Compare commits

..

4 Commits

Author SHA1 Message Date
pablodanswer
547fefb306 nit 2025-02-13 15:10:29 -08:00
pablodanswer
2c36dd162d update 2025-02-13 14:55:53 -08:00
pablodanswer
e0f1ca974e quick nit 2025-02-13 14:55:53 -08:00
pablodanswer
737c6118a4 reduce errors in workers 2025-02-13 14:55:53 -08:00
1117 changed files with 23210 additions and 70734 deletions

1
.github/CODEOWNERS vendored
View File

@@ -1 +0,0 @@
* @onyx-dot-app/onyx-core-team

View File

@@ -65,7 +65,6 @@ jobs:
NEXT_PUBLIC_POSTHOG_KEY=${{ secrets.POSTHOG_KEY }}
NEXT_PUBLIC_POSTHOG_HOST=${{ secrets.POSTHOG_HOST }}
NEXT_PUBLIC_SENTRY_DSN=${{ secrets.SENTRY_DSN }}
NEXT_PUBLIC_STRIPE_PUBLISHABLE_KEY=${{ secrets.STRIPE_PUBLISHABLE_KEY }}
NEXT_PUBLIC_GTM_ENABLED=true
NEXT_PUBLIC_FORGOT_PASSWORD_ENABLED=true
NEXT_PUBLIC_INCLUDE_ERROR_POPUP_SUPPORT_LINK=true

View File

@@ -4,6 +4,9 @@ on:
push:
tags:
- "*"
paths:
- 'backend/model_server/**'
- 'backend/Dockerfile.model_server'
env:
REGISTRY_IMAGE: ${{ contains(github.ref_name, 'cloud') && 'onyxdotapp/onyx-model-server-cloud' || 'onyxdotapp/onyx-model-server' }}
@@ -12,43 +15,7 @@ env:
BUILDKIT_PROGRESS: plain
jobs:
# Bypassing this for now as the idea of not building is glitching
# releases and builds that depends on everything being tagged in docker
# 1) Preliminary job to check if the changed files are relevant
# check_model_server_changes:
# runs-on: ubuntu-latest
# outputs:
# changed: ${{ steps.check.outputs.changed }}
# steps:
# - name: Checkout code
# uses: actions/checkout@v4
#
# - name: Check if relevant files changed
# id: check
# run: |
# # Default to "false"
# echo "changed=false" >> $GITHUB_OUTPUT
#
# # Compare the previous commit (github.event.before) to the current one (github.sha)
# # If any file in backend/model_server/** or backend/Dockerfile.model_server is changed,
# # set changed=true
# if git diff --name-only ${{ github.event.before }} ${{ github.sha }} \
# | grep -E '^backend/model_server/|^backend/Dockerfile.model_server'; then
# echo "changed=true" >> $GITHUB_OUTPUT
# fi
check_model_server_changes:
runs-on: ubuntu-latest
outputs:
changed: "true"
steps:
- name: Bypass check and set output
run: echo "changed=true" >> $GITHUB_OUTPUT
build-amd64:
needs: [check_model_server_changes]
if: needs.check_model_server_changes.outputs.changed == 'true'
runs-on:
[runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-amd64"]
steps:
@@ -88,8 +55,6 @@ jobs:
provenance: false
build-arm64:
needs: [check_model_server_changes]
if: needs.check_model_server_changes.outputs.changed == 'true'
runs-on:
[runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-arm64"]
steps:
@@ -129,8 +94,7 @@ jobs:
provenance: false
merge-and-scan:
needs: [build-amd64, build-arm64, check_model_server_changes]
if: needs.check_model_server_changes.outputs.changed == 'true'
needs: [build-amd64, build-arm64]
runs-on: ubuntu-latest
steps:
- name: Login to Docker Hub

View File

@@ -53,90 +53,24 @@ jobs:
exclude: '(?i)^(pylint|aio[-_]*).*'
- name: Print report
if: always()
if: ${{ always() }}
run: echo "${{ steps.license_check_report.outputs.report }}"
- name: Install npm dependencies
working-directory: ./web
run: npm ci
- name: Run Trivy vulnerability scanner in repo mode
uses: aquasecurity/trivy-action@0.28.0
with:
scan-type: fs
scanners: license
format: table
# format: sarif
# output: trivy-results.sarif
severity: HIGH,CRITICAL
# be careful enabling the sarif and upload as it may spam the security tab
# with a huge amount of items. Work out the issues before enabling upload.
# - name: Run Trivy vulnerability scanner in repo mode
# if: always()
# uses: aquasecurity/trivy-action@0.29.0
# - name: Upload Trivy scan results to GitHub Security tab
# uses: github/codeql-action/upload-sarif@v3
# with:
# scan-type: fs
# scan-ref: .
# scanners: license
# format: table
# severity: HIGH,CRITICAL
# # format: sarif
# # output: trivy-results.sarif
#
# # - name: Upload Trivy scan results to GitHub Security tab
# # uses: github/codeql-action/upload-sarif@v3
# # with:
# # sarif_file: trivy-results.sarif
scan-trivy:
# See https://runs-on.com/runners/linux/
runs-on: [runs-on,runner=2cpu-linux-x64,"run-id=${{ github.run_id }}"]
steps:
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_TOKEN }}
# Backend
- name: Pull backend docker image
run: docker pull onyxdotapp/onyx-backend:latest
- name: Run Trivy vulnerability scanner on backend
uses: aquasecurity/trivy-action@0.29.0
env:
TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
with:
image-ref: onyxdotapp/onyx-backend:latest
scanners: license
severity: HIGH,CRITICAL
vuln-type: library
exit-code: 0 # Set to 1 if we want a failed scan to fail the workflow
# Web server
- name: Pull web server docker image
run: docker pull onyxdotapp/onyx-web-server:latest
- name: Run Trivy vulnerability scanner on web server
uses: aquasecurity/trivy-action@0.29.0
env:
TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
with:
image-ref: onyxdotapp/onyx-web-server:latest
scanners: license
severity: HIGH,CRITICAL
vuln-type: library
exit-code: 0
# Model server
- name: Pull model server docker image
run: docker pull onyxdotapp/onyx-model-server:latest
- name: Run Trivy vulnerability scanner
uses: aquasecurity/trivy-action@0.29.0
env:
TRIVY_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-db:2'
TRIVY_JAVA_DB_REPOSITORY: 'public.ecr.aws/aquasecurity/trivy-java-db:1'
with:
image-ref: onyxdotapp/onyx-model-server:latest
scanners: license
severity: HIGH,CRITICAL
vuln-type: library
exit-code: 0
# sarif_file: trivy-results.sarif

View File

@@ -1,6 +1,6 @@
name: Run Playwright Tests
name: Run Chromatic Tests
concurrency:
group: Run-Playwright-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
group: Run-Chromatic-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
cancel-in-progress: true
on: push
@@ -198,47 +198,43 @@ jobs:
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p danswer-stack down -v
# NOTE: Chromatic UI diff testing is currently disabled.
# We are using Playwright for local and CI testing without visual regression checks.
# Chromatic may be reintroduced in the future for UI diff testing if needed.
chromatic-tests:
name: Chromatic Tests
# chromatic-tests:
# name: Chromatic Tests
needs: playwright-tests
runs-on:
[
runs-on,
runner=32cpu-linux-x64,
disk=large,
"run-id=${{ github.run_id }}",
]
steps:
- name: Checkout code
uses: actions/checkout@v4
with:
fetch-depth: 0
# needs: playwright-tests
# runs-on:
# [
# runs-on,
# runner=32cpu-linux-x64,
# disk=large,
# "run-id=${{ github.run_id }}",
# ]
# steps:
# - name: Checkout code
# uses: actions/checkout@v4
# with:
# fetch-depth: 0
- name: Setup node
uses: actions/setup-node@v4
with:
node-version: 22
# - name: Setup node
# uses: actions/setup-node@v4
# with:
# node-version: 22
- name: Install node dependencies
working-directory: ./web
run: npm ci
# - name: Install node dependencies
# working-directory: ./web
# run: npm ci
- name: Download Playwright test results
uses: actions/download-artifact@v4
with:
name: test-results
path: ./web/test-results
# - name: Download Playwright test results
# uses: actions/download-artifact@v4
# with:
# name: test-results
# path: ./web/test-results
# - name: Run Chromatic
# uses: chromaui/action@latest
# with:
# playwright: true
# projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
# workingDir: ./web
# env:
# CHROMATIC_ARCHIVE_LOCATION: ./test-results
- name: Run Chromatic
uses: chromaui/action@latest
with:
playwright: true
projectToken: ${{ secrets.CHROMATIC_PROJECT_TOKEN }}
workingDir: ./web
env:
CHROMATIC_ARCHIVE_LOCATION: ./test-results

View File

@@ -99,7 +99,7 @@ jobs:
DISABLE_TELEMETRY=true \
IMAGE_TAG=test \
DEV_MODE=true \
docker compose -f docker-compose.multitenant-dev.yml -p onyx-stack up -d
docker compose -f docker-compose.multitenant-dev.yml -p danswer-stack up -d
id: start_docker_multi_tenant
# In practice, `cloud` Auth type would require OAUTH credentials to be set.
@@ -108,13 +108,12 @@ jobs:
echo "Waiting for 3 minutes to ensure API server is ready..."
sleep 180
echo "Running integration tests..."
docker run --rm --network onyx-stack_default \
docker run --rm --network danswer-stack_default \
--name test-runner \
-e POSTGRES_HOST=relational_db \
-e POSTGRES_USER=postgres \
-e POSTGRES_PASSWORD=password \
-e POSTGRES_DB=postgres \
-e POSTGRES_USE_NULL_POOL=true \
-e VESPA_HOST=index \
-e REDIS_HOST=cache \
-e API_SERVER_HOST=api_server \
@@ -144,28 +143,24 @@ jobs:
- name: Stop multi-tenant Docker containers
run: |
cd deployment/docker_compose
docker compose -f docker-compose.multitenant-dev.yml -p onyx-stack down -v
docker compose -f docker-compose.multitenant-dev.yml -p danswer-stack down -v
# NOTE: Use pre-ping/null pool to reduce flakiness due to dropped connections
- name: Start Docker containers
run: |
cd deployment/docker_compose
ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
AUTH_TYPE=basic \
POSTGRES_POOL_PRE_PING=true \
POSTGRES_USE_NULL_POOL=true \
REQUIRE_EMAIL_VERIFICATION=false \
DISABLE_TELEMETRY=true \
IMAGE_TAG=test \
INTEGRATION_TESTS_MODE=true \
docker compose -f docker-compose.dev.yml -p onyx-stack up -d
docker compose -f docker-compose.dev.yml -p danswer-stack up -d
id: start_docker
- name: Wait for service to be ready
run: |
echo "Starting wait-for-service script..."
docker logs -f onyx-stack-api_server-1 &
docker logs -f danswer-stack-api_server-1 &
start_time=$(date +%s)
timeout=300 # 5 minutes in seconds
@@ -195,24 +190,15 @@ jobs:
done
echo "Finished waiting for service."
- name: Start Mock Services
run: |
cd backend/tests/integration/mock_services
docker compose -f docker-compose.mock-it-services.yml \
-p mock-it-services-stack up -d
# NOTE: Use pre-ping/null to reduce flakiness due to dropped connections
- name: Run Standard Integration Tests
run: |
echo "Running integration tests..."
docker run --rm --network onyx-stack_default \
docker run --rm --network danswer-stack_default \
--name test-runner \
-e POSTGRES_HOST=relational_db \
-e POSTGRES_USER=postgres \
-e POSTGRES_PASSWORD=password \
-e POSTGRES_DB=postgres \
-e POSTGRES_POOL_PRE_PING=true \
-e POSTGRES_USE_NULL_POOL=true \
-e VESPA_HOST=index \
-e REDIS_HOST=cache \
-e API_SERVER_HOST=api_server \
@@ -222,8 +208,6 @@ jobs:
-e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
-e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
-e TEST_WEB_HOSTNAME=test-runner \
-e MOCK_CONNECTOR_SERVER_HOST=mock_connector_server \
-e MOCK_CONNECTOR_SERVER_PORT=8001 \
onyxdotapp/onyx-integration:test \
/app/tests/integration/tests \
/app/tests/integration/connector_job_tests
@@ -245,13 +229,13 @@ jobs:
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color api_server > $GITHUB_WORKSPACE/api_server.log || true
docker compose -f docker-compose.dev.yml -p danswer-stack logs --no-color api_server > $GITHUB_WORKSPACE/api_server.log || true
- name: Dump all-container logs (optional)
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
docker compose -f docker-compose.dev.yml -p danswer-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
- name: Upload logs
if: always()
@@ -265,4 +249,4 @@ jobs:
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack down -v
docker compose -f docker-compose.dev.yml -p danswer-stack down -v

View File

@@ -1,209 +0,0 @@
name: Run MIT Integration Tests v2
concurrency:
group: Run-MIT-Integration-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
cancel-in-progress: true
on:
merge_group:
pull_request:
branches:
- main
- "release/**"
env:
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}
CONFLUENCE_TEST_SPACE_URL: ${{ secrets.CONFLUENCE_TEST_SPACE_URL }}
CONFLUENCE_USER_NAME: ${{ secrets.CONFLUENCE_USER_NAME }}
CONFLUENCE_ACCESS_TOKEN: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
jobs:
integration-tests-mit:
# See https://runs-on.com/runners/linux/
runs-on: [runs-on, runner=32cpu-linux-x64, "run-id=${{ github.run_id }}"]
steps:
- name: Checkout code
uses: actions/checkout@v4
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_TOKEN }}
# tag every docker image with "test" so that we can spin up the correct set
# of images during testing
# We don't need to build the Web Docker image since it's not yet used
# in the integration tests. We have a separate action to verify that it builds
# successfully.
- name: Pull Web Docker image
run: |
docker pull onyxdotapp/onyx-web-server:latest
docker tag onyxdotapp/onyx-web-server:latest onyxdotapp/onyx-web-server:test
# we use the runs-on cache for docker builds
# in conjunction with runs-on runners, it has better speed and unlimited caching
# https://runs-on.com/caching/s3-cache-for-github-actions/
# https://runs-on.com/caching/docker/
# https://github.com/moby/buildkit#s3-cache-experimental
# images are built and run locally for testing purposes. Not pushed.
- name: Build Backend Docker image
uses: ./.github/actions/custom-build-and-push
with:
context: ./backend
file: ./backend/Dockerfile
platforms: linux/amd64
tags: onyxdotapp/onyx-backend:test
push: false
load: true
cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/backend/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
- name: Build Model Server Docker image
uses: ./.github/actions/custom-build-and-push
with:
context: ./backend
file: ./backend/Dockerfile.model_server
platforms: linux/amd64
tags: onyxdotapp/onyx-model-server:test
push: false
load: true
cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/model-server/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
- name: Build integration test Docker image
uses: ./.github/actions/custom-build-and-push
with:
context: ./backend
file: ./backend/tests/integration/Dockerfile
platforms: linux/amd64
tags: onyxdotapp/onyx-integration:test
push: false
load: true
cache-from: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }}
cache-to: type=s3,prefix=cache/${{ github.repository }}/integration-tests/integration/,region=${{ env.RUNS_ON_AWS_REGION }},bucket=${{ env.RUNS_ON_S3_BUCKET_CACHE }},mode=max
# NOTE: Use pre-ping/null pool to reduce flakiness due to dropped connections
- name: Start Docker containers
run: |
cd deployment/docker_compose
AUTH_TYPE=basic \
POSTGRES_POOL_PRE_PING=true \
POSTGRES_USE_NULL_POOL=true \
REQUIRE_EMAIL_VERIFICATION=false \
DISABLE_TELEMETRY=true \
IMAGE_TAG=test \
INTEGRATION_TESTS_MODE=true \
docker compose -f docker-compose.dev.yml -p onyx-stack up -d
id: start_docker
- name: Wait for service to be ready
run: |
echo "Starting wait-for-service script..."
docker logs -f onyx-stack-api_server-1 &
start_time=$(date +%s)
timeout=300 # 5 minutes in seconds
while true; do
current_time=$(date +%s)
elapsed_time=$((current_time - start_time))
if [ $elapsed_time -ge $timeout ]; then
echo "Timeout reached. Service did not become ready in 5 minutes."
exit 1
fi
# Use curl with error handling to ignore specific exit code 56
response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/health || echo "curl_error")
if [ "$response" = "200" ]; then
echo "Service is ready!"
break
elif [ "$response" = "curl_error" ]; then
echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
else
echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
fi
sleep 5
done
echo "Finished waiting for service."
- name: Start Mock Services
run: |
cd backend/tests/integration/mock_services
docker compose -f docker-compose.mock-it-services.yml \
-p mock-it-services-stack up -d
# NOTE: Use pre-ping/null to reduce flakiness due to dropped connections
- name: Run Standard Integration Tests
run: |
echo "Running integration tests..."
docker run --rm --network onyx-stack_default \
--name test-runner \
-e POSTGRES_HOST=relational_db \
-e POSTGRES_USER=postgres \
-e POSTGRES_PASSWORD=password \
-e POSTGRES_DB=postgres \
-e POSTGRES_POOL_PRE_PING=true \
-e POSTGRES_USE_NULL_POOL=true \
-e VESPA_HOST=index \
-e REDIS_HOST=cache \
-e API_SERVER_HOST=api_server \
-e OPENAI_API_KEY=${OPENAI_API_KEY} \
-e SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN} \
-e CONFLUENCE_TEST_SPACE_URL=${CONFLUENCE_TEST_SPACE_URL} \
-e CONFLUENCE_USER_NAME=${CONFLUENCE_USER_NAME} \
-e CONFLUENCE_ACCESS_TOKEN=${CONFLUENCE_ACCESS_TOKEN} \
-e TEST_WEB_HOSTNAME=test-runner \
-e MOCK_CONNECTOR_SERVER_HOST=mock_connector_server \
-e MOCK_CONNECTOR_SERVER_PORT=8001 \
onyxdotapp/onyx-integration:test \
/app/tests/integration/tests \
/app/tests/integration/connector_job_tests
continue-on-error: true
id: run_tests
- name: Check test results
run: |
if [ ${{ steps.run_tests.outcome }} == 'failure' ]; then
echo "Integration tests failed. Exiting with error."
exit 1
else
echo "All integration tests passed successfully."
fi
# ------------------------------------------------------------
# Always gather logs BEFORE "down":
- name: Dump API server logs
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color api_server > $GITHUB_WORKSPACE/api_server.log || true
- name: Dump all-container logs (optional)
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
- name: Upload logs
if: always()
uses: actions/upload-artifact@v4
with:
name: docker-all-logs
path: ${{ github.workspace }}/docker-compose.log
# ------------------------------------------------------------
- name: Stop Docker containers
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.dev.yml -p onyx-stack down -v

View File

@@ -44,7 +44,7 @@ jobs:
- name: Check import order with reorder-python-imports
run: |
cd backend
find ./onyx -name "*.py" | xargs reorder-python-imports --py311-plus
find ./danswer -name "*.py" | xargs reorder-python-imports --py311-plus
- name: Check code formatting with Black
run: |

View File

@@ -1,7 +1,6 @@
name: Connector Tests
on:
merge_group:
pull_request:
branches: [main]
schedule:
@@ -9,10 +8,6 @@ on:
- cron: "0 16 * * *"
env:
# AWS
AWS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS: ${{ secrets.AWS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS }}
AWS_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS: ${{ secrets.AWS_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS }}
# Confluence
CONFLUENCE_TEST_SPACE_URL: ${{ secrets.CONFLUENCE_TEST_SPACE_URL }}
CONFLUENCE_TEST_SPACE: ${{ secrets.CONFLUENCE_TEST_SPACE }}
@@ -23,10 +18,6 @@ env:
# Jira
JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
GONG_ACCESS_KEY: ${{ secrets.GONG_ACCESS_KEY }}
GONG_ACCESS_KEY_SECRET: ${{ secrets.GONG_ACCESS_KEY_SECRET }}
# Google
GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR }}
GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1 }}
@@ -53,21 +44,11 @@ env:
SHAREPOINT_CLIENT_SECRET: ${{ secrets.SHAREPOINT_CLIENT_SECRET }}
SHAREPOINT_CLIENT_DIRECTORY_ID: ${{ secrets.SHAREPOINT_CLIENT_DIRECTORY_ID }}
SHAREPOINT_SITE: ${{ secrets.SHAREPOINT_SITE }}
# Github
ACCESS_TOKEN_GITHUB: ${{ secrets.ACCESS_TOKEN_GITHUB }}
# Gitbook
GITBOOK_SPACE_ID: ${{ secrets.GITBOOK_SPACE_ID }}
GITBOOK_API_KEY: ${{ secrets.GITBOOK_API_KEY }}
# Notion
NOTION_INTEGRATION_TOKEN: ${{ secrets.NOTION_INTEGRATION_TOKEN }}
# Highspot
HIGHSPOT_KEY: ${{ secrets.HIGHSPOT_KEY }}
HIGHSPOT_SECRET: ${{ secrets.HIGHSPOT_SECRET }}
jobs:
connectors-check:
# See https://runs-on.com/runners/linux/
runs-on: [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}"]
runs-on: [runs-on,runner=8cpu-linux-x64,"run-id=${{ github.run_id }}"]
env:
PYTHONPATH: ./backend
@@ -90,8 +71,6 @@ jobs:
python -m pip install --upgrade pip
pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
playwright install chromium
playwright install-deps chromium
- name: Run Tests
shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"

View File

@@ -1,29 +1,18 @@
name: Model Server Tests
name: Connector Tests
on:
schedule:
# This cron expression runs the job daily at 16:00 UTC (9am PT)
- cron: "0 16 * * *"
workflow_dispatch:
inputs:
branch:
description: 'Branch to run the workflow on'
required: false
default: 'main'
env:
# Bedrock
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
AWS_REGION_NAME: ${{ secrets.AWS_REGION_NAME }}
# API keys for testing
COHERE_API_KEY: ${{ secrets.COHERE_API_KEY }}
LITELLM_API_KEY: ${{ secrets.LITELLM_API_KEY }}
LITELLM_API_URL: ${{ secrets.LITELLM_API_URL }}
# OpenAI
OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
AZURE_API_KEY: ${{ secrets.AZURE_API_KEY }}
AZURE_API_URL: ${{ secrets.AZURE_API_URL }}
jobs:
model-check:
@@ -37,23 +26,6 @@ jobs:
- name: Checkout code
uses: actions/checkout@v4
- name: Login to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_TOKEN }}
# tag every docker image with "test" so that we can spin up the correct set
# of images during testing
# We don't need to build the Web Docker image since it's not yet used
# in the integration tests. We have a separate action to verify that it builds
# successfully.
- name: Pull Model Server Docker image
run: |
docker pull onyxdotapp/onyx-model-server:latest
docker tag onyxdotapp/onyx-model-server:latest onyxdotapp/onyx-model-server:test
- name: Set up Python
uses: actions/setup-python@v5
with:
@@ -69,49 +41,6 @@ jobs:
pip install --retries 5 --timeout 30 -r backend/requirements/default.txt
pip install --retries 5 --timeout 30 -r backend/requirements/dev.txt
- name: Start Docker containers
run: |
cd deployment/docker_compose
ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=true \
AUTH_TYPE=basic \
REQUIRE_EMAIL_VERIFICATION=false \
DISABLE_TELEMETRY=true \
IMAGE_TAG=test \
docker compose -f docker-compose.model-server-test.yml -p onyx-stack up -d indexing_model_server
id: start_docker
- name: Wait for service to be ready
run: |
echo "Starting wait-for-service script..."
start_time=$(date +%s)
timeout=300 # 5 minutes in seconds
while true; do
current_time=$(date +%s)
elapsed_time=$((current_time - start_time))
if [ $elapsed_time -ge $timeout ]; then
echo "Timeout reached. Service did not become ready in 5 minutes."
exit 1
fi
# Use curl with error handling to ignore specific exit code 56
response=$(curl -s -o /dev/null -w "%{http_code}" http://localhost:9000/api/health || echo "curl_error")
if [ "$response" = "200" ]; then
echo "Service is ready!"
break
elif [ "$response" = "curl_error" ]; then
echo "Curl encountered an error, possibly exit code 56. Continuing to retry..."
else
echo "Service not ready yet (HTTP status $response). Retrying in 5 seconds..."
fi
sleep 5
done
echo "Finished waiting for service."
- name: Run Tests
shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
run: |
@@ -127,23 +56,3 @@ jobs:
-H 'Content-type: application/json' \
--data '{"text":"Scheduled Model Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
$SLACK_WEBHOOK
- name: Dump all-container logs (optional)
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.model-server-test.yml -p onyx-stack logs --no-color > $GITHUB_WORKSPACE/docker-compose.log || true
- name: Upload logs
if: always()
uses: actions/upload-artifact@v4
with:
name: docker-all-logs
path: ${{ github.workspace }}/docker-compose.log
- name: Stop Docker containers
if: always()
run: |
cd deployment/docker_compose
docker compose -f docker-compose.model-server-test.yml -p onyx-stack down -v

23
.gitignore vendored
View File

@@ -1,25 +1,12 @@
# editors
.vscode
.zed
# macos
.env
.DS_store
# python
.venv
.mypy_cache
.idea
# testing
/deployment/data/nginx/app.conf
.vscode/
*.sw?
/backend/tests/regression/answer_quality/search_test_config.yaml
/web/test-results/
backend/onyx/agent_search/main/test_data.json
backend/tests/regression/answer_quality/test_data.json
# secret files
.env
jira_test_env
# others
/deployment/data/nginx/app.conf
*.sw?
/backend/tests/regression/answer_quality/search_test_config.yaml

View File

@@ -1,13 +1,12 @@
repos:
- repo: https://github.com/psf/black
rev: 25.1.0
rev: 23.3.0
hooks:
- id: black
language_version: python3.11
# this is a fork which keeps compatibility with black
- repo: https://github.com/wimglenn/reorder-python-imports-black
rev: v3.14.0
- repo: https://github.com/asottile/reorder_python_imports
rev: v3.9.0
hooks:
- id: reorder-python-imports
args: ['--py311-plus', '--application-directories=backend/']
@@ -19,14 +18,14 @@ repos:
# These settings will remove unused imports with side effects
# Note: The repo currently does not and should not have imports with side effects
- repo: https://github.com/PyCQA/autoflake
rev: v2.3.1
rev: v2.2.0
hooks:
- id: autoflake
args: [ '--remove-all-unused-imports', '--remove-unused-variables', '--in-place' , '--recursive']
- repo: https://github.com/astral-sh/ruff-pre-commit
# Ruff version.
rev: v0.11.4
rev: v0.0.286
hooks:
- id: ruff
- repo: https://github.com/pre-commit/mirrors-prettier

View File

@@ -6,419 +6,396 @@
// For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
"version": "0.2.0",
"compounds": [
{
// Dummy entry used to label the group
"name": "--- Compound ---",
"configurations": ["--- Individual ---"],
"presentation": {
"group": "1"
}
},
{
"name": "Run All Onyx Services",
"configurations": [
"Web Server",
"Model Server",
"API Server",
"Slack Bot",
"Celery primary",
"Celery light",
"Celery heavy",
"Celery indexing",
"Celery user files indexing",
"Celery beat",
"Celery monitoring"
],
"presentation": {
"group": "1"
}
},
{
"name": "Web / Model / API",
"configurations": ["Web Server", "Model Server", "API Server"],
"presentation": {
"group": "1"
}
},
{
"name": "Celery (all)",
"configurations": [
"Celery primary",
"Celery light",
"Celery heavy",
"Celery indexing",
"Celery user files indexing",
"Celery beat",
"Celery monitoring"
],
"presentation": {
"group": "1"
}
}
{
// Dummy entry used to label the group
"name": "--- Compound ---",
"configurations": [
"--- Individual ---"
],
"presentation": {
"group": "1",
}
},
{
"name": "Run All Onyx Services",
"configurations": [
"Web Server",
"Model Server",
"API Server",
"Slack Bot",
"Celery primary",
"Celery light",
"Celery heavy",
"Celery indexing",
"Celery beat",
"Celery monitoring",
],
"presentation": {
"group": "1",
}
},
{
"name": "Web / Model / API",
"configurations": [
"Web Server",
"Model Server",
"API Server",
],
"presentation": {
"group": "1",
}
},
{
"name": "Celery (all)",
"configurations": [
"Celery primary",
"Celery light",
"Celery heavy",
"Celery indexing",
"Celery beat",
"Celery monitoring",
],
"presentation": {
"group": "1",
}
}
],
"configurations": [
{
// Dummy entry used to label the group
"name": "--- Individual ---",
"type": "node",
"request": "launch",
"presentation": {
"group": "2",
"order": 0
}
},
{
"name": "Web Server",
"type": "node",
"request": "launch",
"cwd": "${workspaceRoot}/web",
"runtimeExecutable": "npm",
"envFile": "${workspaceFolder}/.vscode/.env",
"runtimeArgs": ["run", "dev"],
"presentation": {
"group": "2"
{
// Dummy entry used to label the group
"name": "--- Individual ---",
"type": "node",
"request": "launch",
"presentation": {
"group": "2",
"order": 0
}
},
{
"name": "Web Server",
"type": "node",
"request": "launch",
"cwd": "${workspaceRoot}/web",
"runtimeExecutable": "npm",
"envFile": "${workspaceFolder}/.vscode/.env",
"runtimeArgs": [
"run", "dev"
],
"presentation": {
"group": "2",
},
"console": "integratedTerminal",
"consoleTitle": "Web Server Console"
},
"console": "integratedTerminal",
"consoleTitle": "Web Server Console"
},
{
"name": "Model Server",
"consoleName": "Model Server",
"type": "debugpy",
"request": "launch",
"module": "uvicorn",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1"
{
"name": "Model Server",
"consoleName": "Model Server",
"type": "debugpy",
"request": "launch",
"module": "uvicorn",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1"
},
"args": [
"model_server.main:app",
"--reload",
"--port",
"9000"
],
"presentation": {
"group": "2",
},
"consoleTitle": "Model Server Console"
},
"args": ["model_server.main:app", "--reload", "--port", "9000"],
"presentation": {
"group": "2"
{
"name": "API Server",
"consoleName": "API Server",
"type": "debugpy",
"request": "launch",
"module": "uvicorn",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_DANSWER_MODEL_INTERACTIONS": "True",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1"
},
"args": [
"onyx.main:app",
"--reload",
"--port",
"8080"
],
"presentation": {
"group": "2",
},
"consoleTitle": "API Server Console"
},
"consoleTitle": "Model Server Console"
},
{
"name": "API Server",
"consoleName": "API Server",
"type": "debugpy",
"request": "launch",
"module": "uvicorn",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_DANSWER_MODEL_INTERACTIONS": "True",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1"
// For the listener to access the Slack API,
// DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
{
"name": "Slack Bot",
"consoleName": "Slack Bot",
"type": "debugpy",
"request": "launch",
"program": "onyx/onyxbot/slack/listener.py",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"presentation": {
"group": "2",
},
"consoleTitle": "Slack Bot Console"
},
"args": ["onyx.main:app", "--reload", "--port", "8080"],
"presentation": {
"group": "2"
{
"name": "Celery primary",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.primary",
"worker",
"--pool=threads",
"--concurrency=4",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=primary@%n",
"-Q",
"celery",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery primary Console"
},
"consoleTitle": "API Server Console"
},
// For the listener to access the Slack API,
// DANSWER_BOT_SLACK_APP_TOKEN & DANSWER_BOT_SLACK_BOT_TOKEN need to be set in .env file located in the root of the project
{
"name": "Slack Bot",
"consoleName": "Slack Bot",
"type": "debugpy",
"request": "launch",
"program": "onyx/onyxbot/slack/listener.py",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
{
"name": "Celery light",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.light",
"worker",
"--pool=threads",
"--concurrency=64",
"--prefetch-multiplier=8",
"--loglevel=INFO",
"--hostname=light@%n",
"-Q",
"vespa_metadata_sync,connector_deletion,doc_permissions_upsert",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery light Console"
},
"presentation": {
"group": "2"
{
"name": "Celery heavy",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.heavy",
"worker",
"--pool=threads",
"--concurrency=4",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=heavy@%n",
"-Q",
"connector_pruning,connector_doc_permissions_sync,connector_external_group_sync",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery heavy Console"
},
"consoleTitle": "Slack Bot Console"
},
{
"name": "Celery primary",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
{
"name": "Celery indexing",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"ENABLE_MULTIPASS_INDEXING": "false",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.indexing",
"worker",
"--pool=threads",
"--concurrency=1",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=indexing@%n",
"-Q",
"connector_indexing",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery indexing Console"
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.primary",
"worker",
"--pool=threads",
"--concurrency=4",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=primary@%n",
"-Q",
"celery"
],
"presentation": {
"group": "2"
{
"name": "Celery monitoring",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {},
"args": [
"-A",
"onyx.background.celery.versioned_apps.monitoring",
"worker",
"--pool=solo",
"--concurrency=1",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=monitoring@%n",
"-Q",
"monitoring",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery monitoring Console"
},
"consoleTitle": "Celery primary Console"
},
{
"name": "Celery light",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
{
"name": "Celery beat",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.beat",
"beat",
"--loglevel=INFO",
],
"presentation": {
"group": "2",
},
"consoleTitle": "Celery beat Console"
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.light",
"worker",
"--pool=threads",
"--concurrency=64",
"--prefetch-multiplier=8",
"--loglevel=INFO",
"--hostname=light@%n",
"-Q",
"vespa_metadata_sync,connector_deletion,doc_permissions_upsert"
],
"presentation": {
"group": "2"
{
"name": "Pytest",
"consoleName": "Pytest",
"type": "debugpy",
"request": "launch",
"module": "pytest",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-v"
// Specify a sepcific module/test to run or provide nothing to run all tests
//"tests/unit/onyx/llm/answering/test_prune_and_merge.py"
],
"presentation": {
"group": "2",
},
"consoleTitle": "Pytest Console"
},
"consoleTitle": "Celery light Console"
},
{
"name": "Celery heavy",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "INFO",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
{
// Dummy entry used to label the group
"name": "--- Tasks ---",
"type": "node",
"request": "launch",
"presentation": {
"group": "3",
"order": 0
}
},
{
"name": "Clear and Restart External Volumes and Containers",
"type": "node",
"request": "launch",
"runtimeExecutable": "bash",
"runtimeArgs": ["${workspaceFolder}/backend/scripts/restart_containers.sh"],
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"stopOnEntry": true,
"presentation": {
"group": "3",
},
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.heavy",
"worker",
"--pool=threads",
"--concurrency=4",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=heavy@%n",
"-Q",
"connector_pruning,connector_doc_permissions_sync,connector_external_group_sync"
],
"presentation": {
"group": "2"
{
// Celery jobs launched through a single background script (legacy)
// Recommend using the "Celery (all)" compound launch instead.
"name": "Background Jobs",
"consoleName": "Background Jobs",
"type": "debugpy",
"request": "launch",
"program": "scripts/dev_run_background_jobs.py",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_DANSWER_MODEL_INTERACTIONS": "True",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
},
"consoleTitle": "Celery heavy Console"
},
{
"name": "Celery indexing",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"ENABLE_MULTIPASS_INDEXING": "false",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
{
"name": "Install Python Requirements",
"type": "node",
"request": "launch",
"runtimeExecutable": "bash",
"runtimeArgs": [
"-c",
"pip install -r backend/requirements/default.txt && pip install -r backend/requirements/dev.txt && pip install -r backend/requirements/ee.txt && pip install -r backend/requirements/model_server.txt"
],
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"presentation": {
"group": "3"
}
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.indexing",
"worker",
"--pool=threads",
"--concurrency=1",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=indexing@%n",
"-Q",
"connector_indexing"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Celery indexing Console"
},
{
"name": "Celery monitoring",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {},
"args": [
"-A",
"onyx.background.celery.versioned_apps.monitoring",
"worker",
"--pool=solo",
"--concurrency=1",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=monitoring@%n",
"-Q",
"monitoring"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Celery monitoring Console"
},
{
"name": "Celery beat",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.beat",
"beat",
"--loglevel=INFO"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Celery beat Console"
},
{
"name": "Celery user files indexing",
"type": "debugpy",
"request": "launch",
"module": "celery",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-A",
"onyx.background.celery.versioned_apps.indexing",
"worker",
"--pool=threads",
"--concurrency=1",
"--prefetch-multiplier=1",
"--loglevel=INFO",
"--hostname=user_files_indexing@%n",
"-Q",
"user_files_indexing"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Celery user files indexing Console"
},
{
"name": "Pytest",
"consoleName": "Pytest",
"type": "debugpy",
"request": "launch",
"module": "pytest",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
},
"args": [
"-v"
// Specify a sepcific module/test to run or provide nothing to run all tests
//"tests/unit/onyx/llm/answering/test_prune_and_merge.py"
],
"presentation": {
"group": "2"
},
"consoleTitle": "Pytest Console"
},
{
// Dummy entry used to label the group
"name": "--- Tasks ---",
"type": "node",
"request": "launch",
"presentation": {
"group": "3",
"order": 0
}
},
{
"name": "Clear and Restart External Volumes and Containers",
"type": "node",
"request": "launch",
"runtimeExecutable": "bash",
"runtimeArgs": [
"${workspaceFolder}/backend/scripts/restart_containers.sh"
],
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"stopOnEntry": true,
"presentation": {
"group": "3"
}
},
{
// Celery jobs launched through a single background script (legacy)
// Recommend using the "Celery (all)" compound launch instead.
"name": "Background Jobs",
"consoleName": "Background Jobs",
"type": "debugpy",
"request": "launch",
"program": "scripts/dev_run_background_jobs.py",
"cwd": "${workspaceFolder}/backend",
"envFile": "${workspaceFolder}/.vscode/.env",
"env": {
"LOG_DANSWER_MODEL_INTERACTIONS": "True",
"LOG_LEVEL": "DEBUG",
"PYTHONUNBUFFERED": "1",
"PYTHONPATH": "."
}
},
{
"name": "Install Python Requirements",
"type": "node",
"request": "launch",
"runtimeExecutable": "bash",
"runtimeArgs": [
"-c",
"pip install -r backend/requirements/default.txt && pip install -r backend/requirements/dev.txt && pip install -r backend/requirements/ee.txt && pip install -r backend/requirements/model_server.txt"
],
"cwd": "${workspaceFolder}",
"console": "integratedTerminal",
"presentation": {
"group": "3"
}
},
{
"name": "Debug React Web App in Chrome",
"type": "chrome",
"request": "launch",
"url": "http://localhost:3000",
"webRoot": "${workspaceFolder}/web"
}
]
}
}

123
README.md
View File

@@ -24,94 +24,113 @@
</a>
</p>
<strong>[Onyx](https://www.onyx.app/)</strong> (formerly Danswer) is the AI platform connected to your company's docs, apps, and people.
Onyx provides a feature rich Chat interface and plugs into any LLM of your choice.
Keep knowledge and access controls sync-ed across over 40 connectors like Google Drive, Slack, Confluence, Salesforce, etc.
Create custom AI agents with unique prompts, knowledge, and actions that the agents can take.
Onyx can be deployed securely anywhere and for any scale - on a laptop, on-premise, or to cloud.
<strong>[Onyx](https://www.onyx.app/)</strong> (formerly Danswer) is the AI Assistant connected to your company's docs, apps, and people.
Onyx provides a Chat interface and plugs into any LLM of your choice. Onyx can be deployed anywhere and for any
scale - on a laptop, on-premise, or to cloud. Since you own the deployment, your user data and chats are fully in your
own control. Onyx is dual Licensed with most of it under MIT license and designed to be modular and easily extensible. The system also comes fully ready
for production usage with user authentication, role management (admin/basic users), chat persistence, and a UI for
configuring AI Assistants.
Onyx also serves as a Enterprise Search across all common workplace tools such as Slack, Google Drive, Confluence, etc.
By combining LLMs and team specific knowledge, Onyx becomes a subject matter expert for the team. Imagine ChatGPT if
it had access to your team's unique knowledge! It enables questions such as "A customer wants feature X, is this already
supported?" or "Where's the pull request for feature Y?"
<h3>Feature Highlights</h3>
<h3>Usage</h3>
**Deep research over your team's knowledge:**
Onyx Web App:
https://private-user-images.githubusercontent.com/32520769/414509312-48392e83-95d0-4fb5-8650-a396e05e0a32.mp4?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.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.a9D8A0sgKE9AoaoE-mfFbJ6_OKYeqaf7TZ4Han2JfW8
https://github.com/onyx-dot-app/onyx/assets/32520769/563be14c-9304-47b5-bf0a-9049c2b6f410
Or, plug Onyx into your existing Slack workflows (more integrations to come 😁):
**Use Onyx as a secure AI Chat with any LLM:**
![Onyx Chat Silent Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxChatSilentDemo.gif)
**Easily set up connectors to your apps:**
![Onyx Connector Silent Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxConnectorSilentDemo.gif)
**Access Onyx where your team already works:**
![Onyx Bot Demo](https://github.com/onyx-dot-app/onyx/releases/download/v0.21.1/OnyxBot.png)
https://github.com/onyx-dot-app/onyx/assets/25087905/3e19739b-d178-4371-9a38-011430bdec1b
For more details on the Admin UI to manage connectors and users, check out our
<strong><a href="https://www.youtube.com/watch?v=geNzY1nbCnU">Full Video Demo</a></strong>!
## Deployment
**To try it out for free and get started in seconds, check out [Onyx Cloud](https://cloud.onyx.app/signup)**.
Onyx can also be run locally (even on a laptop) or deployed on a virtual machine with a single
Onyx can easily be run locally (even on a laptop) or deployed on a virtual machine with a single
`docker compose` command. Checkout our [docs](https://docs.onyx.app/quickstart) to learn more.
We also have built-in support for high-availability/scalable deployment on Kubernetes.
References [here](https://github.com/onyx-dot-app/onyx/tree/main/deployment).
We also have built-in support for deployment on Kubernetes. Files for that can be found [here](https://github.com/onyx-dot-app/onyx/tree/main/deployment/kubernetes).
## 💃 Main Features
## 🔍 Other Notable Benefits of Onyx
- Custom deep learning models for indexing and inference time, only through Onyx + learning from user feedback.
- Flexible security features like SSO (OIDC/SAML/OAuth2), RBAC, encryption of credentials, etc.
- Knowledge curation features like document-sets, query history, usage analytics, etc.
- Scalable deployment options tested up to many tens of thousands users and hundreds of millions of documents.
- Chat UI with the ability to select documents to chat with.
- Create custom AI Assistants with different prompts and backing knowledge sets.
- Connect Onyx with LLM of your choice (self-host for a fully airgapped solution).
- Document Search + AI Answers for natural language queries.
- Connectors to all common workplace tools like Google Drive, Confluence, Slack, etc.
- Slack integration to get answers and search results directly in Slack.
## 🚧 Roadmap
- New methods in information retrieval (StructRAG, LightGraphRAG, etc.)
- Personalized Search
- Organizational understanding and ability to locate and suggest experts from your team.
- Code Search
- SQL and Structured Query Language
- Chat/Prompt sharing with specific teammates and user groups.
- Multimodal model support, chat with images, video etc.
- Choosing between LLMs and parameters during chat session.
- Tool calling and agent configurations options.
- Organizational understanding and ability to locate and suggest experts from your team.
## Other Notable Benefits of Onyx
- User Authentication with document level access management.
- Best in class Hybrid Search across all sources (BM-25 + prefix aware embedding models).
- Admin Dashboard to configure connectors, document-sets, access, etc.
- Custom deep learning models + learn from user feedback.
- Easy deployment and ability to host Onyx anywhere of your choosing.
## 🔌 Connectors
Keep knowledge and access up to sync across 40+ connectors:
Efficiently pulls the latest changes from:
- Slack
- GitHub
- Google Drive
- Confluence
- Slack
- Gmail
- Salesforce
- Microsoft Sharepoint
- Github
- Jira
- Zendesk
- Gmail
- Notion
- Gong
- Microsoft Teams
- Dropbox
- Slab
- Linear
- Productboard
- Guru
- Bookstack
- Document360
- Sharepoint
- Hubspot
- Local Files
- Websites
- And more ...
See the full list [here](https://docs.onyx.app/connectors).
## 📚 Editions
## 📚 Licensing
There are two editions of Onyx:
- Onyx Community Edition (CE) is available freely under the MIT Expat license. Simply follow the Deployment guide above.
- Onyx Enterprise Edition (EE) includes extra features that are primarily useful for larger organizations.
For feature details, check out [our website](https://www.onyx.app/pricing).
- Onyx Community Edition (CE) is available freely under the MIT Expat license. This version has ALL the core features discussed above. This is the version of Onyx you will get if you follow the Deployment guide above.
- Onyx Enterprise Edition (EE) includes extra features that are primarily useful for larger organizations. Specifically, this includes:
- Single Sign-On (SSO), with support for both SAML and OIDC
- Role-based access control
- Document permission inheritance from connected sources
- Usage analytics and query history accessible to admins
- Whitelabeling
- API key authentication
- Encryption of secrets
- And many more! Checkout [our website](https://www.onyx.app/) for the latest.
To try the Onyx Enterprise Edition:
1. Checkout [Onyx Cloud](https://cloud.onyx.app/signup).
2. For self-hosting the Enterprise Edition, contact us at [founders@onyx.app](mailto:founders@onyx.app) or book a call with us on our [Cal](https://cal.com/team/onyx/founders).
1. Checkout our [Cloud product](https://cloud.onyx.app/signup).
2. For self-hosting, contact us at [founders@onyx.app](mailto:founders@onyx.app) or book a call with us on our [Cal](https://cal.com/team/onyx/founders).
## 💡 Contributing
Looking to contribute? Please check out the [Contribution Guide](CONTRIBUTING.md) for more details.
## ⭐Star History
[![Star History Chart](https://api.star-history.com/svg?repos=onyx-dot-app/onyx&type=Date)](https://star-history.com/#onyx-dot-app/onyx&Date)

View File

@@ -8,7 +8,7 @@ Edition features outside of personal development or testing purposes. Please rea
founders@onyx.app for more information. Please visit https://github.com/onyx-dot-app/onyx"
# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
ARG ONYX_VERSION=0.0.0-dev
ARG ONYX_VERSION=0.8-dev
# DO_NOT_TRACK is used to disable telemetry for Unstructured
ENV ONYX_VERSION=${ONYX_VERSION} \
DANSWER_RUNNING_IN_DOCKER="true" \
@@ -28,16 +28,14 @@ RUN apt-get update && \
curl \
zip \
ca-certificates \
libgnutls30 \
libblkid1 \
libmount1 \
libsmartcols1 \
libuuid1 \
libgnutls30=3.7.9-2+deb12u3 \
libblkid1=2.38.1-5+deb12u1 \
libmount1=2.38.1-5+deb12u1 \
libsmartcols1=2.38.1-5+deb12u1 \
libuuid1=2.38.1-5+deb12u1 \
libxmlsec1-dev \
pkg-config \
gcc \
nano \
vim && \
gcc && \
rm -rf /var/lib/apt/lists/* && \
apt-get clean
@@ -102,7 +100,6 @@ COPY ./alembic /app/alembic
COPY ./alembic_tenants /app/alembic_tenants
COPY ./alembic.ini /app/alembic.ini
COPY supervisord.conf /usr/etc/supervisord.conf
COPY ./static /app/static
# Escape hatch scripts
COPY ./scripts/debugging /app/scripts/debugging

View File

@@ -7,7 +7,7 @@ You can find it at https://hub.docker.com/r/onyx/onyx-model-server. For more det
visit https://github.com/onyx-dot-app/onyx."
# Default ONYX_VERSION, typically overriden during builds by GitHub Actions.
ARG ONYX_VERSION=0.0.0-dev
ARG ONYX_VERSION=0.8-dev
ENV ONYX_VERSION=${ONYX_VERSION} \
DANSWER_RUNNING_IN_DOCKER="true"
@@ -31,8 +31,7 @@ RUN python -c "from transformers import AutoTokenizer; \
AutoTokenizer.from_pretrained('distilbert-base-uncased'); \
AutoTokenizer.from_pretrained('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
from huggingface_hub import snapshot_download; \
snapshot_download(repo_id='onyx-dot-app/hybrid-intent-token-classifier'); \
snapshot_download(repo_id='onyx-dot-app/information-content-model'); \
snapshot_download(repo_id='danswer/hybrid-intent-token-classifier', revision='v1.0.3'); \
snapshot_download('nomic-ai/nomic-embed-text-v1'); \
snapshot_download('mixedbread-ai/mxbai-rerank-xsmall-v1'); \
from sentence_transformers import SentenceTransformer; \
@@ -46,7 +45,6 @@ WORKDIR /app
# Utils used by model server
COPY ./onyx/utils/logger.py /app/onyx/utils/logger.py
COPY ./onyx/utils/middleware.py /app/onyx/utils/middleware.py
# Place to fetch version information
COPY ./onyx/__init__.py /app/onyx/__init__.py

View File

@@ -84,7 +84,7 @@ keys = console
keys = generic
[logger_root]
level = INFO
level = WARN
handlers = console
qualname =

View File

@@ -25,9 +25,6 @@ from shared_configs.configs import MULTI_TENANT, POSTGRES_DEFAULT_SCHEMA
from onyx.db.models import Base
from celery.backends.database.session import ResultModelBase # type: ignore
# Make sure in alembic.ini [logger_root] level=INFO is set or most logging will be
# hidden! (defaults to level=WARN)
# Alembic Config object
config = context.config
@@ -39,7 +36,6 @@ if config.config_file_name is not None and config.attributes.get(
target_metadata = [Base.metadata, ResultModelBase.metadata]
EXCLUDE_TABLES = {"kombu_queue", "kombu_message"}
logger = logging.getLogger(__name__)
ssl_context: ssl.SSLContext | None = None
@@ -68,7 +64,7 @@ def include_object(
return True
def get_schema_options() -> tuple[str, bool, bool, bool]:
def get_schema_options() -> tuple[str, bool, bool]:
x_args_raw = context.get_x_argument()
x_args = {}
for arg in x_args_raw:
@@ -80,10 +76,6 @@ def get_schema_options() -> tuple[str, bool, bool, bool]:
create_schema = x_args.get("create_schema", "true").lower() == "true"
upgrade_all_tenants = x_args.get("upgrade_all_tenants", "false").lower() == "true"
# continue on error with individual tenant
# only applies to online migrations
continue_on_error = x_args.get("continue", "false").lower() == "true"
if (
MULTI_TENANT
and schema_name == POSTGRES_DEFAULT_SCHEMA
@@ -94,12 +86,14 @@ def get_schema_options() -> tuple[str, bool, bool, bool]:
"Please specify a tenant-specific schema."
)
return schema_name, create_schema, upgrade_all_tenants, continue_on_error
return schema_name, create_schema, upgrade_all_tenants
def do_run_migrations(
connection: Connection, schema_name: str, create_schema: bool
) -> None:
logger.info(f"About to migrate schema: {schema_name}")
if create_schema:
connection.execute(text(f'CREATE SCHEMA IF NOT EXISTS "{schema_name}"'))
connection.execute(text("COMMIT"))
@@ -140,12 +134,7 @@ def provide_iam_token_for_alembic(
async def run_async_migrations() -> None:
(
schema_name,
create_schema,
upgrade_all_tenants,
continue_on_error,
) = get_schema_options()
schema_name, create_schema, upgrade_all_tenants = get_schema_options()
engine = create_async_engine(
build_connection_string(),
@@ -162,15 +151,9 @@ async def run_async_migrations() -> None:
if upgrade_all_tenants:
tenant_schemas = get_all_tenant_ids()
i_tenant = 0
num_tenants = len(tenant_schemas)
for schema in tenant_schemas:
i_tenant += 1
logger.info(
f"Migrating schema: index={i_tenant} num_tenants={num_tenants} schema={schema}"
)
try:
logger.info(f"Migrating schema: {schema}")
async with engine.connect() as connection:
await connection.run_sync(
do_run_migrations,
@@ -179,12 +162,7 @@ async def run_async_migrations() -> None:
)
except Exception as e:
logger.error(f"Error migrating schema {schema}: {e}")
if not continue_on_error:
logger.error("--continue is not set, raising exception!")
raise
logger.warning("--continue is set, continuing to next schema.")
raise
else:
try:
logger.info(f"Migrating schema: {schema_name}")
@@ -202,11 +180,7 @@ async def run_async_migrations() -> None:
def run_migrations_offline() -> None:
"""This doesn't really get used when we migrate in the cloud."""
logger.info("run_migrations_offline starting.")
schema_name, _, upgrade_all_tenants, continue_on_error = get_schema_options()
schema_name, _, upgrade_all_tenants = get_schema_options()
url = build_connection_string()
if upgrade_all_tenants:
@@ -256,7 +230,6 @@ def run_migrations_offline() -> None:
def run_migrations_online() -> None:
logger.info("run_migrations_online starting.")
asyncio.run(run_async_migrations())

View File

@@ -5,7 +5,6 @@ Revises: 6fc7886d665d
Create Date: 2025-01-14 12:14:00.814390
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 8a87bd6ec550
Create Date: 2024-07-23 11:12:39.462397
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 5f4b8568a221
Create Date: 2024-03-02 23:23:49.960309
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 570282d33c49
Create Date: 2024-05-05 19:30:34.317972
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.sql import table

View File

@@ -5,7 +5,6 @@ Revises: 52a219fb5233
Create Date: 2024-09-10 15:03:48.233926
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 369644546676
Create Date: 2025-01-10 14:01:14.067144
"""
from alembic import op
# revision identifiers, used by Alembic.

View File

@@ -5,7 +5,6 @@ Revises: 77d07dffae64
Create Date: 2023-11-11 20:51:24.228999
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: e50154680a5c
Create Date: 2024-03-19 15:30:44.425436
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 4ee1287bd26a
Create Date: 2024-11-21 11:49:04.488677
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -1,28 +0,0 @@
"""Add indexes to document__tag
Revision ID: 1a03d2c2856b
Revises: 9c00a2bccb83
Create Date: 2025-02-18 10:45:13.957807
"""
from alembic import op
# revision identifiers, used by Alembic.
revision = "1a03d2c2856b"
down_revision = "9c00a2bccb83"
branch_labels: None = None
depends_on: None = None
def upgrade() -> None:
op.create_index(
op.f("ix_document__tag_tag_id"),
"document__tag",
["tag_id"],
unique=False,
)
def downgrade() -> None:
op.drop_index(op.f("ix_document__tag_tag_id"), table_name="document__tag")

View File

@@ -5,7 +5,6 @@ Revises: 6756efa39ada
Create Date: 2024-10-15 19:26:44.071259
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 35e6853a51d5
Create Date: 2024-09-18 11:48:59.418726
"""
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 5fc1f54cc252
Create Date: 2024-08-10 11:13:36.070790
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: bc9771dccadf
Create Date: 2024-06-27 16:04:51.480437
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 6d387b3196c2
Create Date: 2023-05-05 15:49:35.716016
"""
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 2daa494a0851
Create Date: 2024-11-12 13:23:29.858995
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 2666d766cb9b
Create Date: 2023-05-24 18:45:17.244495
"""
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: c0aab6edb6dd
Create Date: 2025-01-04 11:39:43.268612
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: f5437cc136c5
Create Date: 2025-02-11 14:57:51.308775
"""
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 4b08d97e175a
Create Date: 2024-08-21 19:15:15.762948
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: c0fd6e4da83a
Create Date: 2024-11-11 10:57:22.991157
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 33ea50e88f24
Create Date: 2025-01-31 10:30:27.289646
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 7f99be1cb9f5
Create Date: 2023-10-16 23:21:01.283424
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 91ffac7e65b3
Create Date: 2024-07-24 21:29:31.784562
"""
import random
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 5b29123cd710
Create Date: 2024-11-01 12:51:01.535003
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: a6df6b88ef81
Create Date: 2025-01-29 10:54:22.141765
"""
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: ee3f4b47fad5
Create Date: 2024-08-15 22:37:08.397052
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 91a0a4d62b14
Create Date: 2024-09-20 21:24:04.891018
"""
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: c99d76fcd298
Create Date: 2024-09-13 13:20:32.885317
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 2955778aa44c
Create Date: 2025-01-08 15:38:17.224380
"""
from alembic import op
from sqlalchemy import text

View File

@@ -1,52 +0,0 @@
"""add chunk stats table
Revision ID: 3781a5eb12cb
Revises: df46c75b714e
Create Date: 2025-03-10 10:02:30.586666
"""
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision = "3781a5eb12cb"
down_revision = "df46c75b714e"
branch_labels = None
depends_on = None
def upgrade() -> None:
op.create_table(
"chunk_stats",
sa.Column("id", sa.String(), primary_key=True, index=True),
sa.Column(
"document_id",
sa.String(),
sa.ForeignKey("document.id"),
nullable=False,
index=True,
),
sa.Column("chunk_in_doc_id", sa.Integer(), nullable=False),
sa.Column("information_content_boost", sa.Float(), nullable=True),
sa.Column(
"last_modified",
sa.DateTime(timezone=True),
nullable=False,
index=True,
server_default=sa.func.now(),
),
sa.Column("last_synced", sa.DateTime(timezone=True), nullable=True, index=True),
sa.UniqueConstraint(
"document_id", "chunk_in_doc_id", name="uq_chunk_stats_doc_chunk"
),
)
op.create_index(
"ix_chunk_sync_status", "chunk_stats", ["last_modified", "last_synced"]
)
def downgrade() -> None:
op.drop_index("ix_chunk_sync_status", table_name="chunk_stats")
op.drop_table("chunk_stats")

View File

@@ -5,7 +5,6 @@ Revises: f1c6478c3fd8
Create Date: 2024-05-11 16:11:23.718084
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 776b3bbe9092
Create Date: 2024-03-27 19:41:29.073594
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,126 +0,0 @@
"""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

@@ -5,7 +5,6 @@ Revises: e0a68a81d434
Create Date: 2023-10-05 18:47:09.582849
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,99 +0,0 @@
"""improved index
Revision ID: 3bd4c84fe72f
Revises: 8f43500ee275
Create Date: 2025-02-26 13:07:56.217791
"""
from alembic import op
# revision identifiers, used by Alembic.
revision = "3bd4c84fe72f"
down_revision = "8f43500ee275"
branch_labels = None
depends_on = None
# NOTE:
# This migration addresses issues with the previous migration (8f43500ee275) which caused
# an outage by creating an index without using CONCURRENTLY. This migration:
#
# 1. Creates more efficient full-text search capabilities using tsvector columns and GIN indexes
# 2. Uses CONCURRENTLY for all index creation to prevent table locking
# 3. Explicitly manages transactions with COMMIT statements to allow CONCURRENTLY to work
# (see: https://www.postgresql.org/docs/9.4/sql-createindex.html#SQL-CREATEINDEX-CONCURRENTLY)
# (see: https://github.com/sqlalchemy/alembic/issues/277)
# 4. Adds indexes to both chat_message and chat_session tables for comprehensive search
def upgrade() -> None:
# First, drop any existing indexes to avoid conflicts
op.execute("COMMIT")
op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_message_tsv;")
op.execute("COMMIT")
op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_session_desc_tsv;")
op.execute("COMMIT")
op.execute("DROP INDEX IF EXISTS idx_chat_message_message_lower;")
# Drop existing columns if they exist
op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv;")
op.execute("ALTER TABLE chat_session DROP COLUMN IF EXISTS description_tsv;")
# Create a GIN index for full-text search on chat_message.message
op.execute(
"""
ALTER TABLE chat_message
ADD COLUMN message_tsv tsvector
GENERATED ALWAYS AS (to_tsvector('english', message)) STORED;
"""
)
# Commit the current transaction before creating concurrent indexes
op.execute("COMMIT")
op.execute(
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_message_tsv
ON chat_message
USING GIN (message_tsv)
"""
)
# 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;
"""
)
# Commit again before creating the second concurrent index
op.execute("COMMIT")
op.execute(
"""
CREATE INDEX CONCURRENTLY IF NOT EXISTS idx_chat_session_desc_tsv
ON chat_session
USING GIN (description_tsv)
"""
)
def downgrade() -> None:
# Drop the indexes first (use CONCURRENTLY for dropping too)
op.execute("COMMIT")
op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_message_tsv;")
op.execute("COMMIT")
op.execute("DROP INDEX CONCURRENTLY IF EXISTS idx_chat_session_desc_tsv;")
# Then drop the columns
op.execute("ALTER TABLE chat_message DROP COLUMN IF EXISTS message_tsv;")
op.execute("ALTER TABLE chat_session DROP COLUMN IF EXISTS description_tsv;")
op.execute("DROP INDEX IF EXISTS idx_chat_message_message_lower;")

View File

@@ -5,7 +5,6 @@ Revises: 27c6ecc08586
Create Date: 2023-06-14 23:45:51.760440
"""
import sqlalchemy as sa
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: aeda5f2df4f6
Create Date: 2025-01-13 12:49:51.705235
"""
from alembic import op
import sqlalchemy as sa
import fastapi_users_db_sqlalchemy

View File

@@ -5,7 +5,6 @@ Revises: 703313b75876
Create Date: 2024-04-13 18:07:29.153817
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: e1392f05e840
Create Date: 2024-08-01 12:38:54.466081
"""
from alembic import op
# revision identifiers, used by Alembic.

View File

@@ -5,7 +5,6 @@ Revises: d716b0791ddd
Create Date: 2024-06-28 20:01:05.927647
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: c18cdf4b497e
Create Date: 2024-06-18 20:46:09.095034
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 3c5e35aa9af0
Create Date: 2023-07-18 17:33:40.365034
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 9d97fecfab7f
Create Date: 2023-10-27 11:38:33.803145
"""
from alembic import op
from sqlalchemy import String

View File

@@ -5,7 +5,6 @@ Revises: f32615f71aeb
Create Date: 2024-09-23 12:58:03.894038
"""
from alembic import op
# revision identifiers, used by Alembic.

View File

@@ -5,7 +5,6 @@ Revises: e91df4e935ef
Create Date: 2024-03-20 18:53:32.461518
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises:
Create Date: 2023-05-04 00:55:32.971991
"""
import sqlalchemy as sa
from alembic import op
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: ecab2b3f1a3b
Create Date: 2024-04-11 11:05:18.414438
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,51 +0,0 @@
"""update prompt length
Revision ID: 4794bc13e484
Revises: f7505c5b0284
Create Date: 2025-04-02 11:26:36.180328
"""
from alembic import op
import sqlalchemy as sa
# revision identifiers, used by Alembic.
revision = "4794bc13e484"
down_revision = "f7505c5b0284"
branch_labels = None
depends_on = None
def upgrade() -> None:
op.alter_column(
"prompt",
"system_prompt",
existing_type=sa.TEXT(),
type_=sa.String(length=5000000),
existing_nullable=False,
)
op.alter_column(
"prompt",
"task_prompt",
existing_type=sa.TEXT(),
type_=sa.String(length=5000000),
existing_nullable=False,
)
def downgrade() -> None:
op.alter_column(
"prompt",
"system_prompt",
existing_type=sa.String(length=5000000),
type_=sa.TEXT(),
existing_nullable=False,
)
op.alter_column(
"prompt",
"task_prompt",
existing_type=sa.String(length=5000000),
type_=sa.TEXT(),
existing_nullable=False,
)

View File

@@ -5,7 +5,6 @@ Revises: dfbe9e93d3c7
Create Date: 2024-11-05 18:55:02.221064
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: b85f02ec1308
Create Date: 2024-06-09 14:58:19.946509
"""
from alembic import op
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 7477a5f5d728
Create Date: 2024-08-10 19:20:34.527559
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: d9ec13955951
Create Date: 2024-08-20 15:28:52.993827
"""
from alembic import op
# revision identifiers, used by Alembic.

View File

@@ -5,11 +5,7 @@ Revises: f1ca58b2f2ec
Create Date: 2025-01-29 07:48:46.784041
"""
import logging
from typing import cast
from alembic import op
from sqlalchemy.exc import IntegrityError
from sqlalchemy.sql import text
@@ -19,45 +15,21 @@ down_revision = "f1ca58b2f2ec"
branch_labels = None
depends_on = None
logger = logging.getLogger("alembic.runtime.migration")
def upgrade() -> None:
"""Conflicts on lowercasing will result in the uppercased email getting a
unique integer suffix when converted to lowercase."""
# Get database connection
connection = op.get_bind()
# Fetch all user emails that are not already lowercase
user_emails = connection.execute(
text('SELECT id, email FROM "user" WHERE email != LOWER(email)')
).fetchall()
for user_id, email in user_emails:
email = cast(str, email)
username, domain = email.rsplit("@", 1)
new_email = f"{username.lower()}@{domain.lower()}"
attempt = 1
while True:
try:
# Try updating the email
connection.execute(
text('UPDATE "user" SET email = :new_email WHERE id = :user_id'),
{"new_email": new_email, "user_id": user_id},
)
break # Success, exit loop
except IntegrityError:
next_email = f"{username.lower()}_{attempt}@{domain.lower()}"
# Email conflict occurred, append `_1`, `_2`, etc., to the username
logger.warning(
f"Conflict while lowercasing email: "
f"old_email={email} "
f"conflicting_email={new_email} "
f"next_email={next_email}"
)
new_email = next_email
attempt += 1
# Update all user emails to lowercase
connection.execute(
text(
"""
UPDATE "user"
SET email = LOWER(email)
WHERE email != LOWER(email)
"""
)
)
def downgrade() -> None:

View File

@@ -5,7 +5,6 @@ Revises: 47e5bef3a1d7
Create Date: 2024-11-06 13:15:53.302644
"""
from typing import cast
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 7da0ae5ad583
Create Date: 2023-11-27 17:23:29.668422
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: f7e58d357687
Create Date: 2024-08-28 17:40:46.077470
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.sql import func

View File

@@ -5,7 +5,6 @@ Revises: 94dc3d0236f8
Create Date: 2024-12-11 18:05:05.490737
"""
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 61ff3651add4
Create Date: 2024-09-18 17:00:23.755399
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 7547d982db8f
Create Date: 2024-05-04 17:49:28.568109
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 800f48024ae9
Create Date: 2023-09-20 16:59:39.097177
"""
from alembic import op
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: d929f0c1c6af
Create Date: 2023-09-04 15:29:44.002164
"""
import fastapi_users_db_sqlalchemy
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 949b4a92a401
Create Date: 2024-10-30 19:37:59.630704
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: efb35676026c
Create Date: 2024-09-13 18:52:59.256478
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: e4334d5b33ba
Create Date: 2024-10-08 15:56:07.975636
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: e6a4bbc13fe4
Create Date: 2023-08-10 21:43:09.069523
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: dbaa756c2ccf
Create Date: 2024-02-16 15:02:03.319907
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 1d6ad76d1f37
Create Date: 2024-08-06 15:35:40.278485
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 1b8206b29c5d
Create Date: 2024-09-05 13:57:11.770413
"""
import fastapi_users_db_sqlalchemy
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 0a98909f2757
Create Date: 2024-05-07 14:54:55.493100
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 5d12a446f5c0
Create Date: 2024-10-15 17:47:44.108537
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -1,118 +0,0 @@
"""duplicated no-harm user file migration
Revision ID: 6a804aeb4830
Revises: 8e1ac4f39a9f
Create Date: 2025-04-01 07:26:10.539362
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy import inspect
import datetime
# revision identifiers, used by Alembic.
revision = "6a804aeb4830"
down_revision = "8e1ac4f39a9f"
branch_labels = None
depends_on = None
def upgrade() -> None:
# Check if user_file table already exists
conn = op.get_bind()
inspector = inspect(conn)
if not inspector.has_table("user_file"):
# Create user_folder table without parent_id
op.create_table(
"user_folder",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("user_id", sa.UUID(), sa.ForeignKey("user.id"), nullable=True),
sa.Column("name", sa.String(length=255), nullable=True),
sa.Column("description", sa.String(length=255), nullable=True),
sa.Column("display_priority", sa.Integer(), nullable=True, default=0),
sa.Column(
"created_at", sa.DateTime(timezone=True), server_default=sa.func.now()
),
)
# Create user_file table with folder_id instead of parent_folder_id
op.create_table(
"user_file",
sa.Column("id", sa.Integer(), primary_key=True, autoincrement=True),
sa.Column("user_id", sa.UUID(), sa.ForeignKey("user.id"), nullable=True),
sa.Column(
"folder_id",
sa.Integer(),
sa.ForeignKey("user_folder.id"),
nullable=True,
),
sa.Column("link_url", sa.String(), nullable=True),
sa.Column("token_count", sa.Integer(), nullable=True),
sa.Column("file_type", sa.String(), nullable=True),
sa.Column("file_id", sa.String(length=255), nullable=False),
sa.Column("document_id", sa.String(length=255), nullable=False),
sa.Column("name", sa.String(length=255), nullable=False),
sa.Column(
"created_at",
sa.DateTime(),
default=datetime.datetime.utcnow,
),
sa.Column(
"cc_pair_id",
sa.Integer(),
sa.ForeignKey("connector_credential_pair.id"),
nullable=True,
unique=True,
),
)
# Create persona__user_file table
op.create_table(
"persona__user_file",
sa.Column(
"persona_id",
sa.Integer(),
sa.ForeignKey("persona.id"),
primary_key=True,
),
sa.Column(
"user_file_id",
sa.Integer(),
sa.ForeignKey("user_file.id"),
primary_key=True,
),
)
# Create persona__user_folder table
op.create_table(
"persona__user_folder",
sa.Column(
"persona_id",
sa.Integer(),
sa.ForeignKey("persona.id"),
primary_key=True,
),
sa.Column(
"user_folder_id",
sa.Integer(),
sa.ForeignKey("user_folder.id"),
primary_key=True,
),
)
op.add_column(
"connector_credential_pair",
sa.Column("is_user_file", sa.Boolean(), nullable=True, default=False),
)
# Update existing records to have is_user_file=False instead of NULL
op.execute(
"UPDATE connector_credential_pair SET is_user_file = FALSE WHERE is_user_file IS NULL"
)
def downgrade() -> None:
pass

View File

@@ -5,7 +5,6 @@ Revises: 47433d30de82
Create Date: 2023-05-05 14:40:10.242502
"""
import fastapi_users_db_sqlalchemy
import sqlalchemy as sa
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 177de57c21c9
Create Date: 2024-11-22 11:51:29.331336
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 3c6531f32351
Create Date: 2025-01-13 18:12:18.029112
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: fad14119fb92
Create Date: 2024-04-15 01:36:02.952809
"""
import json
from typing import cast
from alembic import op

View File

@@ -5,7 +5,6 @@ Revises: 3879338f8ba1
Create Date: 2024-05-17 17:51:41.926893
"""
from alembic import op
import sqlalchemy as sa
from sqlalchemy.dialects import postgresql

View File

@@ -5,7 +5,6 @@ Revises: 475fcefe8826
Create Date: 2024-04-14 21:15:28.659634
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: ef7da92f7213
Create Date: 2024-05-02 15:18:56.573347
"""
from alembic import op
import sqlalchemy as sa
import fastapi_users_db_sqlalchemy

View File

@@ -5,7 +5,6 @@ Revises: dba7f71618f5
Create Date: 2023-09-21 10:03:21.509899
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: b156fa702355
Create Date: 2023-12-22 21:42:10.018804
"""
from alembic import op
import sqlalchemy as sa

View File

@@ -5,7 +5,6 @@ Revises: 4738e4b3bae1
Create Date: 2024-03-22 21:34:27.629444
"""
from alembic import op
import sqlalchemy as sa

Some files were not shown because too many files have changed in this diff Show More