Compare commits

..

14 Commits

Author SHA1 Message Date
pablonyx
9087320a06 fix 2025-03-06 14:46:20 -08:00
pablonyx
b0af1458c0 ensure checks pass 2025-03-06 14:46:20 -08:00
pablonyx
bb67a7a122 remove unnecessary logs 2025-03-06 14:46:20 -08:00
pablonyx
e239dc31c1 rename 2025-03-06 14:46:19 -08:00
pablonyx
027128502c add csl 2025-03-06 14:46:19 -08:00
Chris Weaver
a7a374dc81 Confluence fixes (#4220)
* Confluence fixes

* Small tweak

* Address greptile comments
2025-03-06 20:57:07 +00:00
rkuo-danswer
facc8cc2fa add scope needed for permission sync (#4198)
Co-authored-by: Richard Kuo (Danswer) <rkuo@onyx.app>
2025-03-06 20:03:38 +00:00
rkuo-danswer
2c0af0a0ca Feature/helm updates (#4201)
* add ingress for api and web

* helm setup docs

* add letsencrypt. close blocks

* use pathType ImplementationSpecific as Prefix is deprecated

* fix backend labels. configure nginx routes. update annotations

* fix linting

---------

Co-authored-by: Sajjad Anwar <sajjadkm@gmail.com>
Co-authored-by: Richard Kuo (Danswer) <rkuo@onyx.app>
2025-03-06 19:48:20 +00:00
pablonyx
bfbc1cd954 k (#4172) 2025-03-06 18:55:12 +00:00
pablonyx
626da583aa Fix gated tenants (#4177)
* fix

* mypy .
2025-03-06 18:07:15 +00:00
pablonyx
92faca139d Fix extra tenant mystery (#4197)
* fix extra tenant mystery

* nit
2025-03-06 18:06:49 +00:00
pablonyx
cec05c5ee9 Revert "k"
This reverts commit 687122911d.
2025-03-06 09:38:31 -08:00
Richard Kuo (Danswer)
eaf054ef06 oauth router went missing? 2025-03-05 15:50:23 -08:00
pablonyx
a7a1a24658 minor nit 2025-03-05 15:35:02 -08:00
25 changed files with 432 additions and 421 deletions

View File

@@ -0,0 +1,125 @@
"""Update GitHub connector repo_name to repositories
Revision ID: 3934b1bc7b62
Revises: b7c2b63c4a03
Create Date: 2025-03-05 10:50:30.516962
"""
from alembic import op
import sqlalchemy as sa
import json
import logging
# revision identifiers, used by Alembic.
revision = "3934b1bc7b62"
down_revision = "b7c2b63c4a03"
branch_labels = None
depends_on = None
logger = logging.getLogger("alembic.runtime.migration")
def upgrade() -> None:
# Get all GitHub connectors
conn = op.get_bind()
# First get all GitHub connectors
github_connectors = conn.execute(
sa.text(
"""
SELECT id, connector_specific_config
FROM connector
WHERE source = 'GITHUB'
"""
)
).fetchall()
# Update each connector's config
updated_count = 0
for connector_id, config in github_connectors:
try:
if not config:
logger.warning(f"Connector {connector_id} has no config, skipping")
continue
# Parse the config if it's a string
if isinstance(config, str):
config = json.loads(config)
if "repo_name" not in config:
continue
# Create new config with repositories instead of repo_name
new_config = dict(config)
repo_name_value = new_config.pop("repo_name")
new_config["repositories"] = repo_name_value
# Update the connector with the new config
conn.execute(
sa.text(
"""
UPDATE connector
SET connector_specific_config = :new_config
WHERE id = :connector_id
"""
),
{"connector_id": connector_id, "new_config": json.dumps(new_config)},
)
updated_count += 1
except Exception as e:
logger.error(f"Error updating connector {connector_id}: {str(e)}")
def downgrade() -> None:
# Get all GitHub connectors
conn = op.get_bind()
logger.debug(
"Starting rollback of GitHub connectors from repositories to repo_name"
)
github_connectors = conn.execute(
sa.text(
"""
SELECT id, connector_specific_config
FROM connector
WHERE source = 'GITHUB'
"""
)
).fetchall()
logger.debug(f"Found {len(github_connectors)} GitHub connectors to rollback")
# Revert each GitHub connector to use repo_name instead of repositories
reverted_count = 0
for connector_id, config in github_connectors:
try:
if not config:
continue
# Parse the config if it's a string
if isinstance(config, str):
config = json.loads(config)
if "repositories" not in config:
continue
# Create new config with repo_name instead of repositories
new_config = dict(config)
repositories_value = new_config.pop("repositories")
new_config["repo_name"] = repositories_value
# Update the connector with the new config
conn.execute(
sa.text(
"""
UPDATE connector
SET connector_specific_config = :new_config
WHERE id = :connector_id
"""
),
{"new_config": json.dumps(new_config), "connector_id": connector_id},
)
reverted_count += 1
except Exception as e:
logger.error(f"Error reverting connector {connector_id}: {str(e)}")

View File

@@ -6,8 +6,7 @@ Create Date: 2025-02-26 13:07:56.217791
"""
from alembic import op
import time
from sqlalchemy import text
# revision identifiers, used by Alembic.
revision = "3bd4c84fe72f"
@@ -28,357 +27,45 @@ depends_on = None
# 4. Adds indexes to both chat_message and chat_session tables for comprehensive search
def upgrade():
# --- PART 1: chat_message table ---
# Step 1: Add nullable column (quick, minimal locking)
# op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv")
# op.execute("DROP TRIGGER IF EXISTS chat_message_tsv_trigger ON chat_message")
# op.execute("DROP FUNCTION IF EXISTS update_chat_message_tsv()")
# op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv")
# # Drop chat_session tsv trigger if it exists
# op.execute("DROP TRIGGER IF EXISTS chat_session_tsv_trigger ON chat_session")
# op.execute("DROP FUNCTION IF EXISTS update_chat_session_tsv()")
# op.execute("ALTER TABLE chat_session DROP COLUMN IF EXISTS title_tsv")
# raise Exception("Stop here")
time.time()
op.execute("ALTER TABLE chat_message ADD COLUMN IF NOT EXISTS message_tsv tsvector")
# Step 2: Create function and trigger for new/updated rows
def upgrade() -> None:
# Create a GIN index for full-text search on chat_message.message
op.execute(
"""
CREATE OR REPLACE FUNCTION update_chat_message_tsv()
RETURNS TRIGGER AS $$
BEGIN
NEW.message_tsv = to_tsvector('english', NEW.message);
RETURN NEW;
END;
$$ LANGUAGE plpgsql
"""
ALTER TABLE chat_message
ADD COLUMN message_tsv tsvector
GENERATED ALWAYS AS (to_tsvector('english', message)) STORED;
"""
)
# Create trigger in a separate execute call
# Commit the current transaction before creating concurrent indexes
op.execute("COMMIT")
op.execute(
"""
CREATE TRIGGER chat_message_tsv_trigger
BEFORE INSERT OR UPDATE ON chat_message
FOR EACH ROW EXECUTE FUNCTION update_chat_message_tsv()
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_message_tsv
ON chat_message
USING GIN (message_tsv)
"""
)
# Step 3: Update existing rows in batches using Python
time.time()
# Get connection and count total rows
connection = op.get_bind()
total_count_result = connection.execute(
text("SELECT COUNT(*) FROM chat_message")
).scalar()
total_count = total_count_result if total_count_result is not None else 0
batch_size = 5000
batches = 0
# Calculate total batches needed
total_batches = (
(total_count + batch_size - 1) // batch_size if total_count > 0 else 0
# Also add a stored tsvector column for chat_session.description
op.execute(
"""
ALTER TABLE chat_session
ADD COLUMN description_tsv tsvector
GENERATED ALWAYS AS (to_tsvector('english', coalesce(description, ''))) STORED;
"""
)
# Process in batches - properly handling UUIDs by using OFFSET/LIMIT approach
for batch_num in range(total_batches):
offset = batch_num * batch_size
# Commit again before creating the second concurrent index
op.execute("COMMIT")
# Execute update for this batch using OFFSET/LIMIT which works with UUIDs
connection.execute(
text(
"""
UPDATE chat_message
SET message_tsv = to_tsvector('english', message)
WHERE id IN (
SELECT id FROM chat_message
WHERE message_tsv IS NULL
ORDER BY id
LIMIT :batch_size OFFSET :offset
)
"""
).bindparams(batch_size=batch_size, offset=offset)
)
# Commit each batch
connection.execute(text("COMMIT"))
# Start a new transaction
connection.execute(text("BEGIN"))
batches += 1
# Final check for any remaining NULL values
connection.execute(
text(
"""
UPDATE chat_message SET message_tsv = to_tsvector('english', message)
WHERE message_tsv IS NULL
"""
)
)
# Create GIN index concurrently
connection.execute(text("COMMIT"))
time.time()
connection.execute(
text(
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_message_tsv
ON chat_message USING GIN (message_tsv)
"""
)
)
# First drop the trigger as it won't be needed anymore
connection.execute(
text(
"""
DROP TRIGGER IF EXISTS chat_message_tsv_trigger ON chat_message;
"""
)
)
connection.execute(
text(
"""
DROP FUNCTION IF EXISTS update_chat_message_tsv();
"""
)
)
# Add new generated column
time.time()
connection.execute(
text(
"""
ALTER TABLE chat_message
ADD COLUMN message_tsv_gen tsvector
GENERATED ALWAYS AS (to_tsvector('english', message)) STORED;
"""
)
)
connection.execute(text("COMMIT"))
time.time()
connection.execute(
text(
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_message_tsv_gen
ON chat_message USING GIN (message_tsv_gen)
"""
)
)
# Drop old index and column
connection.execute(text("COMMIT"))
connection.execute(
text(
"""
DROP INDEX CONCURRENTLY IF EXISTS idx_chat_message_tsv;
"""
)
)
connection.execute(text("COMMIT"))
connection.execute(
text(
"""
ALTER TABLE chat_message DROP COLUMN message_tsv;
"""
)
)
# Rename new column to old name
connection.execute(
text(
"""
ALTER TABLE chat_message RENAME COLUMN message_tsv_gen TO message_tsv;
"""
)
)
# --- PART 2: chat_session table ---
# Step 1: Add nullable column (quick, minimal locking)
time.time()
connection.execute(
text(
"ALTER TABLE chat_session ADD COLUMN IF NOT EXISTS description_tsv tsvector"
)
)
# Step 2: Create function and trigger for new/updated rows - SPLIT INTO SEPARATE CALLS
connection.execute(
text(
"""
CREATE OR REPLACE FUNCTION update_chat_session_tsv()
RETURNS TRIGGER AS $$
BEGIN
NEW.description_tsv = to_tsvector('english', COALESCE(NEW.description, ''));
RETURN NEW;
END;
$$ LANGUAGE plpgsql
"""
)
)
# Create trigger in a separate execute call
connection.execute(
text(
"""
CREATE TRIGGER chat_session_tsv_trigger
BEFORE INSERT OR UPDATE ON chat_session
FOR EACH ROW EXECUTE FUNCTION update_chat_session_tsv()
"""
)
)
# Step 3: Update existing rows in batches using Python
time.time()
# Get the maximum ID to determine batch count
# Cast id to text for MAX function since it's a UUID
max_id_result = connection.execute(
text("SELECT COALESCE(MAX(id::text), '0') FROM chat_session")
).scalar()
max_id_result if max_id_result is not None else "0"
batch_size = 5000
batches = 0
# Get all IDs ordered to process in batches
rows = connection.execute(
text("SELECT id FROM chat_session ORDER BY id")
).fetchall()
total_rows = len(rows)
# Process in batches
for batch_num, batch_start in enumerate(range(0, total_rows, batch_size)):
batch_end = min(batch_start + batch_size, total_rows)
batch_ids = [row[0] for row in rows[batch_start:batch_end]]
if not batch_ids:
continue
# Use IN clause instead of BETWEEN for UUIDs
placeholders = ", ".join([f":id{i}" for i in range(len(batch_ids))])
params = {f"id{i}": id_val for i, id_val in enumerate(batch_ids)}
# Execute update for this batch
connection.execute(
text(
f"""
UPDATE chat_session
SET description_tsv = to_tsvector('english', COALESCE(description, ''))
WHERE id IN ({placeholders})
AND description_tsv IS NULL
"""
).bindparams(**params)
)
# Commit each batch
connection.execute(text("COMMIT"))
# Start a new transaction
connection.execute(text("BEGIN"))
batches += 1
# Final check for any remaining NULL values
connection.execute(
text(
"""
UPDATE chat_session SET description_tsv = to_tsvector('english', COALESCE(description, ''))
WHERE description_tsv IS NULL
"""
)
)
# Create GIN index concurrently
connection.execute(text("COMMIT"))
time.time()
connection.execute(
text(
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_session_desc_tsv
ON chat_session USING GIN (description_tsv)
"""
)
)
# After Final check for chat_session
# First drop the trigger as it won't be needed anymore
connection.execute(
text(
"""
DROP TRIGGER IF EXISTS chat_session_tsv_trigger ON chat_session;
"""
)
)
connection.execute(
text(
"""
DROP FUNCTION IF EXISTS update_chat_session_tsv();
"""
)
)
# Add new generated column
time.time()
connection.execute(
text(
"""
ALTER TABLE chat_session
ADD COLUMN description_tsv_gen tsvector
GENERATED ALWAYS AS (to_tsvector('english', COALESCE(description, ''))) STORED;
"""
)
)
# Create new index on generated column
connection.execute(text("COMMIT"))
time.time()
connection.execute(
text(
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_session_desc_tsv_gen
ON chat_session USING GIN (description_tsv_gen)
"""
)
)
# Drop old index and column
connection.execute(text("COMMIT"))
connection.execute(
text(
"""
DROP INDEX CONCURRENTLY IF EXISTS idx_chat_session_desc_tsv;
"""
)
)
connection.execute(text("COMMIT"))
connection.execute(
text(
"""
ALTER TABLE chat_session DROP COLUMN description_tsv;
"""
)
)
# Rename new column to old name
connection.execute(
text(
"""
ALTER TABLE chat_session RENAME COLUMN description_tsv_gen TO description_tsv;
"""
)
op.execute(
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_session_desc_tsv
ON chat_session
USING GIN (description_tsv)
"""
)

View File

@@ -15,7 +15,7 @@ from ee.onyx.server.enterprise_settings.api import (
)
from ee.onyx.server.manage.standard_answer import router as standard_answer_router
from ee.onyx.server.middleware.tenant_tracking import add_tenant_id_middleware
from ee.onyx.server.oauth.api import router as oauth_router
from ee.onyx.server.oauth.api import router as ee_oauth_router
from ee.onyx.server.query_and_chat.chat_backend import (
router as chat_router,
)
@@ -128,7 +128,7 @@ 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)
include_router_with_global_prefix_prepended(application, ee_oauth_router)
# Enterprise-only global settings
include_router_with_global_prefix_prepended(

View File

@@ -80,6 +80,7 @@ class ConfluenceCloudOAuth:
"search:confluence%20"
# granular scope
"read:attachment:confluence%20" # possibly unneeded unless calling v2 attachments api
"read:content-details:confluence%20" # for permission sync
"offline_access"
)

View File

@@ -48,4 +48,5 @@ def store_product_gating(tenant_id: str, application_status: ApplicationStatus)
def get_gated_tenants() -> set[str]:
redis_client = get_redis_replica_client(tenant_id=ONYX_CLOUD_TENANT_ID)
return cast(set[str], redis_client.smembers(GATED_TENANTS_KEY))
gated_tenants_bytes = cast(set[bytes], redis_client.smembers(GATED_TENANTS_KEY))
return {tenant_id.decode("utf-8") for tenant_id in gated_tenants_bytes}

View File

@@ -55,7 +55,11 @@ logger = logging.getLogger(__name__)
async def get_or_provision_tenant(
email: str, referral_source: str | None = None, request: Request | None = None
) -> str:
"""Get existing tenant ID for an email or create a new tenant if none exists."""
"""
Get existing tenant ID for an email or create a new tenant if none exists.
This function should only be called after we have verified we want this user's tenant to exist.
It returns the tenant ID associated with the email, creating a new tenant if necessary.
"""
if not MULTI_TENANT:
return POSTGRES_DEFAULT_SCHEMA

View File

@@ -587,14 +587,20 @@ class UserManager(UUIDIDMixin, BaseUserManager[User, uuid.UUID]):
) -> Optional[User]:
email = credentials.username
# Get tenant_id from mapping table
tenant_id = await fetch_ee_implementation_or_noop(
"onyx.server.tenants.provisioning",
"get_or_provision_tenant",
async_return_default_schema,
)(
email=email,
)
tenant_id: str | None = None
try:
tenant_id = fetch_ee_implementation_or_noop(
"onyx.server.tenants.provisioning",
"get_tenant_id_for_email",
None,
)(
email=email,
)
except Exception as e:
logger.warning(
f"User attempted to login with invalid credentials: {str(e)}"
)
if not tenant_id:
# User not found in mapping
self.password_helper.hash(credentials.password)

View File

@@ -240,7 +240,7 @@ class ConfluenceConnector(
# Extract basic page information
page_id = page["id"]
page_title = page["title"]
page_url = f"{self.wiki_base}/wiki{page['_links']['webui']}"
page_url = f"{self.wiki_base}{page['_links']['webui']}"
# Get the page content
page_content = extract_text_from_confluence_html(

View File

@@ -124,14 +124,14 @@ class GithubConnector(LoadConnector, PollConnector):
def __init__(
self,
repo_owner: str,
repo_name: str | None = None,
repositories: str | None = None,
batch_size: int = INDEX_BATCH_SIZE,
state_filter: str = "all",
include_prs: bool = True,
include_issues: bool = False,
) -> None:
self.repo_owner = repo_owner
self.repo_name = repo_name
self.repositories = repositories
self.batch_size = batch_size
self.state_filter = state_filter
self.include_prs = include_prs
@@ -157,11 +157,42 @@ class GithubConnector(LoadConnector, PollConnector):
)
try:
return github_client.get_repo(f"{self.repo_owner}/{self.repo_name}")
return github_client.get_repo(f"{self.repo_owner}/{self.repositories}")
except RateLimitExceededException:
_sleep_after_rate_limit_exception(github_client)
return self._get_github_repo(github_client, attempt_num + 1)
def _get_github_repos(
self, github_client: Github, attempt_num: int = 0
) -> list[Repository.Repository]:
"""Get specific repositories based on comma-separated repo_name string."""
if attempt_num > _MAX_NUM_RATE_LIMIT_RETRIES:
raise RuntimeError(
"Re-tried fetching repos too many times. Something is going wrong with fetching objects from Github"
)
try:
repos = []
# Split repo_name by comma and strip whitespace
repo_names = [
name.strip() for name in (cast(str, self.repositories)).split(",")
]
for repo_name in repo_names:
if repo_name: # Skip empty strings
try:
repo = github_client.get_repo(f"{self.repo_owner}/{repo_name}")
repos.append(repo)
except GithubException as e:
logger.warning(
f"Could not fetch repo {self.repo_owner}/{repo_name}: {e}"
)
return repos
except RateLimitExceededException:
_sleep_after_rate_limit_exception(github_client)
return self._get_github_repos(github_client, attempt_num + 1)
def _get_all_repos(
self, github_client: Github, attempt_num: int = 0
) -> list[Repository.Repository]:
@@ -189,11 +220,17 @@ class GithubConnector(LoadConnector, PollConnector):
if self.github_client is None:
raise ConnectorMissingCredentialError("GitHub")
repos = (
[self._get_github_repo(self.github_client)]
if self.repo_name
else self._get_all_repos(self.github_client)
)
repos = []
if self.repositories:
if "," in self.repositories:
# Multiple repositories specified
repos = self._get_github_repos(self.github_client)
else:
# Single repository (backward compatibility)
repos = [self._get_github_repo(self.github_client)]
else:
# All repositories
repos = self._get_all_repos(self.github_client)
for repo in repos:
if self.include_prs:
@@ -268,11 +305,48 @@ class GithubConnector(LoadConnector, PollConnector):
)
try:
if self.repo_name:
test_repo = self.github_client.get_repo(
f"{self.repo_owner}/{self.repo_name}"
)
test_repo.get_contents("")
if self.repositories:
if "," in self.repositories:
# Multiple repositories specified
repo_names = [name.strip() for name in self.repositories.split(",")]
if not repo_names:
raise ConnectorValidationError(
"Invalid connector settings: No valid repository names provided."
)
# Validate at least one repository exists and is accessible
valid_repos = False
validation_errors = []
for repo_name in repo_names:
if not repo_name:
continue
try:
test_repo = self.github_client.get_repo(
f"{self.repo_owner}/{repo_name}"
)
test_repo.get_contents("")
valid_repos = True
# If at least one repo is valid, we can proceed
break
except GithubException as e:
validation_errors.append(
f"Repository '{repo_name}': {e.data.get('message', str(e))}"
)
if not valid_repos:
error_msg = (
"None of the specified repositories could be accessed: "
)
error_msg += ", ".join(validation_errors)
raise ConnectorValidationError(error_msg)
else:
# Single repository (backward compatibility)
test_repo = self.github_client.get_repo(
f"{self.repo_owner}/{self.repositories}"
)
test_repo.get_contents("")
else:
# Try to get organization first
try:
@@ -298,10 +372,15 @@ class GithubConnector(LoadConnector, PollConnector):
"Your GitHub token does not have sufficient permissions for this repository (HTTP 403)."
)
elif e.status == 404:
if self.repo_name:
raise ConnectorValidationError(
f"GitHub repository not found with name: {self.repo_owner}/{self.repo_name}"
)
if self.repositories:
if "," in self.repositories:
raise ConnectorValidationError(
f"None of the specified GitHub repositories could be found for owner: {self.repo_owner}"
)
else:
raise ConnectorValidationError(
f"GitHub repository not found with name: {self.repo_owner}/{self.repositories}"
)
else:
raise ConnectorValidationError(
f"GitHub user or organization not found: {self.repo_owner}"
@@ -310,6 +389,7 @@ class GithubConnector(LoadConnector, PollConnector):
raise ConnectorValidationError(
f"Unexpected GitHub error (status={e.status}): {e.data}"
)
except Exception as exc:
raise Exception(
f"Unexpected error during GitHub settings validation: {exc}"
@@ -321,7 +401,7 @@ if __name__ == "__main__":
connector = GithubConnector(
repo_owner=os.environ["REPO_OWNER"],
repo_name=os.environ["REPO_NAME"],
repositories=os.environ["REPOSITORIES"],
)
connector.load_credentials(
{"github_access_token": os.environ["GITHUB_ACCESS_TOKEN"]}

View File

@@ -464,12 +464,29 @@ def index_doc_batch(
),
)
successful_doc_ids = {record.document_id for record in insertion_records}
if successful_doc_ids != set(updatable_ids):
all_returned_doc_ids = (
{record.document_id for record in insertion_records}
.union(
{
record.failed_document.document_id
for record in vector_db_write_failures
if record.failed_document
}
)
.union(
{
record.failed_document.document_id
for record in embedding_failures
if record.failed_document
}
)
)
if all_returned_doc_ids != set(updatable_ids):
raise RuntimeError(
f"Some documents were not successfully indexed. "
f"Updatable IDs: {updatable_ids}, "
f"Successful IDs: {successful_doc_ids}"
f"Returned IDs: {all_returned_doc_ids}. "
"This should never happen."
)
last_modified_ids = []

View File

@@ -51,6 +51,7 @@ from onyx.server.documents.cc_pair import router as cc_pair_router
from onyx.server.documents.connector import router as connector_router
from onyx.server.documents.credential import router as credential_router
from onyx.server.documents.document import router as document_router
from onyx.server.documents.standard_oauth import router as standard_oauth_router
from onyx.server.features.document_set.api import router as document_set_router
from onyx.server.features.folder.api import router as folder_router
from onyx.server.features.input_prompt.api import (
@@ -322,6 +323,7 @@ def get_application() -> FastAPI:
)
include_router_with_global_prefix_prepended(application, long_term_logs_router)
include_router_with_global_prefix_prepended(application, api_key_router)
include_router_with_global_prefix_prepended(application, standard_oauth_router)
if AUTH_TYPE == AuthType.DISABLED:
# Server logs this during auth setup verification step

View File

@@ -45,7 +45,7 @@ def test_confluence_connector_basic(
with pytest.raises(StopIteration):
next(doc_batch_generator)
assert len(doc_batch) == 3
assert len(doc_batch) == 2
page_within_a_page_doc: Document | None = None
page_doc: Document | None = None

View File

@@ -80,3 +80,13 @@ prod cluster**
- `kubectl delete -f .`
- To not delete the persistent volumes (Document indexes and Users), specify the specific `.yaml` files instead of
`.` without specifying delete on persistent-volumes.yaml.
### Using Helm to deploy to an existing cluster
Onyx has a helm chart that is convenient to install all services to an existing Kubernetes cluster. To install:
* Currently the helm chart is not published so to install, clone the repo.
* Configure access to the cluster via kubectl. Ensure the kubectl context is set to the cluster that you want to use
* The default secrets, environment variables and other service level configuration are stored in `deployment/helm/charts/onyx/values.yml`. You may create another `override.yml`
* `cd deployment/helm/charts/onyx` and run `helm install onyx -n onyx -f override.yaml .`. This will install onyx on the cluster under the `onyx` namespace.
* Check the status of the deploy using `kubectl get pods -n onyx`

View File

@@ -0,0 +1,27 @@
{{- if .Values.ingress.enabled -}}
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: {{ include "onyx-stack.fullname" . }}-ingress-api
annotations:
kubernetes.io/ingress.class: nginx
nginx.ingress.kubernetes.io/rewrite-target: /$2
nginx.ingress.kubernetes.io/use-regex: "true"
cert-manager.io/cluster-issuer: {{ include "onyx-stack.fullname" . }}-letsencrypt
spec:
rules:
- host: {{ .Values.ingress.api.host }}
http:
paths:
- path: /api(/|$)(.*)
pathType: Prefix
backend:
service:
name: {{ include "onyx-stack.fullname" . }}-api-service
port:
number: {{ .Values.api.service.servicePort }}
tls:
- hosts:
- {{ .Values.ingress.api.host }}
secretName: {{ include "onyx-stack.fullname" . }}-ingress-api-tls
{{- end }}

View File

@@ -0,0 +1,26 @@
{{- if .Values.ingress.enabled -}}
apiVersion: networking.k8s.io/v1
kind: Ingress
metadata:
name: {{ include "onyx-stack.fullname" . }}-ingress-webserver
annotations:
kubernetes.io/ingress.class: nginx
cert-manager.io/cluster-issuer: {{ include "onyx-stack.fullname" . }}-letsencrypt
kubernetes.io/tls-acme: "true"
spec:
rules:
- host: {{ .Values.ingress.webserver.host }}
http:
paths:
- path: /
pathType: Prefix
backend:
service:
name: {{ include "onyx-stack.fullname" . }}-webserver
port:
number: {{ .Values.webserver.service.servicePort }}
tls:
- hosts:
- {{ .Values.ingress.webserver.host }}
secretName: {{ include "onyx-stack.fullname" . }}-ingress-webserver-tls
{{- end }}

View File

@@ -0,0 +1,20 @@
{{- if .Values.letsencrypt.enabled -}}
apiVersion: cert-manager.io/v1
kind: ClusterIssuer
metadata:
name: {{ include "onyx-stack.fullname" . }}-letsencrypt
spec:
acme:
# The ACME server URL
server: https://acme-v02.api.letsencrypt.org/directory
# Email address used for ACME registration
email: {{ .Values.letsencrypt.email }}
# Name of a secret used to store the ACME account private key
privateKeySecretRef:
name: {{ include "onyx-stack.fullname" . }}-letsencrypt
# Enable the HTTP-01 challenge provider
solvers:
- http01:
ingress:
class: nginx
{{- end }}

View File

@@ -376,22 +376,17 @@ redis:
existingSecret: onyx-secrets
existingSecretPasswordKey: redis_password
# ingress:
# enabled: false
# className: ""
# annotations: {}
# # kubernetes.io/ingress.class: nginx
# # kubernetes.io/tls-acme: "true"
# hosts:
# - host: chart-example.local
# paths:
# - path: /
# pathType: ImplementationSpecific
# tls: []
# # - secretName: chart-example-tls
# # hosts:
# # - chart-example.local
ingress:
enabled: false
className: ""
api:
host: onyx.local
webserver:
host: onyx.local
letsencrypt:
enabled: false
email: "abc@abc.com"
auth:
# existingSecret onyx-secret for storing smtp, oauth, slack, and other secrets

View File

@@ -290,21 +290,24 @@ export function SettingsForm() {
id="chatRetentionInput"
placeholder="Infinite Retention"
/>
<Button
onClick={handleSetChatRetention}
variant="submit"
size="sm"
className="mr-3"
>
Set Retention Limit
</Button>
<Button
onClick={handleClearChatRetention}
variant="default"
size="sm"
>
Retain All
</Button>
<div className="mr-auto flex gap-2">
<Button
onClick={handleSetChatRetention}
variant="submit"
size="sm"
className="mr-auto"
>
Set Retention Limit
</Button>
<Button
onClick={handleClearChatRetention}
variant="default"
size="sm"
className="mr-auto"
>
Retain All
</Button>
</div>
</>
)}

View File

@@ -61,6 +61,7 @@ export function EmailPasswordForm({
if (!response.ok) {
setIsWorking(false);
const errorDetail = (await response.json()).detail;
let errorMsg = "Unknown error";
if (typeof errorDetail === "object" && errorDetail.reason) {
@@ -96,12 +97,13 @@ export function EmailPasswordForm({
} else {
setIsWorking(false);
const errorDetail = (await loginResponse.json()).detail;
let errorMsg = "Unknown error";
if (errorDetail === "LOGIN_BAD_CREDENTIALS") {
errorMsg = "Invalid email or password";
} else if (errorDetail === "NO_WEB_LOGIN_AND_HAS_NO_PASSWORD") {
errorMsg = "Create an account to set a password";
} else if (typeof errorDetail === "string") {
errorMsg = errorDetail;
}
if (loginResponse.status === 429) {
errorMsg = "Too many requests. Please try again later.";

View File

@@ -191,6 +191,7 @@ export const FolderDropdown = forwardRef<HTMLDivElement, FolderDropdownProps>(
onChange={(e) => setNewFolderName(e.target.value)}
className="text-sm font-medium bg-transparent outline-none w-full pb-1 border-b border-background-500 transition-colors duration-200"
onKeyDown={(e) => {
e.stopPropagation();
if (e.key === "Enter") {
handleEdit();
}

View File

@@ -303,7 +303,6 @@ const FolderItem = ({
key={chatSession.id}
chatSession={chatSession}
isSelected={chatSession.id === currentChatId}
skipGradient={isDragOver}
showShareModal={showShareModal}
showDeleteModal={showDeleteModal}
/>

View File

@@ -32,21 +32,17 @@ export function ChatSessionDisplay({
chatSession,
search,
isSelected,
skipGradient,
closeSidebar,
showShareModal,
showDeleteModal,
foldersExisting,
isDragging,
}: {
chatSession: ChatSession;
isSelected: boolean;
search?: boolean;
skipGradient?: boolean;
closeSidebar?: () => void;
showShareModal?: (chatSession: ChatSession) => void;
showDeleteModal?: (chatSession: ChatSession) => void;
foldersExisting?: boolean;
isDragging?: boolean;
}) {
const router = useRouter();
@@ -238,8 +234,12 @@ export function ChatSessionDisplay({
e.preventDefault();
e.stopPropagation();
}}
onChange={(e) => setChatName(e.target.value)}
onChange={(e) => {
setChatName(e.target.value);
}}
onKeyDown={(event) => {
event.stopPropagation();
if (event.key === "Enter") {
onRename();
event.preventDefault();

View File

@@ -264,7 +264,6 @@ export function PagesTab({
>
<ChatSessionDisplay
chatSession={chat}
foldersExisting={foldersExisting}
isSelected={currentChatId === chat.id}
showShareModal={showShareModal}
showDeleteModal={showDeleteModal}

View File

@@ -40,8 +40,12 @@ export const ConnectorTitle = ({
const typedConnector = connector as Connector<GithubConfig>;
additionalMetadata.set(
"Repo",
typedConnector.connector_specific_config.repo_name
? `${typedConnector.connector_specific_config.repo_owner}/${typedConnector.connector_specific_config.repo_name}`
typedConnector.connector_specific_config.repositories
? `${typedConnector.connector_specific_config.repo_owner}/${
typedConnector.connector_specific_config.repositories.includes(",")
? "multiple repos"
: typedConnector.connector_specific_config.repositories
}`
: `${typedConnector.connector_specific_config.repo_owner}/*`
);
} else if (connector.source === "gitlab") {

View File

@@ -190,10 +190,12 @@ export const connectorConfigs: Record<
fields: [
{
type: "text",
query: "Enter the repository name:",
label: "Repository Name",
name: "repo_name",
query: "Enter the repository name(s):",
label: "Repository Name(s)",
name: "repositories",
optional: false,
description:
"For multiple repositories, enter comma-separated names (e.g., repo1,repo2,repo3)",
},
],
},
@@ -1358,7 +1360,7 @@ export interface WebConfig {
export interface GithubConfig {
repo_owner: string;
repo_name: string;
repositories: string; // Comma-separated list of repository names
include_prs: boolean;
include_issues: boolean;
}