highperfocused/danswer
1
0
Fork 0
mirror of https://github.com/danswer-ai/danswer.git synced 2025-09-27 12:29:41 +02:00
Code Issues Packages Projects Releases Wiki Activity

welcome to onyx

Browse Source
This commit is contained in:
pablodanswer
2024-12-13 09:48:43 -08:00
parent 54dcbfa288
commit 21ec5ed795
813 changed files with 7021 additions and 6824 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
deployment/docker_compose/docker-compose.gpu-dev.yml
View File

@@ -1,13 +1,13 @@
services:
api_server:
image: danswer/danswer-backend:${IMAGE_TAG:-latest}
image: onyxdotapp/onyx-backend:${IMAGE_TAG:-latest}
build:
context: ../../backend
dockerfile: Dockerfile
command: >
/bin/sh -c "alembic upgrade head &&
echo \"Starting Danswer Api Server\" &&
uvicorn danswer.main:app --host 0.0.0.0 --port 8080"
echo \"Starting Onyx Api Server\" &&
uvicorn onyx.main:app --host 0.0.0.0 --port 8080"
depends_on:
- relational_db
- index
@@ -25,8 +25,8 @@ services:
- GOOGLE_OAUTH_CLIENT_ID=${GOOGLE_OAUTH_CLIENT_ID:-}
- GOOGLE_OAUTH_CLIENT_SECRET=${GOOGLE_OAUTH_CLIENT_SECRET:-}
- REQUIRE_EMAIL_VERIFICATION=${REQUIRE_EMAIL_VERIFICATION:-}
- SMTP_SERVER=${SMTP_SERVER:-} # For sending verification emails, if unspecified then defaults to 'smtp.gmail.com'
- SMTP_PORT=${SMTP_PORT:-587} # For sending verification emails, if unspecified then defaults to '587'
- SMTP_SERVER=${SMTP_SERVER:-} # For sending verification emails, if unspecified then defaults to 'smtp.gmail.com'
- SMTP_PORT=${SMTP_PORT:-587} # For sending verification emails, if unspecified then defaults to '587'
- SMTP_USER=${SMTP_USER:-}
- SMTP_PASS=${SMTP_PASS:-}
- EMAIL_FROM=${EMAIL_FROM:-}
@@ -49,8 +49,8 @@ services:
- AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY:-}
- AWS_REGION_NAME=${AWS_REGION_NAME:-}
# Query Options
- DOC_TIME_DECAY=${DOC_TIME_DECAY:-} # Recency Bias for search results, decay at 1 / (1 + DOC_TIME_DECAY * x years)
- HYBRID_ALPHA=${HYBRID_ALPHA:-} # Hybrid Search Alpha (0 for entirely keyword, 1 for entirely vector)
- DOC_TIME_DECAY=${DOC_TIME_DECAY:-} # Recency Bias for search results, decay at 1 / (1 + DOC_TIME_DECAY * x years)
- HYBRID_ALPHA=${HYBRID_ALPHA:-} # Hybrid Search Alpha (0 for entirely keyword, 1 for entirely vector)
- EDIT_KEYWORD_QUERY=${EDIT_KEYWORD_QUERY:-}
- MULTILINGUAL_QUERY_EXPANSION=${MULTILINGUAL_QUERY_EXPANSION:-}
- LANGUAGE_HINT=${LANGUAGE_HINT:-}
@@ -59,8 +59,8 @@ services:
# Other services
- POSTGRES_HOST=relational_db
- VESPA_HOST=index
- REDIS_HOST=cache
- WEB_DOMAIN=${WEB_DOMAIN:-} # For frontend redirect auth purpose
- REDIS_HOST=cache
- WEB_DOMAIN=${WEB_DOMAIN:-} # For frontend redirect auth purpose
# Don't change the NLP model configs unless you know what you're doing
- EMBEDDING_BATCH_SIZE=${EMBEDDING_BATCH_SIZE:-}
- DOCUMENT_ENCODER_MODEL=${DOCUMENT_ENCODER_MODEL:-}
@@ -74,17 +74,17 @@ services:
# We do not recommend changing this value
- SYSTEM_RECURSION_LIMIT=${SYSTEM_RECURSION_LIMIT:-}
# Leave this on pretty please? Nothing sensitive is collected!
# https://docs.danswer.dev/more/telemetry
# https://docs.onyx.app/more/telemetry
- DISABLE_TELEMETRY=${DISABLE_TELEMETRY:-}
- LOG_LEVEL=${LOG_LEVEL:-info} # Set to debug to get more fine-grained logs
- LOG_ALL_MODEL_INTERACTIONS=${LOG_ALL_MODEL_INTERACTIONS:-} # LiteLLM Verbose Logging
# Log all of Danswer prompts and interactions with the LLM
- LOG_LEVEL=${LOG_LEVEL:-info} # Set to debug to get more fine-grained logs
- LOG_ALL_MODEL_INTERACTIONS=${LOG_ALL_MODEL_INTERACTIONS:-} # LiteLLM Verbose Logging
# Log all of Onyx prompts and interactions with the LLM
- LOG_DANSWER_MODEL_INTERACTIONS=${LOG_DANSWER_MODEL_INTERACTIONS:-}
# If set to `true` will enable additional logs about Vespa query performance
# (time spent on finding the right docs + time spent fetching summaries from disk)
- LOG_VESPA_TIMING_INFORMATION=${LOG_VESPA_TIMING_INFORMATION:-}
- CELERY_BROKER_POOL_LIMIT=${CELERY_BROKER_POOL_LIMIT:-}
# Chat Configs
- HARD_DELETE_CHATS=${HARD_DELETE_CHATS:-}
@@ -99,9 +99,8 @@ services:
max-size: "50m"
max-file: "6"
background:
image: danswer/danswer-backend:${IMAGE_TAG:-latest}
image: onyxdotapp/onyx-backend:${IMAGE_TAG:-latest}
build:
context: ../../backend
dockerfile: Dockerfile
@@ -115,7 +114,7 @@ services:
restart: always
environment:
- ENCRYPTION_KEY_SECRET=${ENCRYPTION_KEY_SECRET:-}
# Gen AI Settings (Needed by DanswerBot)
# Gen AI Settings (Needed by OnyxBot)
- GEN_AI_MAX_TOKENS=${GEN_AI_MAX_TOKENS:-}
- QA_TIMEOUT=${QA_TIMEOUT:-}
- MAX_CHUNKS_FED_TO_CHAT=${MAX_CHUNKS_FED_TO_CHAT:-}
@@ -127,8 +126,8 @@ services:
- DISABLE_LITELLM_STREAMING=${DISABLE_LITELLM_STREAMING:-}
- LITELLM_EXTRA_HEADERS=${LITELLM_EXTRA_HEADERS:-}
# Query Options
- DOC_TIME_DECAY=${DOC_TIME_DECAY:-} # Recency Bias for search results, decay at 1 / (1 + DOC_TIME_DECAY * x years)
- HYBRID_ALPHA=${HYBRID_ALPHA:-} # Hybrid Search Alpha (0 for entirely keyword, 1 for entirely vector)
- DOC_TIME_DECAY=${DOC_TIME_DECAY:-} # Recency Bias for search results, decay at 1 / (1 + DOC_TIME_DECAY * x years)
- HYBRID_ALPHA=${HYBRID_ALPHA:-} # Hybrid Search Alpha (0 for entirely keyword, 1 for entirely vector)
- EDIT_KEYWORD_QUERY=${EDIT_KEYWORD_QUERY:-}
- MULTILINGUAL_QUERY_EXPANSION=${MULTILINGUAL_QUERY_EXPANSION:-}
- LANGUAGE_HINT=${LANGUAGE_HINT:-}
@@ -141,12 +140,12 @@ services:
- POSTGRES_DB=${POSTGRES_DB:-}
- VESPA_HOST=index
- REDIS_HOST=cache
- WEB_DOMAIN=${WEB_DOMAIN:-} # For frontend redirect auth purpose for OAuth2 connectors
- WEB_DOMAIN=${WEB_DOMAIN:-} # For frontend redirect auth purpose for OAuth2 connectors
# Don't change the NLP model configs unless you know what you're doing
- DOCUMENT_ENCODER_MODEL=${DOCUMENT_ENCODER_MODEL:-}
- DOC_EMBEDDING_DIM=${DOC_EMBEDDING_DIM:-}
- NORMALIZE_EMBEDDINGS=${NORMALIZE_EMBEDDINGS:-}
- ASYM_QUERY_PREFIX=${ASYM_QUERY_PREFIX:-} # Needed by DanswerBot
- ASYM_QUERY_PREFIX=${ASYM_QUERY_PREFIX:-} # Needed by OnyxBot
- ASYM_PASSAGE_PREFIX=${ASYM_PASSAGE_PREFIX:-}
- MODEL_SERVER_HOST=${MODEL_SERVER_HOST:-inference_model_server}
- MODEL_SERVER_PORT=${MODEL_SERVER_PORT:-}
@@ -166,22 +165,22 @@ services:
- GONG_CONNECTOR_START_TIME=${GONG_CONNECTOR_START_TIME:-}
- NOTION_CONNECTOR_ENABLE_RECURSIVE_PAGE_LOOKUP=${NOTION_CONNECTOR_ENABLE_RECURSIVE_PAGE_LOOKUP:-}
- GITHUB_CONNECTOR_BASE_URL=${GITHUB_CONNECTOR_BASE_URL:-}
# Danswer SlackBot Configs
# Onyx SlackBot Configs
- DANSWER_BOT_DISABLE_DOCS_ONLY_ANSWER=${DANSWER_BOT_DISABLE_DOCS_ONLY_ANSWER:-}
- DANSWER_BOT_FEEDBACK_VISIBILITY=${DANSWER_BOT_FEEDBACK_VISIBILITY:-}
- DANSWER_BOT_DISPLAY_ERROR_MSGS=${DANSWER_BOT_DISPLAY_ERROR_MSGS:-}
- DANSWER_BOT_RESPOND_EVERY_CHANNEL=${DANSWER_BOT_RESPOND_EVERY_CHANNEL:-}
- DANSWER_BOT_DISABLE_COT=${DANSWER_BOT_DISABLE_COT:-} # Currently unused
- DANSWER_BOT_DISABLE_COT=${DANSWER_BOT_DISABLE_COT:-} # Currently unused
- NOTIFY_SLACKBOT_NO_ANSWER=${NOTIFY_SLACKBOT_NO_ANSWER:-}
- DANSWER_BOT_MAX_QPM=${DANSWER_BOT_MAX_QPM:-}
- DANSWER_BOT_MAX_WAIT_TIME=${DANSWER_BOT_MAX_WAIT_TIME:-}
# Logging
# Leave this on pretty please? Nothing sensitive is collected!
# https://docs.danswer.dev/more/telemetry
# https://docs.onyx.app/more/telemetry
- DISABLE_TELEMETRY=${DISABLE_TELEMETRY:-}
- LOG_LEVEL=${LOG_LEVEL:-info} # Set to debug to get more fine-grained logs
- LOG_ALL_MODEL_INTERACTIONS=${LOG_ALL_MODEL_INTERACTIONS:-} # LiteLLM Verbose Logging
# Log all of Danswer prompts and interactions with the LLM
- LOG_LEVEL=${LOG_LEVEL:-info} # Set to debug to get more fine-grained logs
- LOG_ALL_MODEL_INTERACTIONS=${LOG_ALL_MODEL_INTERACTIONS:-} # LiteLLM Verbose Logging
# Log all of Onyx prompts and interactions with the LLM
- LOG_DANSWER_MODEL_INTERACTIONS=${LOG_DANSWER_MODEL_INTERACTIONS:-}
- LOG_VESPA_TIMING_INFORMATION=${LOG_VESPA_TIMING_INFORMATION:-}
# Celery Configs (defaults are set in the supervisord.conf file.
@@ -201,9 +200,8 @@ services:
max-size: "50m"
max-file: "6"
web_server:
image: danswer/danswer-web-server:${IMAGE_TAG:-latest}
image: onyxdotapp/onyx-web-server:${IMAGE_TAG:-latest}
build:
context: ../../web
dockerfile: Dockerfile
@@ -226,9 +224,8 @@ services:
# Enterprise Edition only
- ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=${ENABLE_PAID_ENTERPRISE_EDITION_FEATURES:-false}
inference_model_server:
image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
image: onyxdotapp/onyx-model-server:${IMAGE_TAG:-latest}
# for GPU support, please read installation guidelines in the README.md
# bare minimum to get this working is to install nvidia-container-toolkit
deploy:
@@ -264,9 +261,8 @@ services:
max-size: "50m"
max-file: "6"
indexing_model_server:
image: danswer/danswer-model-server:${IMAGE_TAG:-latest}
image: onyxdotapp/onyx-model-server:${IMAGE_TAG:-latest}
build:
context: ../../backend
dockerfile: Dockerfile.model_server
@@ -302,7 +298,6 @@ services:
max-size: "50m"
max-file: "6"
relational_db:
image: postgres:15.2-alpine
command: -c 'max_connections=250'
@@ -315,7 +310,6 @@ services:
volumes:
- db_volume:/var/lib/postgresql/data
# This container name cannot have an underscore in it due to Vespa expectations of the URL
index:
image: vespaengine/vespa:8.277.17
@@ -331,12 +325,11 @@ services:
max-size: "50m"
max-file: "6"
nginx:
image: nginx:1.23.4-alpine
restart: always
# nginx will immediately crash with `nginx: [emerg] host not found in upstream`
# if api_server / web_server are not up
# if api_server / web_server are not up
depends_on:
- api_server
- web_server
@@ -344,7 +337,7 @@ services:
- DOMAIN=localhost
ports:
- "80:80"
- "3000:80" # allow for localhost:3000 usage, since that is the norm
- "3000:80" # allow for localhost:3000 usage, since that is the norm
volumes:
- ../data/nginx:/etc/nginx/conf.d
logging:
@@ -352,26 +345,24 @@ services:
options:
max-size: "50m"
max-file: "6"
# The specified script waits for the api_server to start up.
# Without this we've seen issues where nginx shows no error logs but
# The specified script waits for the api_server to start up.
# Without this we've seen issues where nginx shows no error logs but
# does not recieve any traffic
# NOTE: we have to use dos2unix to remove Carriage Return chars from the file
# in order to make this work on both Unix-like systems and windows
command: >
command: >
/bin/sh -c "dos2unix /etc/nginx/conf.d/run-nginx.sh
&& /etc/nginx/conf.d/run-nginx.sh app.conf.template.dev"
cache:
image: redis:7.4-alpine
restart: always
ports:
- '6379:6379'
- "6379:6379"
# docker silently mounts /data even without an explicit volume mount, which enables
# persistence. explicitly setting save and appendonly forces ephemeral behavior.
command: redis-server --save "" --appendonly no
volumes:
db_volume:
vespa_volume: