
-from pydantic import Field
-from pydantic import model_validator
-
-from danswer.chat.models import AnswerQuestionStreamReturn
-from danswer.configs.constants import MessageType
-from danswer.file_store.models import InMemoryChatFile
-from danswer.llm.override_models import PromptOverride
-from danswer.llm.utils import build_content_with_imgs
-from danswer.tools.models import ToolCallFinalResult
-
-if TYPE_CHECKING:
-    from danswer.db.models import ChatMessage
-    from danswer.db.models import Prompt
-
-
-StreamProcessor = Callable[[Iterator[str]], AnswerQuestionStreamReturn]
-
-
-class PreviousMessage(BaseModel):
-    """Simplified version of `ChatMessage`"""
-
-    message: str
-    token_count: int
-    message_type: MessageType
-    files: list[InMemoryChatFile]
-    tool_call: ToolCallFinalResult | None
-
-    @classmethod
-    def from_chat_message(
-        cls, chat_message: "ChatMessage", available_files: list[InMemoryChatFile]
-    ) -> "PreviousMessage":
-        message_file_ids = (
-            [file["id"] for file in chat_message.files] if chat_message.files else []
-        )
-        return cls(
-            message=chat_message.message,
-            token_count=chat_message.token_count,
-            message_type=chat_message.message_type,
-            files=[
-                file
-                for file in available_files
-                if str(file.file_id) in message_file_ids
-            ],
-            tool_call=ToolCallFinalResult(
-                tool_name=chat_message.tool_call.tool_name,
-                tool_args=chat_message.tool_call.tool_arguments,
-                tool_result=chat_message.tool_call.tool_result,
-            )
-            if chat_message.tool_call
-            else None,
-        )
-
-    def to_langchain_msg(self) -> BaseMessage:
-        content = build_content_with_imgs(self.message, self.files)
-        if self.message_type == MessageType.USER:
-            return HumanMessage(content=content)
-        elif self.message_type == MessageType.ASSISTANT:
-            return AIMessage(content=content)
-        else:
-            return SystemMessage(content=content)
-
-
-class DocumentPruningConfig(BaseModel):
-    max_chunks: int | None = None
-    max_window_percentage: float | None = None
-    max_tokens: int | None = None
-    # different pruning behavior is expected when the
-    # user manually selects documents they want to chat with
-    # e.g. we don't want to truncate each document to be no more
-    # than one chunk long
-    is_manually_selected_docs: bool = False
-    # If user specifies to include additional context Chunks for each match, then different pruning
-    # is used. As many Sections as possible are included, and the last Section is truncated
-    # If this is false, all of the Sections are truncated if they are longer than the expected Chunk size.
-    # Sections are often expected to be longer than the maximum Chunk size but Chunks should not be.
-    use_sections: bool = True
-    # If using tools, then we need to consider the tool length
-    tool_num_tokens: int = 0
-    # If using a tool message to represent the docs, then we have to JSON serialize
-    # the document content, which adds to the token count.
-    using_tool_message: bool = False
-
-
-class ContextualPruningConfig(DocumentPruningConfig):
-    num_chunk_multiple: int
-
-    @classmethod
-    def from_doc_pruning_config(
-        cls, num_chunk_multiple: int, doc_pruning_config: DocumentPruningConfig
-    ) -> "ContextualPruningConfig":
-        return cls(num_chunk_multiple=num_chunk_multiple, **doc_pruning_config.dict())
-
-
-class CitationConfig(BaseModel):
-    all_docs_useful: bool = False
-
-
-class QuotesConfig(BaseModel):
-    pass
-
-
-class AnswerStyleConfig(BaseModel):
-    citation_config: CitationConfig | None = None
-    quotes_config: QuotesConfig | None = None
-    document_pruning_config: DocumentPruningConfig = Field(
-        default_factory=DocumentPruningConfig
-    )
-    # forces the LLM to return a structured response, see
-    # https://platform.openai.com/docs/guides/structured-outputs/introduction
-    # right now, only used by the simple chat API
-    structured_response_format: dict | None = None
-
-    @model_validator(mode="after")
-    def check_quotes_and_citation(self) -> "AnswerStyleConfig":
-        if self.citation_config is None and self.quotes_config is None:
-            raise ValueError(
-                "One of `citation_config` or `quotes_config` must be provided"
-            )
-
-        if self.citation_config is not None and self.quotes_config is not None:
-            raise ValueError(
-                "Only one of `citation_config` or `quotes_config` must be provided"
-            )
-
-        return self
-
-
-class PromptConfig(BaseModel):
-    """Final representation of the Prompt configuration passed
-    into the `Answer` object."""
-
-    system_prompt: str
-    task_prompt: str
-    datetime_aware: bool
-    include_citations: bool
-
-    @classmethod
-    def from_model(
-        cls, model: "Prompt", prompt_override: PromptOverride | None = None
-    ) -> "PromptConfig":
-        override_system_prompt = (
-            prompt_override.system_prompt if prompt_override else None
-        )
-        override_task_prompt = prompt_override.task_prompt if prompt_override else None
-
-        return cls(
-            system_prompt=override_system_prompt or model.system_prompt,
-            task_prompt=override_task_prompt or model.task_prompt,
-            datetime_aware=model.datetime_aware,
-            include_citations=model.include_citations,
-        )
-
-    model_config = ConfigDict(frozen=True)

backend/danswer/llm/answering/prompts/utils.py

@@ -1,20 +0,0 @@
-from danswer.prompts.direct_qa_prompts import PARAMATERIZED_PROMPT
-from danswer.prompts.direct_qa_prompts import PARAMATERIZED_PROMPT_WITHOUT_CONTEXT
-
-
-def build_dummy_prompt(
-    system_prompt: str, task_prompt: str, retrieval_disabled: bool
-) -> str:
-    if retrieval_disabled:
-        return PARAMATERIZED_PROMPT_WITHOUT_CONTEXT.format(
-            user_query="<USER_QUERY>",
-            system_prompt=system_prompt,
-            task_prompt=task_prompt,
-        ).strip()
-
-    return PARAMATERIZED_PROMPT.format(
-        context_docs_str="<CONTEXT_DOCS>",
-        user_query="<USER_QUERY>",
-        system_prompt=system_prompt,
-        task_prompt=task_prompt,
-    ).strip()

backend/danswer/llm/factory.py

@@ -1,5 +1,6 @@
 from typing import Any
 
+from danswer.chat.models import PersonaOverrideConfig
 from danswer.configs.app_configs import DISABLE_GENERATIVE_AI
 from danswer.configs.chat_configs import QA_TIMEOUT
 from danswer.configs.model_configs import GEN_AI_MODEL_FALLBACK_MAX_TOKENS
@@ -13,8 +14,11 @@ from danswer.llm.exceptions import GenAIDisabledException
 from danswer.llm.interfaces import LLM
 from danswer.llm.override_models import LLMOverride
 from danswer.utils.headers import build_llm_extra_headers
+from danswer.utils.logger import setup_logger
 from danswer.utils.long_term_log import LongTermLogger
 
+logger = setup_logger()
+
 
 def _build_extra_model_kwargs(provider: str) -> dict[str, Any]:
     """Ollama requires us to specify the max context window.
@@ -32,11 +36,15 @@ def get_main_llm_from_tuple(
 
 
 def get_llms_for_persona(
-    persona: Persona,
+    persona: Persona | PersonaOverrideConfig | None,
     llm_override: LLMOverride | None = None,
     additional_headers: dict[str, str] | None = None,
     long_term_logger: LongTermLogger | None = None,
 ) -> tuple[LLM, LLM]:
+    if persona is None:
+        logger.warning("No persona provided, using default LLMs")
+        return get_default_llms()
+
     model_provider_override = llm_override.model_provider if llm_override else None
     model_version_override = llm_override.model_version if llm_override else None
     temperature_override = llm_override.temperature if llm_override else None

backend/danswer/llm/models.py

@@ -0,0 +1,59 @@
+from typing import TYPE_CHECKING
+
+from langchain.schema.messages import AIMessage
+from langchain.schema.messages import BaseMessage
+from langchain.schema.messages import HumanMessage
+from langchain.schema.messages import SystemMessage
+from pydantic import BaseModel
+
+from danswer.configs.constants import MessageType
+from danswer.file_store.models import InMemoryChatFile
+from danswer.llm.utils import build_content_with_imgs
+from danswer.tools.models import ToolCallFinalResult
+
+if TYPE_CHECKING:
+    from danswer.db.models import ChatMessage
+
+
+class PreviousMessage(BaseModel):
+    """Simplified version of `ChatMessage`"""
+
+    message: str
+    token_count: int
+    message_type: MessageType
+    files: list[InMemoryChatFile]
+    tool_call: ToolCallFinalResult | None
+
+    @classmethod
+    def from_chat_message(
+        cls, chat_message: "ChatMessage", available_files: list[InMemoryChatFile]
+    ) -> "PreviousMessage":
+        message_file_ids = (
+            [file["id"] for file in chat_message.files] if chat_message.files else []
+        )
+        return cls(
+            message=chat_message.message,
+            token_count=chat_message.token_count,
+            message_type=chat_message.message_type,
+            files=[
+                file
+                for file in available_files
+                if str(file.file_id) in message_file_ids
+            ],
+            tool_call=ToolCallFinalResult(
+                tool_name=chat_message.tool_call.tool_name,
+                tool_args=chat_message.tool_call.tool_arguments,
+                tool_result=chat_message.tool_call.tool_result,
+            )
+            if chat_message.tool_call
+            else None,
+        )
+
+    def to_langchain_msg(self) -> BaseMessage:
+        content = build_content_with_imgs(self.message, self.files)
+        if self.message_type == MessageType.USER:
+            return HumanMessage(content=content)
+        elif self.message_type == MessageType.ASSISTANT:
+            return AIMessage(content=content)
+        else:
+            return SystemMessage(content=content)

backend/danswer/llm/utils.py

@@ -5,8 +5,6 @@ from collections.abc import Callable
 from collections.abc import Iterator
 from typing import Any
 from typing import cast
-from typing import TYPE_CHECKING
-from typing import Union
 
 import litellm  # type: ignore
 import pandas as pd
@@ -36,17 +34,15 @@ from danswer.configs.constants import MessageType
 from danswer.configs.model_configs import GEN_AI_MAX_TOKENS
 from danswer.configs.model_configs import GEN_AI_MODEL_FALLBACK_MAX_TOKENS
 from danswer.configs.model_configs import GEN_AI_NUM_RESERVED_OUTPUT_TOKENS
-from danswer.db.models import ChatMessage
 from danswer.file_store.models import ChatFileType
 from danswer.file_store.models import InMemoryChatFile
 from danswer.llm.interfaces import LLM
 from danswer.prompts.constants import CODE_BLOCK_PAT
+from danswer.utils.b64 import get_image_type
+from danswer.utils.b64 import get_image_type_from_bytes
 from danswer.utils.logger import setup_logger
 from shared_configs.configs import LOG_LEVEL
 
-if TYPE_CHECKING:
-    from danswer.llm.answering.models import PreviousMessage
-
 logger = setup_logger()
 
 
@@ -104,39 +100,6 @@ def litellm_exception_to_error_msg(
     return error_msg
 
 
-def translate_danswer_msg_to_langchain(
-    msg: Union[ChatMessage, "PreviousMessage"],
-) -> BaseMessage:
-    files: list[InMemoryChatFile] = []
-
-    # If the message is a `ChatMessage`, it doesn't have the downloaded files
-    # attached. Just ignore them for now.
-    if not isinstance(msg, ChatMessage):
-        files = msg.files
-    content = build_content_with_imgs(msg.message, files, message_type=msg.message_type)
-
-    if msg.message_type == MessageType.SYSTEM:
-        raise ValueError("System messages are not currently part of history")
-    if msg.message_type == MessageType.ASSISTANT:
-        return AIMessage(content=content)
-    if msg.message_type == MessageType.USER:
-        return HumanMessage(content=content)
-
-    raise ValueError(f"New message type {msg.message_type} not handled")
-
-
-def translate_history_to_basemessages(
-    history: list[ChatMessage] | list["PreviousMessage"],
-) -> tuple[list[BaseMessage], list[int]]:
-    history_basemessages = [
-        translate_danswer_msg_to_langchain(msg)
-        for msg in history
-        if msg.token_count != 0
-    ]
-    history_token_counts = [msg.token_count for msg in history if msg.token_count != 0]
-    return history_basemessages, history_token_counts
-
-
 #  Processes CSV files to show the first 5 rows and max_columns (default 40) columns
 def _process_csv_file(file: InMemoryChatFile, max_columns: int = 40) -> str:
     df = pd.read_csv(io.StringIO(file.content.decode("utf-8")))
@@ -190,6 +153,7 @@ def build_content_with_imgs(
     message: str,
     files: list[InMemoryChatFile] | None = None,
     img_urls: list[str] | None = None,
+    b64_imgs: list[str] | None = None,
     message_type: MessageType = MessageType.USER,
 ) -> str | list[str | dict[str, Any]]:  # matching Langchain's BaseMessage content type
     files = files or []
@@ -202,6 +166,7 @@ def build_content_with_imgs(
     )
 
     img_urls = img_urls or []
+    b64_imgs = b64_imgs or []
 
     message_main_content = _build_content(message, files)
 
@@ -220,11 +185,22 @@ def build_content_with_imgs(
             {
                 "type": "image_url",
                 "image_url": {
-                    "url": f"data:image/jpeg;base64,{file.to_base64()}",
+                    "url": (
+                        f"data:{get_image_type_from_bytes(file.content)};"
+                        f"base64,{file.to_base64()}"
+                    ),
                 },
             }
-            for file in files
-            if file.file_type == "image"
+            for file in img_files
+        ]
+        + [
+            {
+                "type": "image_url",
+                "image_url": {
+                    "url": f"data:{get_image_type(b64_img)};base64,{b64_img}",
+                },
+            }
+            for b64_img in b64_imgs
         ]
         + [
             {

backend/danswer/main.py

@@ -25,7 +25,6 @@ from danswer.auth.schemas import UserCreate
 from danswer.auth.schemas import UserRead
 from danswer.auth.schemas import UserUpdate
 from danswer.auth.users import auth_backend
-from danswer.auth.users import BasicAuthenticationError
 from danswer.auth.users import create_danswer_oauth_router
 from danswer.auth.users import fastapi_users
 from danswer.configs.app_configs import APP_API_PREFIX
@@ -92,6 +91,7 @@ from danswer.server.settings.api import basic_router as settings_router
 from danswer.server.token_rate_limits.api import (
     router as token_rate_limit_settings_router,
 )
+from danswer.server.utils import BasicAuthenticationError
 from danswer.setup import setup_danswer
 from danswer.setup import setup_multitenant_danswer
 from danswer.utils.logger import setup_logger
@@ -105,7 +105,6 @@ from shared_configs.configs import CORS_ALLOWED_ORIGIN
 from shared_configs.configs import MULTI_TENANT
 from shared_configs.configs import SENTRY_DSN
 
-
 logger = setup_logger()
 
 
@@ -206,7 +205,7 @@ def log_http_error(_: Request, exc: Exception) -> JSONResponse:
 
     if isinstance(exc, BasicAuthenticationError):
         # For BasicAuthenticationError, just log a brief message without stack trace (almost always spam)
-        logger.error(f"Authentication failed: {str(exc)}")
+        logger.warning(f"Authentication failed: {str(exc)}")
 
     elif status_code >= 400:
         error_msg = f"{str(exc)}\n"

backend/danswer/one_shot_answer/answer_question.py

@@ -1,456 +0,0 @@
-from collections.abc import Callable
-from collections.abc import Iterator
-from typing import cast
-
-from sqlalchemy.orm import Session
-
-from danswer.chat.chat_utils import reorganize_citations
-from danswer.chat.models import CitationInfo
-from danswer.chat.models import DanswerAnswerPiece
-from danswer.chat.models import DanswerContexts
-from danswer.chat.models import DanswerQuotes
-from danswer.chat.models import DocumentRelevance
-from danswer.chat.models import LLMRelevanceFilterResponse
-from danswer.chat.models import QADocsResponse
-from danswer.chat.models import RelevanceAnalysis
-from danswer.chat.models import StreamingError
-from danswer.configs.chat_configs import DISABLE_LLM_DOC_RELEVANCE
-from danswer.configs.chat_configs import MAX_CHUNKS_FED_TO_CHAT
-from danswer.configs.chat_configs import QA_TIMEOUT
-from danswer.configs.constants import MessageType
-from danswer.context.search.enums import LLMEvaluationType
-from danswer.context.search.models import RerankMetricsContainer
-from danswer.context.search.models import RetrievalMetricsContainer
-from danswer.context.search.utils import chunks_or_sections_to_search_docs
-from danswer.context.search.utils import dedupe_documents
-from danswer.db.chat import create_chat_session
-from danswer.db.chat import create_db_search_doc
-from danswer.db.chat import create_new_chat_message
-from danswer.db.chat import get_or_create_root_message
-from danswer.db.chat import translate_db_message_to_chat_message_detail
-from danswer.db.chat import translate_db_search_doc_to_server_search_doc
-from danswer.db.chat import update_search_docs_table_with_relevance
-from danswer.db.engine import get_session_context_manager
-from danswer.db.models import Persona
-from danswer.db.models import User
-from danswer.db.persona import get_prompt_by_id
-from danswer.llm.answering.answer import Answer
-from danswer.llm.answering.models import AnswerStyleConfig
-from danswer.llm.answering.models import CitationConfig
-from danswer.llm.answering.models import DocumentPruningConfig
-from danswer.llm.answering.models import PromptConfig
-from danswer.llm.answering.models import QuotesConfig
-from danswer.llm.factory import get_llms_for_persona
-from danswer.llm.factory import get_main_llm_from_tuple
-from danswer.natural_language_processing.utils import get_tokenizer
-from danswer.one_shot_answer.models import DirectQARequest
-from danswer.one_shot_answer.models import OneShotQAResponse
-from danswer.one_shot_answer.models import QueryRephrase
-from danswer.one_shot_answer.qa_utils import combine_message_thread
-from danswer.one_shot_answer.qa_utils import slackify_message_thread
-from danswer.secondary_llm_flows.answer_validation import get_answer_validity
-from danswer.secondary_llm_flows.query_expansion import thread_based_query_rephrase
-from danswer.server.query_and_chat.models import ChatMessageDetail
-from danswer.server.utils import get_json_line
-from danswer.tools.force import ForceUseTool
-from danswer.tools.models import ToolResponse
-from danswer.tools.tool_implementations.search.search_tool import SEARCH_DOC_CONTENT_ID
-from danswer.tools.tool_implementations.search.search_tool import (
-    SEARCH_RESPONSE_SUMMARY_ID,
-)
-from danswer.tools.tool_implementations.search.search_tool import SearchResponseSummary
-from danswer.tools.tool_implementations.search.search_tool import SearchTool
-from danswer.tools.tool_implementations.search.search_tool import (
-    SECTION_RELEVANCE_LIST_ID,
-)
-from danswer.tools.tool_runner import ToolCallKickoff
-from danswer.utils.logger import setup_logger
-from danswer.utils.long_term_log import LongTermLogger
-from danswer.utils.timing import log_generator_function_time
-from danswer.utils.variable_functionality import fetch_ee_implementation_or_noop
-
-logger = setup_logger()
-
-AnswerObjectIterator = Iterator[
-    QueryRephrase
-    | QADocsResponse
-    | LLMRelevanceFilterResponse
-    | DanswerAnswerPiece
-    | DanswerQuotes
-    | DanswerContexts
-    | StreamingError
-    | ChatMessageDetail
-    | CitationInfo
-    | ToolCallKickoff
-    | DocumentRelevance
-]
-
-
-def stream_answer_objects(
-    query_req: DirectQARequest,
-    user: User | None,
-    # These need to be passed in because in Web UI one shot flow,
-    # we can have much more document as there is no history.
-    # For Slack flow, we need to save more tokens for the thread context
-    max_document_tokens: int | None,
-    max_history_tokens: int | None,
-    db_session: Session,
-    # Needed to translate persona num_chunks to tokens to the LLM
-    default_num_chunks: float = MAX_CHUNKS_FED_TO_CHAT,
-    timeout: int = QA_TIMEOUT,
-    bypass_acl: bool = False,
-    use_citations: bool = False,
-    danswerbot_flow: bool = False,
-    retrieval_metrics_callback: (
-        Callable[[RetrievalMetricsContainer], None] | None
-    ) = None,
-    rerank_metrics_callback: Callable[[RerankMetricsContainer], None] | None = None,
-) -> AnswerObjectIterator:
-    """Streams in order:
-    1. [always] Retrieved documents, stops flow if nothing is found
-    2. [conditional] LLM selected chunk indices if LLM chunk filtering is turned on
-    3. [always] A set of streamed DanswerAnswerPiece and DanswerQuotes at the end
-                or an error anywhere along the line if something fails
-    4. [always] Details on the final AI response message that is created
-    """
-    user_id = user.id if user is not None else None
-    query_msg = query_req.messages[-1]
-    history = query_req.messages[:-1]
-
-    chat_session = create_chat_session(
-        db_session=db_session,
-        description="",  # One shot queries don't need naming as it's never displayed
-        user_id=user_id,
-        persona_id=query_req.persona_id,
-        one_shot=True,
-        danswerbot_flow=danswerbot_flow,
-    )
-
-    # permanent "log" store, used primarily for debugging
-    long_term_logger = LongTermLogger(
-        metadata={"user_id": str(user_id), "chat_session_id": str(chat_session.id)}
-    )
-
-    temporary_persona: Persona | None = None
-
-    if query_req.persona_config is not None:
-        temporary_persona = fetch_ee_implementation_or_noop(
-            "danswer.server.query_and_chat.utils", "create_temporary_persona", None
-        )(db_session=db_session, persona_config=query_req.persona_config, user=user)
-
-    persona = temporary_persona if temporary_persona else chat_session.persona
-
-    try:
-        llm, fast_llm = get_llms_for_persona(
-            persona=persona, long_term_logger=long_term_logger
-        )
-    except ValueError as e:
-        logger.error(
-            f"Failed to initialize LLMs for persona '{persona.name}': {str(e)}"
-        )
-        if "No LLM provider" in str(e):
-            raise ValueError(
-                "Please configure a Generative AI model to use this feature."
-            ) from e
-        raise ValueError(
-            "Failed to initialize the AI model. Please check your configuration and try again."
-        ) from e
-
-    llm_tokenizer = get_tokenizer(
-        model_name=llm.config.model_name,
-        provider_type=llm.config.model_provider,
-    )
-
-    # Create a chat session which will just store the root message, the query, and the AI response
-    root_message = get_or_create_root_message(
-        chat_session_id=chat_session.id, db_session=db_session
-    )
-
-    history_str = combine_message_thread(
-        messages=history,
-        max_tokens=max_history_tokens,
-        llm_tokenizer=llm_tokenizer,
-    )
-
-    rephrased_query = query_req.query_override or thread_based_query_rephrase(
-        user_query=query_msg.message,
-        history_str=history_str,
-    )
-
-    # Given back ahead of the documents for latency reasons
-    # In chat flow it's given back along with the documents
-    yield QueryRephrase(rephrased_query=rephrased_query)
-
-    prompt = None
-    if query_req.prompt_id is not None:
-        # NOTE: let the user access any prompt as long as the Persona is shared
-        # with them
-        prompt = get_prompt_by_id(
-            prompt_id=query_req.prompt_id, user=None, db_session=db_session
-        )
-    if prompt is None:
-        if not persona.prompts:
-            raise RuntimeError(
-                "Persona does not have any prompts - this should never happen"
-            )
-        prompt = persona.prompts[0]
-
-    user_message_str = query_msg.message
-    # For this endpoint, we only save one user message to the chat session
-    # However, for slackbot, we want to include the history of the entire thread
-    if danswerbot_flow:
-        # Right now, we only support bringing over citations and search docs
-        # from the last message in the thread, not the entire thread
-        # in the future, we may want to retrieve the entire thread
-        user_message_str = slackify_message_thread(query_req.messages)
-
-    # Create the first User query message
-    new_user_message = create_new_chat_message(
-        chat_session_id=chat_session.id,
-        parent_message=root_message,
-        prompt_id=query_req.prompt_id,
-        message=user_message_str,
-        token_count=len(llm_tokenizer.encode(user_message_str)),
-        message_type=MessageType.USER,
-        db_session=db_session,
-        commit=True,
-    )
-
-    prompt_config = PromptConfig.from_model(prompt)
-    document_pruning_config = DocumentPruningConfig(
-        max_chunks=int(
-            persona.num_chunks if persona.num_chunks is not None else default_num_chunks
-        ),
-        max_tokens=max_document_tokens,
-    )
-
-    answer_config = AnswerStyleConfig(
-        citation_config=CitationConfig() if use_citations else None,
-        quotes_config=QuotesConfig() if not use_citations else None,
-        document_pruning_config=document_pruning_config,
-    )
-
-    search_tool = SearchTool(
-        db_session=db_session,
-        user=user,
-        evaluation_type=(
-            LLMEvaluationType.SKIP
-            if DISABLE_LLM_DOC_RELEVANCE
-            else query_req.evaluation_type
-        ),
-        persona=persona,
-        retrieval_options=query_req.retrieval_options,
-        prompt_config=prompt_config,
-        llm=llm,
-        fast_llm=fast_llm,
-        pruning_config=document_pruning_config,
-        answer_style_config=answer_config,
-        bypass_acl=bypass_acl,
-        chunks_above=query_req.chunks_above,
-        chunks_below=query_req.chunks_below,
-        full_doc=query_req.full_doc,
-    )
-
-    answer = Answer(
-        question=query_msg.message,
-        answer_style_config=answer_config,
-        prompt_config=PromptConfig.from_model(prompt),
-        llm=get_main_llm_from_tuple(
-            get_llms_for_persona(persona=persona, long_term_logger=long_term_logger)
-        ),
-        single_message_history=history_str,
-        tools=[search_tool] if search_tool else [],
-        force_use_tool=(
-            ForceUseTool(
-                tool_name=search_tool.name,
-                args={"query": rephrased_query},
-                force_use=True,
-            )
-        ),
-        # for now, don't use tool calling for this flow, as we haven't
-        # tested quotes with tool calling too much yet
-        skip_explicit_tool_calling=True,
-        return_contexts=query_req.return_contexts,
-        skip_gen_ai_answer_generation=query_req.skip_gen_ai_answer_generation,
-    )
-    # won't be any FileChatDisplay responses since that tool is never passed in
-    for packet in cast(AnswerObjectIterator, answer.processed_streamed_output):
-        # for one-shot flow, don't currently do anything with these
-        if isinstance(packet, ToolResponse):
-            # (likely fine that it comes after the initial creation of the search docs)
-            if packet.id == SEARCH_RESPONSE_SUMMARY_ID:
-                search_response_summary = cast(SearchResponseSummary, packet.response)
-
-                top_docs = chunks_or_sections_to_search_docs(
-                    search_response_summary.top_sections
-                )
-
-                # Deduping happens at the last step to avoid harming quality by dropping content early on
-                deduped_docs = top_docs
-                if query_req.retrieval_options.dedupe_docs:
-                    deduped_docs, dropped_inds = dedupe_documents(top_docs)
-
-                reference_db_search_docs = [
-                    create_db_search_doc(server_search_doc=doc, db_session=db_session)
-                    for doc in deduped_docs
-                ]
-
-                response_docs = [
-                    translate_db_search_doc_to_server_search_doc(db_search_doc)
-                    for db_search_doc in reference_db_search_docs
-                ]
-
-                initial_response = QADocsResponse(
-                    rephrased_query=rephrased_query,
-                    top_documents=response_docs,
-                    predicted_flow=search_response_summary.predicted_flow,
-                    predicted_search=search_response_summary.predicted_search,
-                    applied_source_filters=search_response_summary.final_filters.source_type,
-                    applied_time_cutoff=search_response_summary.final_filters.time_cutoff,
-                    recency_bias_multiplier=search_response_summary.recency_bias_multiplier,
-                )
-
-                yield initial_response
-
-            elif packet.id == SEARCH_DOC_CONTENT_ID:
-                yield packet.response
-
-            elif packet.id == SECTION_RELEVANCE_LIST_ID:
-                document_based_response = {}
-
-                if packet.response is not None:
-                    for evaluation in packet.response:
-                        document_based_response[
-                            evaluation.document_id
-                        ] = RelevanceAnalysis(
-                            relevant=evaluation.relevant, content=evaluation.content
-                        )
-
-                evaluation_response = DocumentRelevance(
-                    relevance_summaries=document_based_response
-                )
-                if reference_db_search_docs is not None:
-                    update_search_docs_table_with_relevance(
-                        db_session=db_session,
-                        reference_db_search_docs=reference_db_search_docs,
-                        relevance_summary=evaluation_response,
-                    )
-                yield evaluation_response
-
-        else:
-            yield packet
-
-    # Saving Gen AI answer and responding with message info
-    gen_ai_response_message = create_new_chat_message(
-        chat_session_id=chat_session.id,
-        parent_message=new_user_message,
-        prompt_id=query_req.prompt_id,
-        message=answer.llm_answer,
-        token_count=len(llm_tokenizer.encode(answer.llm_answer)),
-        message_type=MessageType.ASSISTANT,
-        error=None,
-        reference_docs=reference_db_search_docs,
-        db_session=db_session,
-        commit=True,
-    )
-
-    msg_detail_response = translate_db_message_to_chat_message_detail(
-        gen_ai_response_message
-    )
-    yield msg_detail_response
-
-
-@log_generator_function_time()
-def stream_search_answer(
-    query_req: DirectQARequest,
-    user: User | None,
-    max_document_tokens: int | None,
-    max_history_tokens: int | None,
-) -> Iterator[str]:
-    with get_session_context_manager() as session:
-        objects = stream_answer_objects(
-            query_req=query_req,
-            user=user,
-            max_document_tokens=max_document_tokens,
-            max_history_tokens=max_history_tokens,
-            db_session=session,
-        )
-        for obj in objects:
-            yield get_json_line(obj.model_dump())
-
-
-def get_search_answer(
-    query_req: DirectQARequest,
-    user: User | None,
-    max_document_tokens: int | None,
-    max_history_tokens: int | None,
-    db_session: Session,
-    answer_generation_timeout: int = QA_TIMEOUT,
-    enable_reflexion: bool = False,
-    bypass_acl: bool = False,
-    use_citations: bool = False,
-    danswerbot_flow: bool = False,
-    retrieval_metrics_callback: (
-        Callable[[RetrievalMetricsContainer], None] | None
-    ) = None,
-    rerank_metrics_callback: Callable[[RerankMetricsContainer], None] | None = None,
-) -> OneShotQAResponse:
-    """Collects the streamed one shot answer responses into a single object"""
-    qa_response = OneShotQAResponse()
-
-    results = stream_answer_objects(
-        query_req=query_req,
-        user=user,
-        max_document_tokens=max_document_tokens,
-        max_history_tokens=max_history_tokens,
-        db_session=db_session,
-        bypass_acl=bypass_acl,
-        use_citations=use_citations,
-        danswerbot_flow=danswerbot_flow,
-        timeout=answer_generation_timeout,
-        retrieval_metrics_callback=retrieval_metrics_callback,
-        rerank_metrics_callback=rerank_metrics_callback,
-    )
-
-    answer = ""
-    for packet in results:
-        if isinstance(packet, QueryRephrase):
-            qa_response.rephrase = packet.rephrased_query
-        if isinstance(packet, DanswerAnswerPiece) and packet.answer_piece:
-            answer += packet.answer_piece
-        elif isinstance(packet, QADocsResponse):
-            qa_response.docs = packet
-        elif isinstance(packet, LLMRelevanceFilterResponse):
-            qa_response.llm_selected_doc_indices = packet.llm_selected_doc_indices
-        elif isinstance(packet, DanswerQuotes):
-            qa_response.quotes = packet
-        elif isinstance(packet, CitationInfo):
-            if qa_response.citations:
-                qa_response.citations.append(packet)
-            else:
-                qa_response.citations = [packet]
-        elif isinstance(packet, DanswerContexts):
-            qa_response.contexts = packet
-        elif isinstance(packet, StreamingError):
-            qa_response.error_msg = packet.error
-        elif isinstance(packet, ChatMessageDetail):
-            qa_response.chat_message_id = packet.message_id
-
-    if answer:
-        qa_response.answer = answer
-
-    if enable_reflexion:
-        # Because follow up messages are explicitly tagged, we don't need to verify the answer
-        if len(query_req.messages) == 1:
-            first_query = query_req.messages[0].message
-            qa_response.answer_valid = get_answer_validity(first_query, answer)
-        else:
-            qa_response.answer_valid = True
-
-    if use_citations and qa_response.answer and qa_response.citations:
-        # Reorganize citation nums to be in the same order as the answer
-        qa_response.answer, qa_response.citations = reorganize_citations(
-            qa_response.answer, qa_response.citations
-        )
-
-    return qa_response

backend/danswer/one_shot_answer/models.py

@@ -1,114 +0,0 @@
-from typing import Any
-
-from pydantic import BaseModel
-from pydantic import Field
-from pydantic import model_validator
-
-from danswer.chat.models import CitationInfo
-from danswer.chat.models import DanswerContexts
-from danswer.chat.models import DanswerQuotes
-from danswer.chat.models import QADocsResponse
-from danswer.configs.constants import MessageType
-from danswer.context.search.enums import LLMEvaluationType
-from danswer.context.search.enums import RecencyBiasSetting
-from danswer.context.search.enums import SearchType
-from danswer.context.search.models import ChunkContext
-from danswer.context.search.models import RerankingDetails
-from danswer.context.search.models import RetrievalDetails
-
-
-class QueryRephrase(BaseModel):
-    rephrased_query: str
-
-
-class ThreadMessage(BaseModel):
-    message: str
-    sender: str | None = None
-    role: MessageType = MessageType.USER
-
-
-class PromptConfig(BaseModel):
-    name: str
-    description: str = ""
-    system_prompt: str
-    task_prompt: str = ""
-    include_citations: bool = True
-    datetime_aware: bool = True
-
-
-class ToolConfig(BaseModel):
-    id: int
-
-
-class PersonaConfig(BaseModel):
-    name: str
-    description: str
-    search_type: SearchType = SearchType.SEMANTIC
-    num_chunks: float | None = None
-    llm_relevance_filter: bool = False
-    llm_filter_extraction: bool = False
-    recency_bias: RecencyBiasSetting = RecencyBiasSetting.AUTO
-    llm_model_provider_override: str | None = None
-    llm_model_version_override: str | None = None
-
-    prompts: list[PromptConfig] = Field(default_factory=list)
-    prompt_ids: list[int] = Field(default_factory=list)
-
-    document_set_ids: list[int] = Field(default_factory=list)
-    tools: list[ToolConfig] = Field(default_factory=list)
-    tool_ids: list[int] = Field(default_factory=list)
-    custom_tools_openapi: list[dict[str, Any]] = Field(default_factory=list)
-
-
-class DirectQARequest(ChunkContext):
-    persona_config: PersonaConfig | None = None
-    persona_id: int | None = None
-
-    messages: list[ThreadMessage]
-    prompt_id: int | None = None
-    multilingual_query_expansion: list[str] | None = None
-    retrieval_options: RetrievalDetails = Field(default_factory=RetrievalDetails)
-    rerank_settings: RerankingDetails | None = None
-    evaluation_type: LLMEvaluationType = LLMEvaluationType.UNSPECIFIED
-
-    chain_of_thought: bool = False
-    return_contexts: bool = False
-
-    # allows the caller to specify the exact search query they want to use
-    # can be used if the message sent to the LLM / query should not be the same
-    # will also disable Thread-based Rewording if specified
-    query_override: str | None = None
-
-    # If True, skips generative an AI response to the search query
-    skip_gen_ai_answer_generation: bool = False
-
-    @model_validator(mode="after")
-    def check_persona_fields(self) -> "DirectQARequest":
-        if (self.persona_config is None) == (self.persona_id is None):
-            raise ValueError("Exactly one of persona_config or persona_id must be set")
-        return self
-
-    @model_validator(mode="after")
-    def check_chain_of_thought_and_prompt_id(self) -> "DirectQARequest":
-        if self.chain_of_thought and self.prompt_id is not None:
-            raise ValueError(
-                "If chain_of_thought is True, prompt_id must be None"
-                "The chain of thought prompt is only for question "
-                "answering and does not accept customizing."
-            )
-
-        return self
-
-
-class OneShotQAResponse(BaseModel):
-    # This is built piece by piece, any of these can be None as the flow could break
-    answer: str | None = None
-    rephrase: str | None = None
-    quotes: DanswerQuotes | None = None
-    citations: list[CitationInfo] | None = None
-    docs: QADocsResponse | None = None
-    llm_selected_doc_indices: list[int] | None = None
-    error_msg: str | None = None
-    answer_valid: bool = True  # Reflexion result, default True if Reflexion not run
-    chat_message_id: int | None = None
-    contexts: DanswerContexts | None = None

backend/danswer/one_shot_answer/qa_utils.py

@@ -1,81 +0,0 @@
-from collections.abc import Generator
-
-from danswer.configs.constants import MessageType
-from danswer.natural_language_processing.utils import BaseTokenizer
-from danswer.one_shot_answer.models import ThreadMessage
-from danswer.utils.logger import setup_logger
-
-logger = setup_logger()
-
-
-def simulate_streaming_response(model_out: str) -> Generator[str, None, None]:
-    """Mock streaming by generating the passed in model output, character by character"""
-    for token in model_out:
-        yield token
-
-
-def combine_message_thread(
-    messages: list[ThreadMessage],
-    max_tokens: int | None,
-    llm_tokenizer: BaseTokenizer,
-) -> str:
-    """Used to create a single combined message context from threads"""
-    if not messages:
-        return ""
-
-    message_strs: list[str] = []
-    total_token_count = 0
-
-    for message in reversed(messages):
-        if message.role == MessageType.USER:
-            role_str = message.role.value.upper()
-            if message.sender:
-                role_str += " " + message.sender
-            else:
-                # Since other messages might have the user identifying information
-                # better to use Unknown for symmetry
-                role_str += " Unknown"
-        else:
-            role_str = message.role.value.upper()
-
-        msg_str = f"{role_str}:\n{message.message}"
-        message_token_count = len(llm_tokenizer.encode(msg_str))
-
-        if (
-            max_tokens is not None
-            and total_token_count + message_token_count > max_tokens
-        ):
-            break
-
-        message_strs.insert(0, msg_str)
-        total_token_count += message_token_count
-
-    return "\n\n".join(message_strs)
-
-
-def slackify_message(message: ThreadMessage) -> str:
-    if message.role != MessageType.USER:
-        return message.message
-
-    return f"{message.sender or 'Unknown User'} said in Slack:\n{message.message}"
-
-
-def slackify_message_thread(messages: list[ThreadMessage]) -> str:
-    if not messages:
-        return ""
-
-    message_strs: list[str] = []
-    for message in messages:
-        if message.role == MessageType.USER:
-            message_text = (
-                f"{message.sender or 'Unknown User'} said in Slack:\n{message.message}"
-            )
-        elif message.role == MessageType.ASSISTANT:
-            message_text = f"DanswerBot said in Slack:\n{message.message}"
-        else:
-            message_text = (
-                f"{message.role.value.upper()} said in Slack:\n{message.message}"
-            )
-        message_strs.append(message_text)
-
-    return "\n\n".join(message_strs)

backend/danswer/prompts/prompt_utils.py

@@ -5,11 +5,11 @@ from typing import cast
 from langchain_core.messages import BaseMessage
 
 from danswer.chat.models import LlmDoc
+from danswer.chat.models import PromptConfig
 from danswer.configs.chat_configs import LANGUAGE_HINT
 from danswer.configs.constants import DocumentSource
 from danswer.context.search.models import InferenceChunk
 from danswer.db.models import Prompt
-from danswer.llm.answering.models import PromptConfig
 from danswer.prompts.chat_prompts import ADDITIONAL_INFO
 from danswer.prompts.chat_prompts import CITATION_REMINDER
 from danswer.prompts.constants import CODE_BLOCK_PAT

backend/danswer/redis/redis_connector_doc_perm_sync.py

@@ -133,6 +133,8 @@ class RedisConnectorPermissionSync:
         lock: RedisLock | None,
         new_permissions: list[DocExternalAccess],
         source_string: str,
+        connector_id: int,
+        credential_id: int,
     ) -> int | None:
         last_lock_time = time.monotonic()
         async_results = []
@@ -155,6 +157,8 @@ class RedisConnectorPermissionSync:
                     tenant_id=self.tenant_id,
                     serialized_doc_external_access=doc_perm.to_dict(),
                     source_string=source_string,
+                    connector_id=connector_id,
+                    credential_id=credential_id,
                 ),
                 queue=DanswerCeleryQueues.DOC_PERMISSIONS_UPSERT,
                 task_id=custom_task_id,

backend/danswer/secondary_llm_flows/choose_search.py

@@ -3,14 +3,14 @@ from langchain.schema import HumanMessage
 from langchain.schema import SystemMessage
 
 from danswer.chat.chat_utils import combine_message_chain
+from danswer.chat.prompt_builder.utils import translate_danswer_msg_to_langchain
 from danswer.configs.chat_configs import DISABLE_LLM_CHOOSE_SEARCH
 from danswer.configs.model_configs import GEN_AI_HISTORY_CUTOFF
 from danswer.db.models import ChatMessage
-from danswer.llm.answering.models import PreviousMessage
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.llm.utils import dict_based_prompt_to_langchain_prompt
 from danswer.llm.utils import message_to_string
-from danswer.llm.utils import translate_danswer_msg_to_langchain
 from danswer.prompts.chat_prompts import AGGRESSIVE_SEARCH_TEMPLATE
 from danswer.prompts.chat_prompts import NO_SEARCH
 from danswer.prompts.chat_prompts import REQUIRE_SEARCH_HINT

backend/danswer/secondary_llm_flows/query_expansion.py

@@ -4,10 +4,10 @@ from danswer.chat.chat_utils import combine_message_chain
 from danswer.configs.chat_configs import DISABLE_LLM_QUERY_REPHRASE
 from danswer.configs.model_configs import GEN_AI_HISTORY_CUTOFF
 from danswer.db.models import ChatMessage
-from danswer.llm.answering.models import PreviousMessage
 from danswer.llm.exceptions import GenAIDisabledException
 from danswer.llm.factory import get_default_llms
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.llm.utils import dict_based_prompt_to_langchain_prompt
 from danswer.llm.utils import message_to_string
 from danswer.prompts.chat_prompts import HISTORY_QUERY_REPHRASE

backend/danswer/server/documents/connector.py

@@ -86,6 +86,7 @@ from danswer.db.models import SearchSettings
 from danswer.db.models import User
 from danswer.db.search_settings import get_current_search_settings
 from danswer.db.search_settings import get_secondary_search_settings
+from danswer.file_processing.extract_file_text import convert_docx_to_txt
 from danswer.file_store.file_store import get_default_file_store
 from danswer.key_value_store.interface import KvKeyNotFoundError
 from danswer.redis.redis_connector import RedisConnector
@@ -393,6 +394,12 @@ def upload_files(
                 file_origin=FileOrigin.CONNECTOR,
                 file_type=file.content_type or "text/plain",
             )
+
+            if file.content_type and file.content_type.startswith(
+                "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+            ):
+                convert_docx_to_txt(file, file_store, file_path)
+
     except ValueError as e:
         raise HTTPException(status_code=400, detail=str(e))
     return FileUploadResponse(file_paths=deduped_file_paths)
@@ -1010,37 +1017,18 @@ def get_connector_by_id(
 
 
 class BasicCCPairInfo(BaseModel):
-    docs_indexed: int
     has_successful_run: bool
     source: DocumentSource
 
 
-@router.get("/indexing-status")
+@router.get("/connector-status")
 def get_basic_connector_indexing_status(
     _: User = Depends(current_user),
     db_session: Session = Depends(get_session),
 ) -> list[BasicCCPairInfo]:
     cc_pairs = get_connector_credential_pairs(db_session)
-    cc_pair_identifiers = [
-        ConnectorCredentialPairIdentifier(
-            connector_id=cc_pair.connector_id, credential_id=cc_pair.credential_id
-        )
-        for cc_pair in cc_pairs
-    ]
-    document_count_info = get_document_counts_for_cc_pairs(
-        db_session=db_session,
-        cc_pair_identifiers=cc_pair_identifiers,
-    )
-    cc_pair_to_document_cnt = {
-        (connector_id, credential_id): cnt
-        for connector_id, credential_id, cnt in document_count_info
-    }
     return [
         BasicCCPairInfo(
-            docs_indexed=cc_pair_to_document_cnt.get(
-                (cc_pair.connector_id, cc_pair.credential_id)
-            )
-            or 0,
             has_successful_run=cc_pair.last_successful_index_time is not None,
             source=cc_pair.connector.source,
         )

backend/danswer/server/features/persona/api.py

@@ -13,6 +13,7 @@ from danswer.auth.users import current_admin_user
 from danswer.auth.users import current_curator_or_admin_user
 from danswer.auth.users import current_limited_user
 from danswer.auth.users import current_user
+from danswer.chat.prompt_builder.utils import build_dummy_prompt
 from danswer.configs.constants import FileOrigin
 from danswer.configs.constants import NotificationType
 from danswer.db.engine import get_session
@@ -33,7 +34,6 @@ from danswer.db.persona import update_persona_shared_users
 from danswer.db.persona import update_persona_visibility
 from danswer.file_store.file_store import get_default_file_store
 from danswer.file_store.models import ChatFileType
-from danswer.llm.answering.prompts.utils import build_dummy_prompt
 from danswer.server.features.persona.models import CreatePersonaRequest
 from danswer.server.features.persona.models import ImageGenerationToolStatus
 from danswer.server.features.persona.models import PersonaCategoryCreate

backend/danswer/server/manage/models.py

@@ -1,4 +1,5 @@
 from datetime import datetime
+from enum import Enum
 from typing import TYPE_CHECKING
 
 from pydantic import BaseModel
@@ -15,7 +16,6 @@ from danswer.danswerbot.slack.config import VALID_SLACK_FILTERS
 from danswer.db.models import AllowedAnswerFilters
 from danswer.db.models import ChannelConfig
 from danswer.db.models import SlackBot as SlackAppModel
-from danswer.db.models import SlackBotResponseType
 from danswer.db.models import SlackChannelConfig as SlackChannelConfigModel
 from danswer.db.models import User
 from danswer.server.features.persona.models import PersonaSnapshot
@@ -148,6 +148,12 @@ class SlackBotTokens(BaseModel):
     model_config = ConfigDict(frozen=True)
 
 
+# TODO No longer in use, remove later
+class SlackBotResponseType(str, Enum):
+    QUOTES = "quotes"
+    CITATIONS = "citations"
+
+
 class SlackChannelConfigCreationRequest(BaseModel):
     slack_bot_id: int
     # currently, a persona is created for each Slack channel config
@@ -197,7 +203,6 @@ class SlackChannelConfig(BaseModel):
     id: int
     persona: PersonaSnapshot | None
     channel_config: ChannelConfig
-    response_type: SlackBotResponseType
     # XXX this is going away soon
     standard_answer_categories: list[StandardAnswerCategory]
     enable_auto_filters: bool
@@ -217,7 +222,6 @@ class SlackChannelConfig(BaseModel):
                 else None
             ),
             channel_config=slack_channel_config_model.channel_config,
-            response_type=slack_channel_config_model.response_type,
             # XXX this is going away soon
             standard_answer_categories=[
                 StandardAnswerCategory.from_model(standard_answer_category_model)

backend/danswer/server/manage/slack_bot.py

@@ -118,7 +118,6 @@ def create_slack_channel_config(
         slack_bot_id=slack_channel_config_creation_request.slack_bot_id,
         persona_id=persona_id,
         channel_config=channel_config,
-        response_type=slack_channel_config_creation_request.response_type,
         standard_answer_category_ids=slack_channel_config_creation_request.standard_answer_categories,
         db_session=db_session,
         enable_auto_filters=slack_channel_config_creation_request.enable_auto_filters,
@@ -182,7 +181,6 @@ def patch_slack_channel_config(
         slack_channel_config_id=slack_channel_config_id,
         persona_id=persona_id,
         channel_config=channel_config,
-        response_type=slack_channel_config_creation_request.response_type,
         standard_answer_category_ids=slack_channel_config_creation_request.standard_answer_categories,
         enable_auto_filters=slack_channel_config_creation_request.enable_auto_filters,
     )

backend/danswer/server/manage/users.py

@@ -26,7 +26,6 @@ from danswer.auth.noauth_user import fetch_no_auth_user
 from danswer.auth.noauth_user import set_no_auth_user_preferences
 from danswer.auth.schemas import UserRole
 from danswer.auth.schemas import UserStatus
-from danswer.auth.users import BasicAuthenticationError
 from danswer.auth.users import current_admin_user
 from danswer.auth.users import current_curator_or_admin_user
 from danswer.auth.users import current_user
@@ -60,6 +59,7 @@ from danswer.server.manage.models import UserRoleUpdateRequest
 from danswer.server.models import FullUserSnapshot
 from danswer.server.models import InvitedUserSnapshot
 from danswer.server.models import MinimalUserSnapshot
+from danswer.server.utils import BasicAuthenticationError
 from danswer.server.utils import send_user_email_invite
 from danswer.utils.logger import setup_logger
 from danswer.utils.variable_functionality import fetch_ee_implementation_or_noop
@@ -194,11 +194,11 @@ def bulk_invite_users(
         )
 
     tenant_id = CURRENT_TENANT_ID_CONTEXTVAR.get()
-    normalized_emails = []
+    new_invited_emails = []
     try:
         for email in emails:
             email_info = validate_email(email)
-            normalized_emails.append(email_info.normalized)  # type: ignore
+            new_invited_emails.append(email_info.normalized)
 
     except (EmailUndeliverableError, EmailNotValidError) as e:
         raise HTTPException(
@@ -210,7 +210,7 @@ def bulk_invite_users(
         try:
             fetch_ee_implementation_or_noop(
                 "danswer.server.tenants.provisioning", "add_users_to_tenant", None
-            )(normalized_emails, tenant_id)
+            )(new_invited_emails, tenant_id)
 
         except IntegrityError as e:
             if isinstance(e.orig, UniqueViolation):
@@ -224,7 +224,7 @@ def bulk_invite_users(
 
     initial_invited_users = get_invited_users()
 
-    all_emails = list(set(normalized_emails) | set(initial_invited_users))
+    all_emails = list(set(new_invited_emails) | set(initial_invited_users))
     number_of_invited_users = write_invited_users(all_emails)
 
     if not MULTI_TENANT:
@@ -236,7 +236,7 @@ def bulk_invite_users(
         )(CURRENT_TENANT_ID_CONTEXTVAR.get(), get_total_users_count(db_session))
         if ENABLE_EMAIL_INVITES:
             try:
-                for email in all_emails:
+                for email in new_invited_emails:
                     send_user_email_invite(email, current_user)
             except Exception as e:
                 logger.error(f"Error sending email invite to invited users: {e}")
@@ -250,7 +250,7 @@ def bulk_invite_users(
         write_invited_users(initial_invited_users)  # Reset to original state
         fetch_ee_implementation_or_noop(
             "danswer.server.tenants.user_mapping", "remove_users_from_tenant", None
-        )(normalized_emails, tenant_id)
+        )(new_invited_emails, tenant_id)
         raise e
 
 

backend/danswer/server/openai_assistants_api/runs_api.py

@@ -109,6 +109,7 @@ def process_run_in_background(
         prompt_id=chat_session.persona.prompts[0].id,
         search_doc_ids=None,
         retrieval_options=search_tool_retrieval_details,  # Adjust as needed
+        rerank_settings=None,
         query_override=None,
         regenerate=None,
         llm_override=None,

backend/danswer/server/query_and_chat/chat_backend.py

@@ -1,6 +1,7 @@
 import asyncio
 import io
 import json
+import os
 import uuid
 from collections.abc import Callable
 from collections.abc import Generator
@@ -23,6 +24,9 @@ from danswer.auth.users import current_user
 from danswer.chat.chat_utils import create_chat_chain
 from danswer.chat.chat_utils import extract_headers
 from danswer.chat.process_message import stream_chat_message
+from danswer.chat.prompt_builder.citations_prompt import (
+    compute_max_document_tokens_for_persona,
+)
 from danswer.configs.app_configs import WEB_DOMAIN
 from danswer.configs.constants import FileOrigin
 from danswer.configs.constants import MessageType
@@ -47,13 +51,11 @@ from danswer.db.models import User
 from danswer.db.persona import get_persona_by_id
 from danswer.document_index.document_index_utils import get_both_index_names
 from danswer.document_index.factory import get_default_document_index
+from danswer.file_processing.extract_file_text import docx_to_txt_filename
 from danswer.file_processing.extract_file_text import extract_file_text
 from danswer.file_store.file_store import get_default_file_store
 from danswer.file_store.models import ChatFileType
 from danswer.file_store.models import FileDescriptor
-from danswer.llm.answering.prompts.citations_prompt import (
-    compute_max_document_tokens_for_persona,
-)
 from danswer.llm.exceptions import GenAIDisabledException
 from danswer.llm.factory import get_default_llms
 from danswer.llm.factory import get_llms_for_persona
@@ -718,6 +720,18 @@ def fetch_chat_file(
     if not file_record:
         raise HTTPException(status_code=404, detail="File not found")
 
+    original_file_name = file_record.display_name
+    if file_record.file_type.startswith(
+        "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+    ):
+        # Check if a converted text file exists for .docx files
+        txt_file_name = docx_to_txt_filename(original_file_name)
+        txt_file_id = os.path.join(os.path.dirname(file_id), txt_file_name)
+        txt_file_record = file_store.read_file_record(txt_file_id)
+        if txt_file_record:
+            file_record = txt_file_record
+            file_id = txt_file_id
+
     media_type = file_record.file_type
     file_io = file_store.read_file(file_id, mode="b")
 

backend/danswer/server/query_and_chat/models.py

@@ -1,16 +1,19 @@
 from datetime import datetime
 from typing import Any
+from typing import TYPE_CHECKING
 from uuid import UUID
 
 from pydantic import BaseModel
 from pydantic import model_validator
 
+from danswer.chat.models import PersonaOverrideConfig
 from danswer.chat.models import RetrievalDocs
 from danswer.configs.constants import DocumentSource
 from danswer.configs.constants import MessageType
 from danswer.configs.constants import SearchFeedbackType
 from danswer.context.search.models import BaseFilters
 from danswer.context.search.models import ChunkContext
+from danswer.context.search.models import RerankingDetails
 from danswer.context.search.models import RetrievalDetails
 from danswer.context.search.models import SearchDoc
 from danswer.context.search.models import Tag
@@ -20,6 +23,9 @@ from danswer.llm.override_models import LLMOverride
 from danswer.llm.override_models import PromptOverride
 from danswer.tools.models import ToolCallFinalResult
 
+if TYPE_CHECKING:
+    pass
+
 
 class SourceTag(Tag):
     source: DocumentSource
@@ -87,6 +93,8 @@ class CreateChatMessageRequest(ChunkContext):
     # If search_doc_ids provided, then retrieval options are unused
     search_doc_ids: list[int] | None
     retrieval_options: RetrievalDetails | None
+    # Useable via the APIs but not recommended for most flows
+    rerank_settings: RerankingDetails | None = None
     # allows the caller to specify the exact search query they want to use
     # will disable Query Rewording if specified
     query_override: str | None = None
@@ -102,6 +110,10 @@ class CreateChatMessageRequest(ChunkContext):
     # allow user to specify an alternate assistnat
     alternate_assistant_id: int | None = None
 
+    # This takes the priority over the prompt_override
+    # This won't be a type that's passed in directly from the API
+    persona_override_config: PersonaOverrideConfig | None = None
+
     # used for seeded chats to kick off the generation of an AI answer
     use_existing_user_message: bool = False
 
@@ -145,7 +157,7 @@ class RenameChatSessionResponse(BaseModel):
 
 class ChatSessionDetails(BaseModel):
     id: UUID
-    name: str
+    name: str | None
     persona_id: int | None = None
     time_created: str
     shared_status: ChatSessionSharedStatus
@@ -198,14 +210,14 @@ class ChatMessageDetail(BaseModel):
 
 class SearchSessionDetailResponse(BaseModel):
     search_session_id: UUID
-    description: str
+    description: str | None
     documents: list[SearchDoc]
     messages: list[ChatMessageDetail]
 
 
 class ChatSessionDetailResponse(BaseModel):
     chat_session_id: UUID
-    description: str
+    description: str | None
     persona_id: int | None = None
     persona_name: str | None
     messages: list[ChatMessageDetail]

backend/danswer/server/query_and_chat/query_backend.py

@@ -1,15 +1,11 @@
-import json
-from collections.abc import Generator
 from uuid import UUID
 
 from fastapi import APIRouter
 from fastapi import Depends
 from fastapi import HTTPException
-from fastapi.responses import StreamingResponse
 from sqlalchemy.orm import Session
 
 from danswer.auth.users import current_curator_or_admin_user
-from danswer.auth.users import current_limited_user
 from danswer.auth.users import current_user
 from danswer.configs.constants import DocumentSource
 from danswer.configs.constants import MessageType
@@ -32,8 +28,6 @@ from danswer.db.search_settings import get_current_search_settings
 from danswer.db.tag import find_tags
 from danswer.document_index.factory import get_default_document_index
 from danswer.document_index.vespa.index import VespaIndex
-from danswer.one_shot_answer.answer_question import stream_search_answer
-from danswer.one_shot_answer.models import DirectQARequest
 from danswer.server.query_and_chat.models import AdminSearchRequest
 from danswer.server.query_and_chat.models import AdminSearchResponse
 from danswer.server.query_and_chat.models import ChatSessionDetails
@@ -41,7 +35,6 @@ from danswer.server.query_and_chat.models import ChatSessionsResponse
 from danswer.server.query_and_chat.models import SearchSessionDetailResponse
 from danswer.server.query_and_chat.models import SourceTag
 from danswer.server.query_and_chat.models import TagResponse
-from danswer.server.query_and_chat.token_limit import check_token_rate_limits
 from danswer.utils.logger import setup_logger
 
 logger = setup_logger()
@@ -140,7 +133,7 @@ def get_user_search_sessions(
 
     try:
         search_sessions = get_chat_sessions_by_user(
-            user_id=user_id, deleted=False, db_session=db_session, only_one_shot=True
+            user_id=user_id, deleted=False, db_session=db_session
         )
     except ValueError:
         raise HTTPException(
@@ -229,29 +222,3 @@ def get_search_session(
         ],
     )
     return response
-
-
-@basic_router.post("/stream-answer-with-quote")
-def get_answer_with_quote(
-    query_request: DirectQARequest,
-    user: User = Depends(current_limited_user),
-    _: None = Depends(check_token_rate_limits),
-) -> StreamingResponse:
-    query = query_request.messages[0].message
-
-    logger.notice(f"Received query for one shot answer with quotes: {query}")
-
-    def stream_generator() -> Generator[str, None, None]:
-        try:
-            for packet in stream_search_answer(
-                query_req=query_request,
-                user=user,
-                max_document_tokens=None,
-                max_history_tokens=0,
-            ):
-                yield json.dumps(packet) if isinstance(packet, dict) else packet
-        except Exception as e:
-            logger.exception("Error in search answer streaming")
-            yield json.dumps({"error": str(e)})
-
-    return StreamingResponse(stream_generator(), media_type="application/json")

backend/danswer/server/utils.py

@@ -6,6 +6,9 @@ from email.mime.text import MIMEText
 from textwrap import dedent
 from typing import Any
 
+from fastapi import HTTPException
+from fastapi import status
+
 from danswer.configs.app_configs import SMTP_PASS
 from danswer.configs.app_configs import SMTP_PORT
 from danswer.configs.app_configs import SMTP_SERVER
@@ -14,6 +17,11 @@ from danswer.configs.app_configs import WEB_DOMAIN
 from danswer.db.models import User
 
 
+class BasicAuthenticationError(HTTPException):
+    def __init__(self, detail: str):
+        super().__init__(status_code=status.HTTP_403_FORBIDDEN, detail=detail)
+
+
 class DateTimeEncoder(json.JSONEncoder):
     """Custom JSON encoder that converts datetime objects to ISO format strings."""
 

backend/danswer/setup.py

@@ -4,6 +4,7 @@ from sqlalchemy.orm import Session
 
 from danswer.configs.app_configs import DISABLE_INDEX_UPDATE_ON_SWAP
 from danswer.configs.app_configs import MANAGED_VESPA
+from danswer.configs.app_configs import VESPA_NUM_ATTEMPTS_ON_STARTUP
 from danswer.configs.constants import KV_REINDEX_KEY
 from danswer.configs.constants import KV_SEARCH_SETTINGS
 from danswer.configs.model_configs import FAST_GEN_AI_MODEL_VERSION
@@ -221,13 +222,13 @@ def setup_vespa(
     document_index: DocumentIndex,
     index_setting: IndexingSetting,
     secondary_index_setting: IndexingSetting | None,
+    num_attempts: int = VESPA_NUM_ATTEMPTS_ON_STARTUP,
 ) -> bool:
     # Vespa startup is a bit slow, so give it a few seconds
     WAIT_SECONDS = 5
-    VESPA_ATTEMPTS = 5
-    for x in range(VESPA_ATTEMPTS):
+    for x in range(num_attempts):
         try:
-            logger.notice(f"Setting up Vespa (attempt {x+1}/{VESPA_ATTEMPTS})...")
+            logger.notice(f"Setting up Vespa (attempt {x+1}/{num_attempts})...")
             document_index.ensure_indices_exist(
                 index_embedding_dim=index_setting.model_dim,
                 secondary_index_embedding_dim=secondary_index_setting.model_dim
@@ -244,7 +245,7 @@ def setup_vespa(
             time.sleep(WAIT_SECONDS)
 
     logger.error(
-        f"Vespa setup did not succeed. Attempt limit reached. ({VESPA_ATTEMPTS})"
+        f"Vespa setup did not succeed. Attempt limit reached. ({num_attempts})"
     )
     return False
 

backend/danswer/tools/base_tool.py

@@ -7,7 +7,7 @@ from danswer.llm.utils import message_to_prompt_and_imgs
 from danswer.tools.tool import Tool
 
 if TYPE_CHECKING:
-    from danswer.llm.answering.prompts.build import AnswerPromptBuilder
+    from danswer.chat.prompt_builder.build import AnswerPromptBuilder
     from danswer.tools.tool_implementations.custom.custom_tool import (
         CustomToolCallSummary,
     )

backend/danswer/tools/tool.py

@@ -3,13 +3,13 @@ from collections.abc import Generator
 from typing import Any
 from typing import TYPE_CHECKING
 
-from danswer.llm.answering.models import PreviousMessage
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.utils.special_types import JSON_ro
 
 
 if TYPE_CHECKING:
-    from danswer.llm.answering.prompts.build import AnswerPromptBuilder
+    from danswer.chat.prompt_builder.build import AnswerPromptBuilder
     from danswer.tools.message import ToolCallSummary
     from danswer.tools.models import ToolResponse
 

backend/danswer/tools/tool_constructor.py

@@ -5,6 +5,10 @@ from pydantic import BaseModel
 from pydantic import Field
 from sqlalchemy.orm import Session
 
+from danswer.chat.models import AnswerStyleConfig
+from danswer.chat.models import CitationConfig
+from danswer.chat.models import DocumentPruningConfig
+from danswer.chat.models import PromptConfig
 from danswer.configs.app_configs import AZURE_DALLE_API_BASE
 from danswer.configs.app_configs import AZURE_DALLE_API_KEY
 from danswer.configs.app_configs import AZURE_DALLE_API_VERSION
@@ -13,15 +17,12 @@ from danswer.configs.chat_configs import BING_API_KEY
 from danswer.configs.model_configs import GEN_AI_TEMPERATURE
 from danswer.context.search.enums import LLMEvaluationType
 from danswer.context.search.models import InferenceSection
+from danswer.context.search.models import RerankingDetails
 from danswer.context.search.models import RetrievalDetails
 from danswer.db.llm import fetch_existing_llm_providers
 from danswer.db.models import Persona
 from danswer.db.models import User
 from danswer.file_store.models import InMemoryChatFile
-from danswer.llm.answering.models import AnswerStyleConfig
-from danswer.llm.answering.models import CitationConfig
-from danswer.llm.answering.models import DocumentPruningConfig
-from danswer.llm.answering.models import PromptConfig
 from danswer.llm.interfaces import LLM
 from danswer.llm.interfaces import LLMConfig
 from danswer.natural_language_processing.utils import get_tokenizer
@@ -102,11 +103,14 @@ class SearchToolConfig(BaseModel):
         default_factory=DocumentPruningConfig
     )
     retrieval_options: RetrievalDetails = Field(default_factory=RetrievalDetails)
+    rerank_settings: RerankingDetails | None = None
     selected_sections: list[InferenceSection] | None = None
     chunks_above: int = 0
     chunks_below: int = 0
     full_doc: bool = False
     latest_query_files: list[InMemoryChatFile] | None = None
+    # Use with care, should only be used for DanswerBot in channels with multiple users
+    bypass_acl: bool = False
 
 
 class InternetSearchToolConfig(BaseModel):
@@ -170,6 +174,8 @@ def construct_tools(
                         if persona.llm_relevance_filter
                         else LLMEvaluationType.SKIP
                     ),
+                    rerank_settings=search_tool_config.rerank_settings,
+                    bypass_acl=search_tool_config.bypass_acl,
                 )
                 tool_dict[db_tool_model.id] = [search_tool]
 

backend/danswer/tools/tool_implementations/custom/custom_tool.py

@@ -15,14 +15,14 @@ from langchain_core.messages import SystemMessage
 from pydantic import BaseModel
 from requests import JSONDecodeError
 
+from danswer.chat.prompt_builder.build import AnswerPromptBuilder
 from danswer.configs.constants import FileOrigin
 from danswer.db.engine import get_session_with_default_tenant
 from danswer.file_store.file_store import get_default_file_store
 from danswer.file_store.models import ChatFileType
 from danswer.file_store.models import InMemoryChatFile
-from danswer.llm.answering.models import PreviousMessage
-from danswer.llm.answering.prompts.build import AnswerPromptBuilder
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.tools.base_tool import BaseTool
 from danswer.tools.message import ToolCallSummary
 from danswer.tools.models import CHAT_SESSION_ID_PLACEHOLDER

backend/danswer/tools/tool_implementations/images/image_generation_tool.py

@@ -4,14 +4,16 @@ from enum import Enum
 from typing import Any
 from typing import cast
 
+import requests
 from litellm import image_generation  # type: ignore
 from pydantic import BaseModel
 
 from danswer.chat.chat_utils import combine_message_chain
+from danswer.chat.prompt_builder.build import AnswerPromptBuilder
 from danswer.configs.model_configs import GEN_AI_HISTORY_CUTOFF
-from danswer.llm.answering.models import PreviousMessage
-from danswer.llm.answering.prompts.build import AnswerPromptBuilder
+from danswer.configs.tool_configs import IMAGE_GENERATION_OUTPUT_FORMAT
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.llm.utils import build_content_with_imgs
 from danswer.llm.utils import message_to_string
 from danswer.prompts.constants import GENERAL_SEP_PAT
@@ -56,9 +58,18 @@ Follow Up Input:
 """.strip()
 
 
+class ImageFormat(str, Enum):
+    URL = "url"
+    BASE64 = "b64_json"
+
+
+_DEFAULT_OUTPUT_FORMAT = ImageFormat(IMAGE_GENERATION_OUTPUT_FORMAT)
+
+
 class ImageGenerationResponse(BaseModel):
     revised_prompt: str
-    url: str
+    url: str | None
+    image_data: str | None
 
 
 class ImageShape(str, Enum):
@@ -80,6 +91,7 @@ class ImageGenerationTool(Tool):
         model: str = "dall-e-3",
         num_imgs: int = 2,
         additional_headers: dict[str, str] | None = None,
+        output_format: ImageFormat = _DEFAULT_OUTPUT_FORMAT,
     ) -> None:
         self.api_key = api_key
         self.api_base = api_base
@@ -89,6 +101,7 @@ class ImageGenerationTool(Tool):
         self.num_imgs = num_imgs
 
         self.additional_headers = additional_headers
+        self.output_format = output_format
 
     @property
     def name(self) -> str:
@@ -168,7 +181,7 @@ class ImageGenerationTool(Tool):
         )
 
         return build_content_with_imgs(
-            json.dumps(
+            message=json.dumps(
                 [
                     {
                         "revised_prompt": image_generation.revised_prompt,
@@ -177,13 +190,10 @@ class ImageGenerationTool(Tool):
                     for image_generation in image_generations
                 ]
             ),
-            # NOTE: we can't pass in the image URLs here, since OpenAI doesn't allow
-            # Tool messages to contain images
-            # img_urls=[image_generation.url for image_generation in image_generations],
         )
 
     def _generate_image(
-        self, prompt: str, shape: ImageShape
+        self, prompt: str, shape: ImageShape, format: ImageFormat
     ) -> ImageGenerationResponse:
         if shape == ImageShape.LANDSCAPE:
             size = "1792x1024"
@@ -197,20 +207,32 @@ class ImageGenerationTool(Tool):
                 prompt=prompt,
                 model=self.model,
                 api_key=self.api_key,
-                # need to pass in None rather than empty str
                 api_base=self.api_base or None,
                 api_version=self.api_version or None,
                 size=size,
                 n=1,
+                response_format=format,
                 extra_headers=build_llm_extra_headers(self.additional_headers),
             )
+
+            if format == ImageFormat.URL:
+                url = response.data[0]["url"]
+                image_data = None
+            else:
+                url = None
+                image_data = response.data[0]["b64_json"]
+
             return ImageGenerationResponse(
                 revised_prompt=response.data[0]["revised_prompt"],
-                url=response.data[0]["url"],
+                url=url,
+                image_data=image_data,
             )
 
+        except requests.RequestException as e:
+            logger.error(f"Error fetching or converting image: {e}")
+            raise ValueError("Failed to fetch or convert the generated image")
         except Exception as e:
-            logger.debug(f"Error occured during image generation: {e}")
+            logger.debug(f"Error occurred during image generation: {e}")
 
             error_message = str(e)
             if "OpenAIException" in str(type(e)):
@@ -235,9 +257,8 @@ class ImageGenerationTool(Tool):
     def run(self, **kwargs: str) -> Generator[ToolResponse, None, None]:
         prompt = cast(str, kwargs["prompt"])
         shape = ImageShape(kwargs.get("shape", ImageShape.SQUARE))
+        format = self.output_format
 
-        # dalle3 only supports 1 image at a time, which is why we have to
-        # parallelize this via threading
         results = cast(
             list[ImageGenerationResponse],
             run_functions_tuples_in_parallel(
@@ -247,6 +268,7 @@ class ImageGenerationTool(Tool):
                         (
                             prompt,
                             shape,
+                            format,
                         ),
                     )
                     for _ in range(self.num_imgs)
@@ -288,11 +310,17 @@ class ImageGenerationTool(Tool):
         if img_generation_response is None:
             raise ValueError("No image generation response found")
 
-        img_urls = [img.url for img in img_generation_response]
+        img_urls = [img.url for img in img_generation_response if img.url is not None]
+        b64_imgs = [
+            img.image_data
+            for img in img_generation_response
+            if img.image_data is not None
+        ]
         prompt_builder.update_user_prompt(
             build_image_generation_user_prompt(
                 query=prompt_builder.get_user_message_content(),
                 img_urls=img_urls,
+                b64_imgs=b64_imgs,
             )
         )
 

backend/danswer/tools/tool_implementations/images/prompt.py

@@ -11,11 +11,14 @@ Can you please summarize them in a sentence or two? Do NOT include image urls or
 
 
 def build_image_generation_user_prompt(
-    query: str, img_urls: list[str] | None = None
+    query: str,
+    img_urls: list[str] | None = None,
+    b64_imgs: list[str] | None = None,
 ) -> HumanMessage:
     return HumanMessage(
         content=build_content_with_imgs(
             message=IMG_GENERATION_SUMMARY_PROMPT.format(query=query).strip(),
+            b64_imgs=b64_imgs,
             img_urls=img_urls,
         )
     )

backend/danswer/tools/tool_implementations/internet_search/internet_search_tool.py

@@ -7,15 +7,15 @@ from typing import cast
 import httpx
 
 from danswer.chat.chat_utils import combine_message_chain
+from danswer.chat.models import AnswerStyleConfig
 from danswer.chat.models import LlmDoc
+from danswer.chat.models import PromptConfig
+from danswer.chat.prompt_builder.build import AnswerPromptBuilder
 from danswer.configs.constants import DocumentSource
 from danswer.configs.model_configs import GEN_AI_HISTORY_CUTOFF
 from danswer.context.search.models import SearchDoc
-from danswer.llm.answering.models import AnswerStyleConfig
-from danswer.llm.answering.models import PreviousMessage
-from danswer.llm.answering.models import PromptConfig
-from danswer.llm.answering.prompts.build import AnswerPromptBuilder
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.llm.utils import message_to_string
 from danswer.prompts.chat_prompts import INTERNET_SEARCH_QUERY_REPHRASE
 from danswer.prompts.constants import GENERAL_SEP_PAT

backend/danswer/tools/tool_implementations/search/search_tool.py

@@ -7,10 +7,19 @@ from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
 from danswer.chat.chat_utils import llm_doc_from_inference_section
+from danswer.chat.llm_response_handler import LLMCall
+from danswer.chat.models import AnswerStyleConfig
+from danswer.chat.models import ContextualPruningConfig
 from danswer.chat.models import DanswerContext
 from danswer.chat.models import DanswerContexts
+from danswer.chat.models import DocumentPruningConfig
 from danswer.chat.models import LlmDoc
+from danswer.chat.models import PromptConfig
 from danswer.chat.models import SectionRelevancePiece
+from danswer.chat.prompt_builder.build import AnswerPromptBuilder
+from danswer.chat.prompt_builder.citations_prompt import compute_max_llm_input_tokens
+from danswer.chat.prune_and_merge import prune_and_merge_sections
+from danswer.chat.prune_and_merge import prune_sections
 from danswer.configs.chat_configs import CONTEXT_CHUNKS_ABOVE
 from danswer.configs.chat_configs import CONTEXT_CHUNKS_BELOW
 from danswer.configs.model_configs import GEN_AI_MODEL_FALLBACK_MAX_TOKENS
@@ -19,22 +28,14 @@ from danswer.context.search.enums import QueryFlow
 from danswer.context.search.enums import SearchType
 from danswer.context.search.models import IndexFilters
 from danswer.context.search.models import InferenceSection
+from danswer.context.search.models import RerankingDetails
 from danswer.context.search.models import RetrievalDetails
 from danswer.context.search.models import SearchRequest
 from danswer.context.search.pipeline import SearchPipeline
 from danswer.db.models import Persona
 from danswer.db.models import User
-from danswer.llm.answering.llm_response_handler import LLMCall
-from danswer.llm.answering.models import AnswerStyleConfig
-from danswer.llm.answering.models import ContextualPruningConfig
-from danswer.llm.answering.models import DocumentPruningConfig
-from danswer.llm.answering.models import PreviousMessage
-from danswer.llm.answering.models import PromptConfig
-from danswer.llm.answering.prompts.build import AnswerPromptBuilder
-from danswer.llm.answering.prompts.citations_prompt import compute_max_llm_input_tokens
-from danswer.llm.answering.prune_and_merge import prune_and_merge_sections
-from danswer.llm.answering.prune_and_merge import prune_sections
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.secondary_llm_flows.choose_search import check_if_need_search
 from danswer.secondary_llm_flows.query_expansion import history_based_query_rephrase
 from danswer.tools.message import ToolCallSummary
@@ -103,6 +104,7 @@ class SearchTool(Tool):
         chunks_below: int | None = None,
         full_doc: bool = False,
         bypass_acl: bool = False,
+        rerank_settings: RerankingDetails | None = None,
     ) -> None:
         self.user = user
         self.persona = persona
@@ -118,6 +120,9 @@ class SearchTool(Tool):
         self.bypass_acl = bypass_acl
         self.db_session = db_session
 
+        # Only used via API
+        self.rerank_settings = rerank_settings
+
         self.chunks_above = (
             chunks_above
             if chunks_above is not None
@@ -292,6 +297,7 @@ class SearchTool(Tool):
                     self.retrieval_options.offset if self.retrieval_options else None
                 ),
                 limit=self.retrieval_options.limit if self.retrieval_options else None,
+                rerank_settings=self.rerank_settings,
                 chunks_above=self.chunks_above,
                 chunks_below=self.chunks_below,
                 full_doc=self.full_doc,

backend/danswer/tools/tool_implementations/search_like_tool_utils.py

@@ -2,15 +2,15 @@ from typing import cast
 
 from langchain_core.messages import HumanMessage
 
+from danswer.chat.models import AnswerStyleConfig
 from danswer.chat.models import LlmDoc
-from danswer.llm.answering.models import AnswerStyleConfig
-from danswer.llm.answering.models import PromptConfig
-from danswer.llm.answering.prompts.build import AnswerPromptBuilder
-from danswer.llm.answering.prompts.citations_prompt import (
+from danswer.chat.models import PromptConfig
+from danswer.chat.prompt_builder.build import AnswerPromptBuilder
+from danswer.chat.prompt_builder.citations_prompt import (
     build_citations_system_message,
 )
-from danswer.llm.answering.prompts.citations_prompt import build_citations_user_message
-from danswer.llm.answering.prompts.quotes_prompt import build_quotes_user_message
+from danswer.chat.prompt_builder.citations_prompt import build_citations_user_message
+from danswer.chat.prompt_builder.quotes_prompt import build_quotes_user_message
 from danswer.tools.message import ToolCallSummary
 from danswer.tools.models import ToolResponse
 

backend/danswer/tools/tool_runner.py

@@ -2,8 +2,8 @@ from collections.abc import Callable
 from collections.abc import Generator
 from typing import Any
 
-from danswer.llm.answering.models import PreviousMessage
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.tools.models import ToolCallFinalResult
 from danswer.tools.models import ToolCallKickoff
 from danswer.tools.models import ToolResponse

backend/danswer/tools/tool_selection.py

@@ -3,8 +3,8 @@ from typing import Any
 
 from danswer.chat.chat_utils import combine_message_chain
 from danswer.configs.model_configs import GEN_AI_HISTORY_CUTOFF
-from danswer.llm.answering.models import PreviousMessage
 from danswer.llm.interfaces import LLM
+from danswer.llm.models import PreviousMessage
 from danswer.llm.utils import message_to_string
 from danswer.prompts.constants import GENERAL_SEP_PAT
 from danswer.tools.tool import Tool

backend/danswer/utils/b64.py

@@ -0,0 +1,25 @@
+import base64
+
+
+def get_image_type_from_bytes(raw_b64_bytes: bytes) -> str:
+    magic_number = raw_b64_bytes[:4]
+
+    if magic_number.startswith(b"\x89PNG"):
+        mime_type = "image/png"
+    elif magic_number.startswith(b"\xFF\xD8"):
+        mime_type = "image/jpeg"
+    elif magic_number.startswith(b"GIF8"):
+        mime_type = "image/gif"
+    elif magic_number.startswith(b"RIFF") and raw_b64_bytes[8:12] == b"WEBP":
+        mime_type = "image/webp"
+    else:
+        raise ValueError(
+            "Unsupported image format - only PNG, JPEG, " "GIF, and WEBP are supported."
+        )
+
+    return mime_type
+
+
+def get_image_type(raw_b64_string: str) -> str:
+    binary_data = base64.b64decode(raw_b64_string)
+    return get_image_type_from_bytes(binary_data)

backend/ee/danswer/chat/process_message.py

@@ -0,0 +1,41 @@
+from danswer.chat.models import AllCitations
+from danswer.chat.models import DanswerAnswerPiece
+from danswer.chat.models import DanswerContexts
+from danswer.chat.models import LLMRelevanceFilterResponse
+from danswer.chat.models import QADocsResponse
+from danswer.chat.models import StreamingError
+from danswer.chat.process_message import ChatPacketStream
+from danswer.server.query_and_chat.models import ChatMessageDetail
+from danswer.utils.timing import log_function_time
+from ee.danswer.server.query_and_chat.models import OneShotQAResponse
+
+
+@log_function_time()
+def gather_stream_for_answer_api(
+    packets: ChatPacketStream,
+) -> OneShotQAResponse:
+    response = OneShotQAResponse()
+
+    answer = ""
+    for packet in packets:
+        if isinstance(packet, DanswerAnswerPiece) and packet.answer_piece:
+            answer += packet.answer_piece
+        elif isinstance(packet, QADocsResponse):
+            response.docs = packet
+            # Extraneous, provided for backwards compatibility
+            response.rephrase = packet.rephrased_query
+        elif isinstance(packet, StreamingError):
+            response.error_msg = packet.error
+        elif isinstance(packet, ChatMessageDetail):
+            response.chat_message_id = packet.message_id
+        elif isinstance(packet, LLMRelevanceFilterResponse):
+            response.llm_selected_doc_indices = packet.llm_selected_doc_indices
+        elif isinstance(packet, AllCitations):
+            response.citations = packet.citations
+        elif isinstance(packet, DanswerContexts):
+            response.contexts = packet
+
+    if answer:
+        response.answer = answer
+
+    return response

backend/ee/danswer/configs/app_configs.py

@@ -28,3 +28,6 @@ JWT_PUBLIC_KEY_URL: str | None = os.getenv("JWT_PUBLIC_KEY_URL", None)
 # Super Users
 SUPER_USERS = json.loads(os.environ.get("SUPER_USERS", '["pablo@danswer.ai"]'))
 SUPER_CLOUD_API_KEY = os.environ.get("SUPER_CLOUD_API_KEY", "api_key")
+
+OAUTH_SLACK_CLIENT_ID = os.environ.get("OAUTH_SLACK_CLIENT_ID", "")
+OAUTH_SLACK_CLIENT_SECRET = os.environ.get("OAUTH_SLACK_CLIENT_SECRET", "")

backend/ee/danswer/danswerbot/slack/handlers/handle_standard_answers.py

@@ -155,7 +155,6 @@ def _handle_standard_answers(
             else 0,
             danswerbot_flow=True,
             slack_thread_id=slack_thread_id,
-            one_shot=True,
         )
 
         root_message = get_or_create_root_message(

backend/ee/danswer/db/analytics.py

@@ -170,3 +170,67 @@ def fetch_danswerbot_analytics(
     )
 
     return results
+
+
+def fetch_persona_message_analytics(
+    db_session: Session,
+    persona_id: int,
+    start: datetime.datetime,
+    end: datetime.datetime,
+) -> list[tuple[int, datetime.date]]:
+    """Gets the daily message counts for a specific persona within the given time range."""
+    query = (
+        select(
+            func.count(ChatMessage.id),
+            cast(ChatMessage.time_sent, Date),
+        )
+        .join(
+            ChatSession,
+            ChatMessage.chat_session_id == ChatSession.id,
+        )
+        .where(
+            or_(
+                ChatMessage.alternate_assistant_id == persona_id,
+                ChatSession.persona_id == persona_id,
+            ),
+            ChatMessage.time_sent >= start,
+            ChatMessage.time_sent <= end,
+            ChatMessage.message_type == MessageType.ASSISTANT,
+        )
+        .group_by(cast(ChatMessage.time_sent, Date))
+        .order_by(cast(ChatMessage.time_sent, Date))
+    )
+
+    return [tuple(row) for row in db_session.execute(query).all()]
+
+
+def fetch_persona_unique_users(
+    db_session: Session,
+    persona_id: int,
+    start: datetime.datetime,
+    end: datetime.datetime,
+) -> list[tuple[int, datetime.date]]:
+    """Gets the daily unique user counts for a specific persona within the given time range."""
+    query = (
+        select(
+            func.count(func.distinct(ChatSession.user_id)),
+            cast(ChatMessage.time_sent, Date),
+        )
+        .join(
+            ChatSession,
+            ChatMessage.chat_session_id == ChatSession.id,
+        )
+        .where(
+            or_(
+                ChatMessage.alternate_assistant_id == persona_id,
+                ChatSession.persona_id == persona_id,
+            ),
+            ChatMessage.time_sent >= start,
+            ChatMessage.time_sent <= end,
+            ChatMessage.message_type == MessageType.ASSISTANT,
+        )
+        .group_by(cast(ChatMessage.time_sent, Date))
+        .order_by(cast(ChatMessage.time_sent, Date))
+    )
+
+    return [tuple(row) for row in db_session.execute(query).all()]

backend/ee/danswer/db/connector_credential_pair.py

@@ -37,10 +37,15 @@ def get_cc_pairs_by_source(
     source_type: DocumentSource,
     only_sync: bool,
 ) -> list[ConnectorCredentialPair]:
+    """
+    Get all cc_pairs for a given source type (and optionally only sync)
+    result is sorted by cc_pair id
+    """
     query = (
         db_session.query(ConnectorCredentialPair)
         .join(ConnectorCredentialPair.connector)
         .filter(Connector.source == source_type)
+        .order_by(ConnectorCredentialPair.id)
     )
 
     if only_sync:

backend/ee/danswer/db/document.py

@@ -55,9 +55,10 @@ def upsert_document_external_perms(
     doc_id: str,
     external_access: ExternalAccess,
     source_type: DocumentSource,
-) -> None:
+) -> bool:
     """
-    This sets the permissions for a document in postgres.
+    This sets the permissions for a document in postgres. Returns True if the
+    a new document was created, False otherwise.
     NOTE: this will replace any existing external access, it will not do a union
     """
     document = db_session.scalars(
@@ -85,7 +86,7 @@ def upsert_document_external_perms(
         )
         db_session.add(document)
         db_session.commit()
-        return
+        return True
 
     # If the document exists, we need to check if the external access has changed
     if (
@@ -98,3 +99,5 @@ def upsert_document_external_perms(
         document.is_public = external_access.is_public
         document.last_modified = datetime.now(timezone.utc)
         db_session.commit()
+
+    return False

backend/ee/danswer/db/usage_export.py

@@ -33,12 +33,7 @@ def get_empty_chat_messages_entries__paginated(
 
     message_skeletons: list[ChatMessageSkeleton] = []
     for chat_session in chat_sessions:
-        if chat_session.one_shot:
-            flow_type = FlowType.SEARCH
-        elif chat_session.danswerbot_flow:
-            flow_type = FlowType.SLACK
-        else:
-            flow_type = FlowType.CHAT
+        flow_type = FlowType.SLACK if chat_session.danswerbot_flow else FlowType.CHAT
 
         for message in chat_session.messages:
             # Only count user messages

backend/ee/danswer/external_permissions/confluence/doc_sync.py

@@ -242,7 +242,9 @@ def _fetch_all_page_restrictions_for_space(
                 )
             continue
 
-        logger.warning(f"No permissions found for document {slim_doc.id}")
+        logger.warning(
+            f"No permissions found for document {slim_doc.id} in space {space_key}"
+        )
 
     logger.debug("Finished fetching all page restrictions for space")
     return document_restrictions

backend/ee/danswer/external_permissions/sync_params.py

@@ -48,6 +48,11 @@ GROUP_PERMISSIONS_FUNC_MAP: dict[DocumentSource, GroupSyncFuncType] = {
 }
 
 
+GROUP_PERMISSIONS_IS_CC_PAIR_AGNOSTIC: set[DocumentSource] = {
+    DocumentSource.CONFLUENCE,
+}
+
+
 # If nothing is specified here, we run the doc_sync every time the celery beat runs
 DOC_PERMISSION_SYNC_PERIODS: dict[DocumentSource, int] = {
     # Polling is not supported so we fetch all doc permissions every 5 minutes
@@ -57,9 +62,9 @@ DOC_PERMISSION_SYNC_PERIODS: dict[DocumentSource, int] = {
 
 # If nothing is specified here, we run the doc_sync every time the celery beat runs
 EXTERNAL_GROUP_SYNC_PERIODS: dict[DocumentSource, int] = {
-    # Polling is not supported so we fetch all group permissions every 5 minutes
+    # Polling is not supported so we fetch all group permissions every 30 minutes
     DocumentSource.GOOGLE_DRIVE: 5 * 60,
-    DocumentSource.CONFLUENCE: 5 * 60,
+    DocumentSource.CONFLUENCE: 30 * 60,
 }
 
 

backend/ee/danswer/main.py

@@ -26,6 +26,7 @@ from ee.danswer.server.enterprise_settings.api import (
 )
 from ee.danswer.server.manage.standard_answer import router as standard_answer_router
 from ee.danswer.server.middleware.tenant_tracking import add_tenant_id_middleware
+from ee.danswer.server.oauth import router as oauth_router
 from ee.danswer.server.query_and_chat.chat_backend import (
     router as chat_router,
 )
@@ -119,6 +120,8 @@ def get_application() -> FastAPI:
     include_router_with_global_prefix_prepended(application, query_router)
     include_router_with_global_prefix_prepended(application, chat_router)
     include_router_with_global_prefix_prepended(application, standard_answer_router)
+    include_router_with_global_prefix_prepended(application, oauth_router)
+
     # Enterprise-only global settings
     include_router_with_global_prefix_prepended(
         application, enterprise_settings_admin_router

backend/ee/danswer/server/analytics/api.py

@@ -11,11 +11,16 @@ from danswer.db.engine import get_session
 from danswer.db.models import User
 from ee.danswer.db.analytics import fetch_danswerbot_analytics
 from ee.danswer.db.analytics import fetch_per_user_query_analytics
+from ee.danswer.db.analytics import fetch_persona_message_analytics
+from ee.danswer.db.analytics import fetch_persona_unique_users
 from ee.danswer.db.analytics import fetch_query_analytics
 
 router = APIRouter(prefix="/analytics")
 
 
+_DEFAULT_LOOKBACK_DAYS = 30
+
+
 class QueryAnalyticsResponse(BaseModel):
     total_queries: int
     total_likes: int
@@ -33,7 +38,7 @@ def get_query_analytics(
     daily_query_usage_info = fetch_query_analytics(
         start=start
         or (
-            datetime.datetime.utcnow() - datetime.timedelta(days=30)
+            datetime.datetime.utcnow() - datetime.timedelta(days=_DEFAULT_LOOKBACK_DAYS)
         ),  # default is 30d lookback
         end=end or datetime.datetime.utcnow(),
         db_session=db_session,
@@ -64,7 +69,7 @@ def get_user_analytics(
     daily_query_usage_info_per_user = fetch_per_user_query_analytics(
         start=start
         or (
-            datetime.datetime.utcnow() - datetime.timedelta(days=30)
+            datetime.datetime.utcnow() - datetime.timedelta(days=_DEFAULT_LOOKBACK_DAYS)
         ),  # default is 30d lookback
         end=end or datetime.datetime.utcnow(),
         db_session=db_session,
@@ -98,7 +103,7 @@ def get_danswerbot_analytics(
     daily_danswerbot_info = fetch_danswerbot_analytics(
         start=start
         or (
-            datetime.datetime.utcnow() - datetime.timedelta(days=30)
+            datetime.datetime.utcnow() - datetime.timedelta(days=_DEFAULT_LOOKBACK_DAYS)
         ),  # default is 30d lookback
         end=end or datetime.datetime.utcnow(),
         db_session=db_session,
@@ -115,3 +120,74 @@ def get_danswerbot_analytics(
     ]
 
     return resolution_results
+
+
+class PersonaMessageAnalyticsResponse(BaseModel):
+    total_messages: int
+    date: datetime.date
+    persona_id: int
+
+
+@router.get("/admin/persona/messages")
+def get_persona_messages(
+    persona_id: int,
+    start: datetime.datetime | None = None,
+    end: datetime.datetime | None = None,
+    _: User | None = Depends(current_admin_user),
+    db_session: Session = Depends(get_session),
+) -> list[PersonaMessageAnalyticsResponse]:
+    """Fetch daily message counts for a single persona within the given time range."""
+    start = start or (
+        datetime.datetime.utcnow() - datetime.timedelta(days=_DEFAULT_LOOKBACK_DAYS)
+    )
+    end = end or datetime.datetime.utcnow()
+
+    persona_message_counts = []
+    for count, date in fetch_persona_message_analytics(
+        db_session=db_session,
+        persona_id=persona_id,
+        start=start,
+        end=end,
+    ):
+        persona_message_counts.append(
+            PersonaMessageAnalyticsResponse(
+                total_messages=count,
+                date=date,
+                persona_id=persona_id,
+            )
+        )
+
+    return persona_message_counts
+
+
+class PersonaUniqueUsersResponse(BaseModel):
+    unique_users: int
+    date: datetime.date
+    persona_id: int
+
+
+@router.get("/admin/persona/unique-users")
+def get_persona_unique_users(
+    persona_id: int,
+    start: datetime.datetime,
+    end: datetime.datetime,
+    _: User | None = Depends(current_admin_user),
+    db_session: Session = Depends(get_session),
+) -> list[PersonaUniqueUsersResponse]:
+    """Get unique users per day for a single persona."""
+    unique_user_counts = []
+    daily_counts = fetch_persona_unique_users(
+        db_session=db_session,
+        persona_id=persona_id,
+        start=start,
+        end=end,
+    )
+    for count, date in daily_counts:
+        unique_user_counts.append(
+            PersonaUniqueUsersResponse(
+                unique_users=count,
+                date=date,
+                persona_id=persona_id,
+            )
+        )
+    return unique_user_counts

backend/ee/danswer/server/oauth.py

@@ -0,0 +1,423 @@
+import base64
+import uuid
+from typing import cast
+
+import requests
+from fastapi import APIRouter
+from fastapi import Depends
+from fastapi import HTTPException
+from fastapi.responses import JSONResponse
+from pydantic import BaseModel
+from sqlalchemy.orm import Session
+
+from danswer.auth.users import current_user
+from danswer.configs.app_configs import WEB_DOMAIN
+from danswer.configs.constants import DocumentSource
+from danswer.db.credentials import create_credential
+from danswer.db.engine import get_current_tenant_id
+from danswer.db.engine import get_session
+from danswer.db.models import User
+from danswer.redis.redis_pool import get_redis_client
+from danswer.server.documents.models import CredentialBase
+from danswer.utils.logger import setup_logger
+from ee.danswer.configs.app_configs import OAUTH_SLACK_CLIENT_ID
+from ee.danswer.configs.app_configs import OAUTH_SLACK_CLIENT_SECRET
+
+
+logger = setup_logger()
+
+router = APIRouter(prefix="/oauth")
+
+
+class SlackOAuth:
+    # https://knock.app/blog/how-to-authenticate-users-in-slack-using-oauth
+    # Example: https://api.slack.com/authentication/oauth-v2#exchanging
+
+    class OAuthSession(BaseModel):
+        """Stored in redis to be looked up on callback"""
+
+        email: str
+        redirect_on_success: str | None  # Where to send the user if OAuth flow succeeds
+
+    CLIENT_ID = OAUTH_SLACK_CLIENT_ID
+    CLIENT_SECRET = OAUTH_SLACK_CLIENT_SECRET
+
+    TOKEN_URL = "https://slack.com/api/oauth.v2.access"
+
+    # SCOPE is per https://docs.danswer.dev/connectors/slack
+    BOT_SCOPE = (
+        "channels:history,"
+        "channels:read,"
+        "groups:history,"
+        "groups:read,"
+        "channels:join,"
+        "im:history,"
+        "users:read,"
+        "users:read.email,"
+        "usergroups:read"
+    )
+
+    REDIRECT_URI = f"{WEB_DOMAIN}/admin/connectors/slack/oauth/callback"
+    DEV_REDIRECT_URI = f"https://redirectmeto.com/{REDIRECT_URI}"
+
+    @classmethod
+    def generate_oauth_url(cls, state: str) -> str:
+        url = (
+            f"https://slack.com/oauth/v2/authorize"
+            f"?client_id={cls.CLIENT_ID}"
+            f"&redirect_uri={cls.REDIRECT_URI}"
+            f"&scope={cls.BOT_SCOPE}"
+            f"&state={state}"
+        )
+        return url
+
+    @classmethod
+    def generate_dev_oauth_url(cls, state: str) -> str:
+        """dev mode workaround for localhost testing
+        - https://www.nango.dev/blog/oauth-redirects-on-localhost-with-https
+        """
+
+        url = (
+            f"https://slack.com/oauth/v2/authorize"
+            f"?client_id={cls.CLIENT_ID}"
+            f"&redirect_uri={cls.DEV_REDIRECT_URI}"
+            f"&scope={cls.BOT_SCOPE}"
+            f"&state={state}"
+        )
+        return url
+
+    @classmethod
+    def session_dump_json(cls, email: str, redirect_on_success: str | None) -> str:
+        """Temporary state to store in redis. to be looked up on auth response.
+        Returns a json string.
+        """
+        session = SlackOAuth.OAuthSession(
+            email=email, redirect_on_success=redirect_on_success
+        )
+        return session.model_dump_json()
+
+    @classmethod
+    def parse_session(cls, session_json: str) -> OAuthSession:
+        session = SlackOAuth.OAuthSession.model_validate_json(session_json)
+        return session
+
+
+# Work in progress
+# class ConfluenceCloudOAuth:
+#     """work in progress"""
+
+#     # https://developer.atlassian.com/cloud/confluence/oauth-2-3lo-apps/
+
+#     class OAuthSession(BaseModel):
+#         """Stored in redis to be looked up on callback"""
+
+#         email: str
+#         redirect_on_success: str | None  # Where to send the user if OAuth flow succeeds
+
+#     CLIENT_ID = OAUTH_CONFLUENCE_CLIENT_ID
+#     CLIENT_SECRET = OAUTH_CONFLUENCE_CLIENT_SECRET
+#     TOKEN_URL = "https://auth.atlassian.com/oauth/token"
+
+#     # All read scopes per https://developer.atlassian.com/cloud/confluence/scopes-for-oauth-2-3LO-and-forge-apps/
+#     CONFLUENCE_OAUTH_SCOPE = (
+#         "read:confluence-props%20"
+#         "read:confluence-content.all%20"
+#         "read:confluence-content.summary%20"
+#         "read:confluence-content.permission%20"
+#         "read:confluence-user%20"
+#         "read:confluence-groups%20"
+#         "readonly:content.attachment:confluence"
+#     )
+
+#     REDIRECT_URI = f"{WEB_DOMAIN}/admin/connectors/confluence/oauth/callback"
+#     DEV_REDIRECT_URI = f"https://redirectmeto.com/{REDIRECT_URI}"
+
+#     # eventually for Confluence Data Center
+#     # oauth_url = (
+#     #     f"http://localhost:8090/rest/oauth/v2/authorize?client_id={CONFLUENCE_OAUTH_CLIENT_ID}"
+#     #     f"&scope={CONFLUENCE_OAUTH_SCOPE_2}"
+#     #     f"&redirect_uri={redirectme_uri}"
+#     # )
+
+#     @classmethod
+#     def generate_oauth_url(cls, state: str) -> str:
+#         return cls._generate_oauth_url_helper(cls.REDIRECT_URI, state)
+
+#     @classmethod
+#     def generate_dev_oauth_url(cls, state: str) -> str:
+#         """dev mode workaround for localhost testing
+#         - https://www.nango.dev/blog/oauth-redirects-on-localhost-with-https
+#         """
+#         return cls._generate_oauth_url_helper(cls.DEV_REDIRECT_URI, state)
+
+#     @classmethod
+#     def _generate_oauth_url_helper(cls, redirect_uri: str, state: str) -> str:
+#         url = (
+#             "https://auth.atlassian.com/authorize"
+#             f"?audience=api.atlassian.com"
+#             f"&client_id={cls.CLIENT_ID}"
+#             f"&redirect_uri={redirect_uri}"
+#             f"&scope={cls.CONFLUENCE_OAUTH_SCOPE}"
+#             f"&state={state}"
+#             "&response_type=code"
+#             "&prompt=consent"
+#         )
+#         return url
+
+#     @classmethod
+#     def session_dump_json(cls, email: str, redirect_on_success: str | None) -> str:
+#         """Temporary state to store in redis. to be looked up on auth response.
+#         Returns a json string.
+#         """
+#         session = ConfluenceCloudOAuth.OAuthSession(
+#             email=email, redirect_on_success=redirect_on_success
+#         )
+#         return session.model_dump_json()
+
+#     @classmethod
+#     def parse_session(cls, session_json: str) -> SlackOAuth.OAuthSession:
+#         session = SlackOAuth.OAuthSession.model_validate_json(session_json)
+#         return session
+
+
+@router.post("/prepare-authorization-request")
+def prepare_authorization_request(
+    connector: DocumentSource,
+    redirect_on_success: str | None,
+    user: User = Depends(current_user),
+    tenant_id: str | None = Depends(get_current_tenant_id),
+) -> JSONResponse:
+    """Used by the frontend to generate the url for the user's browser during auth request.
+
+    Example: https://www.oauth.com/oauth2-servers/authorization/the-authorization-request/
+    """
+
+    oauth_uuid = uuid.uuid4()
+    oauth_uuid_str = str(oauth_uuid)
+    oauth_state = (
+        base64.urlsafe_b64encode(oauth_uuid.bytes).rstrip(b"=").decode("utf-8")
+    )
+
+    if connector == DocumentSource.SLACK:
+        oauth_url = SlackOAuth.generate_oauth_url(oauth_state)
+        session = SlackOAuth.session_dump_json(
+            email=user.email, redirect_on_success=redirect_on_success
+        )
+    # elif connector == DocumentSource.CONFLUENCE:
+    #     oauth_url = ConfluenceCloudOAuth.generate_oauth_url(oauth_state)
+    #     session = ConfluenceCloudOAuth.session_dump_json(
+    #         email=user.email, redirect_on_success=redirect_on_success
+    #     )
+    # elif connector == DocumentSource.JIRA:
+    #     oauth_url = JiraCloudOAuth.generate_dev_oauth_url(oauth_state)
+    # elif connector == DocumentSource.GOOGLE_DRIVE:
+    #     oauth_url = GoogleDriveOAuth.generate_dev_oauth_url(oauth_state)
+    else:
+        oauth_url = None
+
+    if not oauth_url:
+        raise HTTPException(
+            status_code=404,
+            detail=f"The document source type {connector} does not have OAuth implemented",
+        )
+
+    r = get_redis_client(tenant_id=tenant_id)
+
+    # 10 min is the max we want an oauth flow to be valid
+    r.set(f"da_oauth:{oauth_uuid_str}", session, ex=600)
+
+    return JSONResponse(content={"url": oauth_url})
+
+
+@router.post("/connector/slack/callback")
+def handle_slack_oauth_callback(
+    code: str,
+    state: str,
+    user: User = Depends(current_user),
+    db_session: Session = Depends(get_session),
+    tenant_id: str | None = Depends(get_current_tenant_id),
+) -> JSONResponse:
+    if not SlackOAuth.CLIENT_ID or not SlackOAuth.CLIENT_SECRET:
+        raise HTTPException(
+            status_code=500,
+            detail="Slack client ID or client secret is not configured.",
+        )
+
+    r = get_redis_client(tenant_id=tenant_id)
+
+    # recover the state
+    padded_state = state + "=" * (
+        -len(state) % 4
+    )  # Add padding back (Base64 decoding requires padding)
+    uuid_bytes = base64.urlsafe_b64decode(
+        padded_state
+    )  # Decode the Base64 string back to bytes
+
+    # Convert bytes back to a UUID
+    oauth_uuid = uuid.UUID(bytes=uuid_bytes)
+    oauth_uuid_str = str(oauth_uuid)
+
+    r_key = f"da_oauth:{oauth_uuid_str}"
+
+    session_json_bytes = cast(bytes, r.get(r_key))
+    if not session_json_bytes:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Slack OAuth failed - OAuth state key not found: key={r_key}",
+        )
+
+    session_json = session_json_bytes.decode("utf-8")
+    try:
+        session = SlackOAuth.parse_session(session_json)
+
+        # Exchange the authorization code for an access token
+        response = requests.post(
+            SlackOAuth.TOKEN_URL,
+            headers={"Content-Type": "application/x-www-form-urlencoded"},
+            data={
+                "client_id": SlackOAuth.CLIENT_ID,
+                "client_secret": SlackOAuth.CLIENT_SECRET,
+                "code": code,
+                "redirect_uri": SlackOAuth.REDIRECT_URI,
+            },
+        )
+
+        response_data = response.json()
+
+        if not response_data.get("ok"):
+            raise HTTPException(
+                status_code=400,
+                detail=f"Slack OAuth failed: {response_data.get('error')}",
+            )
+
+        # Extract token and team information
+        access_token: str = response_data.get("access_token")
+        team_id: str = response_data.get("team", {}).get("id")
+        authed_user_id: str = response_data.get("authed_user", {}).get("id")
+
+        credential_info = CredentialBase(
+            credential_json={"slack_bot_token": access_token},
+            admin_public=True,
+            source=DocumentSource.SLACK,
+            name="Slack OAuth",
+        )
+
+        create_credential(credential_info, user, db_session)
+    except Exception as e:
+        return JSONResponse(
+            status_code=500,
+            content={
+                "success": False,
+                "message": f"An error occurred during Slack OAuth: {str(e)}",
+            },
+        )
+    finally:
+        r.delete(r_key)
+
+    # return the result
+    return JSONResponse(
+        content={
+            "success": True,
+            "message": "Slack OAuth completed successfully.",
+            "team_id": team_id,
+            "authed_user_id": authed_user_id,
+            "redirect_on_success": session.redirect_on_success,
+        }
+    )
+
+
+# Work in progress
+# @router.post("/connector/confluence/callback")
+# def handle_confluence_oauth_callback(
+#     code: str,
+#     state: str,
+#     user: User = Depends(current_user),
+#     db_session: Session = Depends(get_session),
+#     tenant_id: str | None = Depends(get_current_tenant_id),
+# ) -> JSONResponse:
+#     if not ConfluenceCloudOAuth.CLIENT_ID or not ConfluenceCloudOAuth.CLIENT_SECRET:
+#         raise HTTPException(
+#             status_code=500,
+#             detail="Confluence client ID or client secret is not configured."
+#         )
+
+#     r = get_redis_client(tenant_id=tenant_id)
+
+#     # recover the state
+#     padded_state = state + '=' * (-len(state) % 4)  # Add padding back (Base64 decoding requires padding)
+#     uuid_bytes = base64.urlsafe_b64decode(padded_state)  # Decode the Base64 string back to bytes
+
+#     # Convert bytes back to a UUID
+#     oauth_uuid = uuid.UUID(bytes=uuid_bytes)
+#     oauth_uuid_str = str(oauth_uuid)
+
+#     r_key = f"da_oauth:{oauth_uuid_str}"
+
+#     result = r.get(r_key)
+#     if not result:
+#         raise HTTPException(
+#             status_code=400,
+#             detail=f"Confluence OAuth failed - OAuth state key not found: key={r_key}"
+#         )
+
+#     try:
+#         session = ConfluenceCloudOAuth.parse_session(result)
+
+#         # Exchange the authorization code for an access token
+#         response = requests.post(
+#             ConfluenceCloudOAuth.TOKEN_URL,
+#             headers={"Content-Type": "application/x-www-form-urlencoded"},
+#             data={
+#                 "client_id": ConfluenceCloudOAuth.CLIENT_ID,
+#                 "client_secret": ConfluenceCloudOAuth.CLIENT_SECRET,
+#                 "code": code,
+#                 "redirect_uri": ConfluenceCloudOAuth.DEV_REDIRECT_URI,
+#             },
+#         )
+
+#         response_data = response.json()
+
+#         if not response_data.get("ok"):
+#             raise HTTPException(
+#                 status_code=400,
+#                 detail=f"ConfluenceCloudOAuth OAuth failed: {response_data.get('error')}"
+#             )
+
+#         # Extract token and team information
+#         access_token: str = response_data.get("access_token")
+#         team_id: str = response_data.get("team", {}).get("id")
+#         authed_user_id: str = response_data.get("authed_user", {}).get("id")
+
+#         credential_info = CredentialBase(
+#             credential_json={"slack_bot_token": access_token},
+#             admin_public=True,
+#             source=DocumentSource.CONFLUENCE,
+#             name="Confluence OAuth",
+#         )
+
+#         logger.info(f"Slack access token: {access_token}")
+
+#         credential = create_credential(credential_info, user, db_session)
+
+#         logger.info(f"new_credential_id={credential.id}")
+#     except Exception as e:
+#         return JSONResponse(
+#             status_code=500,
+#             content={
+#                 "success": False,
+#                 "message": f"An error occurred during Slack OAuth: {str(e)}",
+#             },
+#         )
+#     finally:
+#         r.delete(r_key)
+
+#     # return the result
+#     return JSONResponse(
+#         content={
+#             "success": True,
+#             "message": "Slack OAuth completed successfully.",
+#             "team_id": team_id,
+#             "authed_user_id": authed_user_id,
+#             "redirect_on_success": session.redirect_on_success,
+#         }
+#     )

backend/ee/danswer/server/query_and_chat/chat_backend.py

@@ -6,6 +6,7 @@ from fastapi import HTTPException
 from sqlalchemy.orm import Session
 
 from danswer.auth.users import current_user
+from danswer.chat.chat_utils import combine_message_thread
 from danswer.chat.chat_utils import create_chat_chain
 from danswer.chat.models import AllCitations
 from danswer.chat.models import DanswerAnswerPiece
@@ -16,8 +17,8 @@ from danswer.chat.models import QADocsResponse
 from danswer.chat.models import StreamingError
 from danswer.chat.process_message import ChatPacketStream
 from danswer.chat.process_message import stream_chat_message_objects
+from danswer.configs.chat_configs import CHAT_TARGET_CHUNK_PERCENTAGE
 from danswer.configs.constants import MessageType
-from danswer.configs.danswerbot_configs import DANSWER_BOT_TARGET_CHUNK_PERCENTAGE
 from danswer.context.search.models import OptionalSearchSetting
 from danswer.context.search.models import RetrievalDetails
 from danswer.context.search.models import SavedSearchDoc
@@ -29,7 +30,6 @@ from danswer.db.models import User
 from danswer.llm.factory import get_llms_for_persona
 from danswer.llm.utils import get_max_input_tokens
 from danswer.natural_language_processing.utils import get_tokenizer
-from danswer.one_shot_answer.qa_utils import combine_message_thread
 from danswer.secondary_llm_flows.query_expansion import thread_based_query_rephrase
 from danswer.server.query_and_chat.models import ChatMessageDetail
 from danswer.server.query_and_chat.models import CreateChatMessageRequest
@@ -171,6 +171,8 @@ def handle_simplified_chat_message(
         prompt_id=None,
         search_doc_ids=chat_message_req.search_doc_ids,
         retrieval_options=retrieval_options,
+        # Simple API does not support reranking, hide complexity from user
+        rerank_settings=None,
         query_override=chat_message_req.query_override,
         # Currently only applies to search flow not chat
         chunks_above=0,
@@ -232,7 +234,6 @@ def handle_send_message_simple_with_history(
         description="handle_send_message_simple_with_history",
         user_id=user_id,
         persona_id=req.persona_id,
-        one_shot=False,
     )
 
     llm, _ = get_llms_for_persona(persona=chat_session.persona)
@@ -245,7 +246,7 @@ def handle_send_message_simple_with_history(
     input_tokens = get_max_input_tokens(
         model_name=llm.config.model_name, model_provider=llm.config.model_provider
     )
-    max_history_tokens = int(input_tokens * DANSWER_BOT_TARGET_CHUNK_PERCENTAGE)
+    max_history_tokens = int(input_tokens * CHAT_TARGET_CHUNK_PERCENTAGE)
 
     # Every chat Session begins with an empty root message
     root_message = get_or_create_root_message(
@@ -293,6 +294,8 @@ def handle_send_message_simple_with_history(
         prompt_id=req.prompt_id,
         search_doc_ids=req.search_doc_ids,
         retrieval_options=retrieval_options,
+        # Simple API does not support reranking, hide complexity from user
+        rerank_settings=None,
         query_override=rephrased_query,
         chunks_above=0,
         chunks_below=0,

backend/ee/danswer/server/query_and_chat/models.py

@@ -2,7 +2,13 @@ from uuid import UUID
 
 from pydantic import BaseModel
 from pydantic import Field
+from pydantic import model_validator
 
+from danswer.chat.models import CitationInfo
+from danswer.chat.models import DanswerContexts
+from danswer.chat.models import PersonaOverrideConfig
+from danswer.chat.models import QADocsResponse
+from danswer.chat.models import ThreadMessage
 from danswer.configs.constants import DocumentSource
 from danswer.context.search.enums import LLMEvaluationType
 from danswer.context.search.enums import SearchType
@@ -10,7 +16,6 @@ from danswer.context.search.models import ChunkContext
 from danswer.context.search.models import RerankingDetails
 from danswer.context.search.models import RetrievalDetails
 from danswer.context.search.models import SavedSearchDoc
-from danswer.one_shot_answer.models import ThreadMessage
 from ee.danswer.server.manage.models import StandardAnswer
 
 
@@ -96,3 +101,48 @@ class ChatBasicResponse(BaseModel):
     # TODO: deprecate both of these
     simple_search_docs: list[SimpleDoc] | None = None
     llm_chunks_indices: list[int] | None = None
+
+
+class OneShotQARequest(ChunkContext):
+    # Supports simplier APIs that don't deal with chat histories or message edits
+    # Easier APIs to work with for developers
+    persona_override_config: PersonaOverrideConfig | None = None
+    persona_id: int | None = None
+
+    messages: list[ThreadMessage]
+    prompt_id: int | None = None
+    retrieval_options: RetrievalDetails = Field(default_factory=RetrievalDetails)
+    rerank_settings: RerankingDetails | None = None
+    return_contexts: bool = False
+
+    # allows the caller to specify the exact search query they want to use
+    # can be used if the message sent to the LLM / query should not be the same
+    # will also disable Thread-based Rewording if specified
+    query_override: str | None = None
+
+    # If True, skips generative an AI response to the search query
+    skip_gen_ai_answer_generation: bool = False
+
+    @model_validator(mode="after")
+    def check_persona_fields(self) -> "OneShotQARequest":
+        if self.persona_override_config is None and self.persona_id is None:
+            raise ValueError("Exactly one of persona_config or persona_id must be set")
+        elif self.persona_override_config is not None and (
+            self.persona_id is not None or self.prompt_id is not None
+        ):
+            raise ValueError(
+                "If persona_override_config is set, persona_id and prompt_id cannot be set"
+            )
+        return self
+
+
+class OneShotQAResponse(BaseModel):
+    # This is built piece by piece, any of these can be None as the flow could break
+    answer: str | None = None
+    rephrase: str | None = None
+    citations: list[CitationInfo] | None = None
+    docs: QADocsResponse | None = None
+    llm_selected_doc_indices: list[int] | None = None
+    error_msg: str | None = None
+    chat_message_id: int | None = None
+    contexts: DanswerContexts | None = None

backend/ee/danswer/server/query_and_chat/query_backend.py

@@ -1,38 +1,47 @@
+import json
+from collections.abc import Generator
+
 from fastapi import APIRouter
 from fastapi import Depends
 from fastapi import HTTPException
+from fastapi.responses import StreamingResponse
 from pydantic import BaseModel
 from sqlalchemy.orm import Session
 
 from danswer.auth.users import current_user
-from danswer.configs.danswerbot_configs import DANSWER_BOT_TARGET_CHUNK_PERCENTAGE
+from danswer.chat.chat_utils import combine_message_thread
+from danswer.chat.chat_utils import prepare_chat_message_request
+from danswer.chat.models import PersonaOverrideConfig
+from danswer.chat.process_message import ChatPacketStream
+from danswer.chat.process_message import stream_chat_message_objects
+from danswer.configs.danswerbot_configs import MAX_THREAD_CONTEXT_PERCENTAGE
 from danswer.context.search.models import SavedSearchDocWithContent
 from danswer.context.search.models import SearchRequest
 from danswer.context.search.pipeline import SearchPipeline
 from danswer.context.search.utils import dedupe_documents
 from danswer.context.search.utils import drop_llm_indices
 from danswer.context.search.utils import relevant_sections_to_indices
+from danswer.db.chat import get_prompt_by_id
 from danswer.db.engine import get_session
+from danswer.db.models import Persona
 from danswer.db.models import User
 from danswer.db.persona import get_persona_by_id
-from danswer.llm.answering.prompts.citations_prompt import (
-    compute_max_document_tokens_for_persona,
-)
 from danswer.llm.factory import get_default_llms
 from danswer.llm.factory import get_llms_for_persona
 from danswer.llm.factory import get_main_llm_from_tuple
 from danswer.llm.utils import get_max_input_tokens
-from danswer.one_shot_answer.answer_question import get_search_answer
-from danswer.one_shot_answer.models import DirectQARequest
-from danswer.one_shot_answer.models import OneShotQAResponse
+from danswer.natural_language_processing.utils import get_tokenizer
+from danswer.server.utils import get_json_line
 from danswer.utils.logger import setup_logger
+from ee.danswer.chat.process_message import gather_stream_for_answer_api
 from ee.danswer.danswerbot.slack.handlers.handle_standard_answers import (
     oneoff_standard_answers,
 )
 from ee.danswer.server.query_and_chat.models import DocumentSearchRequest
+from ee.danswer.server.query_and_chat.models import OneShotQARequest
+from ee.danswer.server.query_and_chat.models import OneShotQAResponse
 from ee.danswer.server.query_and_chat.models import StandardAnswerRequest
 from ee.danswer.server.query_and_chat.models import StandardAnswerResponse
-from ee.danswer.server.query_and_chat.utils import create_temporary_persona
 
 
 logger = setup_logger()
@@ -125,58 +134,115 @@ def handle_search_request(
     return DocumentSearchResponse(top_documents=deduped_docs, llm_indices=llm_indices)
 
 
-@basic_router.post("/answer-with-quote")
-def get_answer_with_quote(
-    query_request: DirectQARequest,
+def get_answer_stream(
+    query_request: OneShotQARequest,
     user: User | None = Depends(current_user),
     db_session: Session = Depends(get_session),
-) -> OneShotQAResponse:
+) -> ChatPacketStream:
     query = query_request.messages[0].message
-    logger.notice(f"Received query for one shot answer API with quotes: {query}")
+    logger.notice(f"Received query for Answer API: {query}")
 
-    if query_request.persona_config is not None:
-        new_persona = create_temporary_persona(
-            db_session=db_session,
-            persona_config=query_request.persona_config,
+    if (
+        query_request.persona_override_config is None
+        and query_request.persona_id is None
+    ):
+        raise KeyError("Must provide persona ID or Persona Config")
+
+    prompt = None
+    if query_request.prompt_id is not None:
+        prompt = get_prompt_by_id(
+            prompt_id=query_request.prompt_id,
             user=user,
+            db_session=db_session,
         )
-        persona = new_persona
 
+    persona_info: Persona | PersonaOverrideConfig | None = None
+    if query_request.persona_override_config is not None:
+        persona_info = query_request.persona_override_config
     elif query_request.persona_id is not None:
-        persona = get_persona_by_id(
+        persona_info = get_persona_by_id(
             persona_id=query_request.persona_id,
             user=user,
             db_session=db_session,
             is_for_edit=False,
         )
-    else:
-        raise KeyError("Must provide persona ID or Persona Config")
 
-    llm = get_main_llm_from_tuple(
-        get_default_llms() if not persona else get_llms_for_persona(persona)
+    llm = get_main_llm_from_tuple(get_llms_for_persona(persona_info))
+
+    llm_tokenizer = get_tokenizer(
+        model_name=llm.config.model_name,
+        provider_type=llm.config.model_provider,
     )
+
     input_tokens = get_max_input_tokens(
         model_name=llm.config.model_name, model_provider=llm.config.model_provider
     )
-    max_history_tokens = int(input_tokens * DANSWER_BOT_TARGET_CHUNK_PERCENTAGE)
+    max_history_tokens = int(input_tokens * MAX_THREAD_CONTEXT_PERCENTAGE)
 
-    remaining_tokens = input_tokens - max_history_tokens
-
-    max_document_tokens = compute_max_document_tokens_for_persona(
-        persona=persona,
-        actual_user_input=query,
-        max_llm_token_override=remaining_tokens,
+    combined_message = combine_message_thread(
+        messages=query_request.messages,
+        max_tokens=max_history_tokens,
+        llm_tokenizer=llm_tokenizer,
     )
 
-    answer_details = get_search_answer(
-        query_req=query_request,
+    # Also creates a new chat session
+    request = prepare_chat_message_request(
+        message_text=combined_message,
         user=user,
-        max_document_tokens=max_document_tokens,
-        max_history_tokens=max_history_tokens,
+        persona_id=query_request.persona_id,
+        persona_override_config=query_request.persona_override_config,
+        prompt=prompt,
+        message_ts_to_respond_to=None,
+        retrieval_details=query_request.retrieval_options,
+        rerank_settings=query_request.rerank_settings,
         db_session=db_session,
     )
 
-    return answer_details
+    packets = stream_chat_message_objects(
+        new_msg_req=request,
+        user=user,
+        db_session=db_session,
+        include_contexts=query_request.return_contexts,
+    )
+
+    return packets
+
+
+@basic_router.post("/answer-with-citation")
+def get_answer_with_citation(
+    request: OneShotQARequest,
+    db_session: Session = Depends(get_session),
+    user: User | None = Depends(current_user),
+) -> OneShotQAResponse:
+    try:
+        packets = get_answer_stream(request, user, db_session)
+        answer = gather_stream_for_answer_api(packets)
+
+        if answer.error_msg:
+            raise RuntimeError(answer.error_msg)
+
+        return answer
+    except Exception as e:
+        logger.error(f"Error in get_answer_with_citation: {str(e)}", exc_info=True)
+        raise HTTPException(status_code=500, detail="An internal server error occurred")
+
+
+@basic_router.post("/stream-answer-with-citation")
+def stream_answer_with_citation(
+    request: OneShotQARequest,
+    db_session: Session = Depends(get_session),
+    user: User | None = Depends(current_user),
+) -> StreamingResponse:
+    def stream_generator() -> Generator[str, None, None]:
+        try:
+            for packet in get_answer_stream(request, user, db_session):
+                serialized = get_json_line(packet.model_dump())
+                yield serialized
+        except Exception as e:
+            logger.exception("Error in answer streaming")
+            yield json.dumps({"error": str(e)})
+
+    return StreamingResponse(stream_generator(), media_type="application/json")
 
 
 @basic_router.get("/standard-answer")

backend/ee/danswer/server/query_and_chat/utils.py

@@ -1,85 +0,0 @@
-from typing import cast
-
-from fastapi import HTTPException
-from sqlalchemy.orm import Session
-
-from danswer.auth.users import is_user_admin
-from danswer.db.llm import fetch_existing_doc_sets
-from danswer.db.llm import fetch_existing_tools
-from danswer.db.models import Persona
-from danswer.db.models import Prompt
-from danswer.db.models import Tool
-from danswer.db.models import User
-from danswer.db.persona import get_prompts_by_ids
-from danswer.one_shot_answer.models import PersonaConfig
-from danswer.tools.tool_implementations.custom.custom_tool import (
-    build_custom_tools_from_openapi_schema_and_headers,
-)
-
-
-def create_temporary_persona(
-    persona_config: PersonaConfig, db_session: Session, user: User | None = None
-) -> Persona:
-    if not is_user_admin(user):
-        raise HTTPException(
-            status_code=403,
-            detail="User is not authorized to create a persona in one shot queries",
-        )
-
-    """Create a temporary Persona object from the provided configuration."""
-    persona = Persona(
-        name=persona_config.name,
-        description=persona_config.description,
-        num_chunks=persona_config.num_chunks,
-        llm_relevance_filter=persona_config.llm_relevance_filter,
-        llm_filter_extraction=persona_config.llm_filter_extraction,
-        recency_bias=persona_config.recency_bias,
-        llm_model_provider_override=persona_config.llm_model_provider_override,
-        llm_model_version_override=persona_config.llm_model_version_override,
-    )
-
-    if persona_config.prompts:
-        persona.prompts = [
-            Prompt(
-                name=p.name,
-                description=p.description,
-                system_prompt=p.system_prompt,
-                task_prompt=p.task_prompt,
-                include_citations=p.include_citations,
-                datetime_aware=p.datetime_aware,
-            )
-            for p in persona_config.prompts
-        ]
-    elif persona_config.prompt_ids:
-        persona.prompts = get_prompts_by_ids(
-            db_session=db_session, prompt_ids=persona_config.prompt_ids
-        )
-
-    persona.tools = []
-    if persona_config.custom_tools_openapi:
-        for schema in persona_config.custom_tools_openapi:
-            tools = cast(
-                list[Tool],
-                build_custom_tools_from_openapi_schema_and_headers(schema),
-            )
-            persona.tools.extend(tools)
-
-    if persona_config.tools:
-        tool_ids = [tool.id for tool in persona_config.tools]
-        persona.tools.extend(
-            fetch_existing_tools(db_session=db_session, tool_ids=tool_ids)
-        )
-
-    if persona_config.tool_ids:
-        persona.tools.extend(
-            fetch_existing_tools(
-                db_session=db_session, tool_ids=persona_config.tool_ids
-            )
-        )
-
-    fetched_docs = fetch_existing_doc_sets(
-        db_session=db_session, doc_ids=persona_config.document_set_ids
-    )
-    persona.document_sets = fetched_docs
-
-    return persona

backend/ee/danswer/server/query_history/api.py

@@ -179,13 +179,7 @@ class QuestionAnswerPairSnapshot(BaseModel):
 
 
 def determine_flow_type(chat_session: ChatSession) -> SessionType:
-    return (
-        SessionType.SLACK
-        if chat_session.danswerbot_flow
-        else SessionType.SEARCH
-        if chat_session.one_shot
-        else SessionType.CHAT
-    )
+    return SessionType.SLACK if chat_session.danswerbot_flow else SessionType.CHAT
 
 
 def fetch_and_process_chat_session_history_minimal(

backend/ee/danswer/server/reporting/usage_export_models.py

@@ -9,7 +9,6 @@ from danswer.auth.schemas import UserStatus
 
 class FlowType(str, Enum):
     CHAT = "chat"
-    SEARCH = "search"
     SLACK = "slack"