Docker Compose Eval Pipeline Cleanup (#1780)

backend/danswer/db/connector_credential_pair.py

@@ -201,7 +201,7 @@ def add_credential_to_connector(
 def remove_credential_from_connector(
     connector_id: int,
     credential_id: int,
-    user: User,
+    user: User | None,
     db_session: Session,
 ) -> StatusResponse[int]:
     connector = fetch_connector_by_id(connector_id, db_session)

backend/danswer/server/documents/cc_pair.py

@@ -77,7 +77,7 @@ def associate_credential_to_connector(
     connector_id: int,
     credential_id: int,
     metadata: ConnectorCredentialPairMetadata,
-    user: User = Depends(current_user),
+    user: User | None = Depends(current_user),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse[int]:
     try:
@@ -97,7 +97,7 @@ def associate_credential_to_connector(
 def dissociate_credential_from_connector(
     connector_id: int,
     credential_id: int,
-    user: User = Depends(current_user),
+    user: User | None = Depends(current_user),
     db_session: Session = Depends(get_session),
 ) -> StatusResponse[int]:
     return remove_credential_from_connector(

deployment/docker_compose/docker-compose.dev.yml

@@ -287,6 +287,7 @@ services:
         max-size: "50m"
         max-file: "6"
 
+
   relational_db:
     image: postgres:15.2-alpine
     restart: always
@@ -335,7 +336,7 @@ services:
       options:
         max-size: "50m"
         max-file: "6"
-    # the specified script waits for the api_server to start up. 
+    # 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

deployment/docker_compose/docker-compose.gpu-dev.yml

@@ -343,7 +343,7 @@ services:
       options:
         max-size: "50m"
         max-file: "6"
-    # the specified script waits for the api_server to start up. 
+    # 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

deployment/docker_compose/docker-compose.prod-no-letsencrypt.yml

@@ -190,7 +190,7 @@ services:
       options:
         max-size: "50m"
         max-file: "6"
-    # the specified script waits for the api_server to start up. 
+    # 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

deployment/docker_compose/docker-compose.prod.yml

@@ -193,7 +193,7 @@ services:
       options:
         max-size: "50m"
         max-file: "6"
-    # the specified script waits for the api_server to start up. 
+    # 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

deployment/docker_compose/docker-compose.search-testing.yml

@@ -12,89 +12,17 @@ services:
     depends_on:
       - relational_db
       - index
-      # - inference_model_server
     restart: always
     ports:
       - "8080"
+    env_file:
+      - .env
     environment:
-      # Auth Settings
+      - AUTH_TYPE=disabled
-      - AUTH_TYPE=${AUTH_TYPE:-disabled}
-      - SESSION_EXPIRE_TIME_SECONDS=${SESSION_EXPIRE_TIME_SECONDS:-86400}
-      - ENCRYPTION_KEY_SECRET=${ENCRYPTION_KEY_SECRET:-}
-      - VALID_EMAIL_DOMAINS=${VALID_EMAIL_DOMAINS:-}
-      - 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=${SMTP_PORT:-587}  # For sending verification emails, if unspecified then defaults to '587'
-      - SMTP_USER=${SMTP_USER:-}
-      - SMTP_PASS=${SMTP_PASS:-}
-      - EMAIL_FROM=${EMAIL_FROM:-}
-      - OAUTH_CLIENT_ID=${OAUTH_CLIENT_ID:-}
-      - OAUTH_CLIENT_SECRET=${OAUTH_CLIENT_SECRET:-}
-      - OPENID_CONFIG_URL=${OPENID_CONFIG_URL:-}
-      # Gen AI Settings
-      - GEN_AI_MODEL_PROVIDER=${GEN_AI_MODEL_PROVIDER:-}
-      - GEN_AI_MODEL_VERSION=${GEN_AI_MODEL_VERSION:-}
-      - FAST_GEN_AI_MODEL_VERSION=${FAST_GEN_AI_MODEL_VERSION:-}
-      - GEN_AI_API_KEY=${GEN_AI_API_KEY:-}
-      - GEN_AI_API_ENDPOINT=${GEN_AI_API_ENDPOINT:-}
-      - GEN_AI_API_VERSION=${GEN_AI_API_VERSION:-}
-      - GEN_AI_LLM_PROVIDER_TYPE=${GEN_AI_LLM_PROVIDER_TYPE:-}
-      - GEN_AI_MAX_TOKENS=${GEN_AI_MAX_TOKENS:-}
-      - QA_TIMEOUT=${QA_TIMEOUT:-}
-      - MAX_CHUNKS_FED_TO_CHAT=${MAX_CHUNKS_FED_TO_CHAT:-}
-      - DISABLE_LLM_FILTER_EXTRACTION=${DISABLE_LLM_FILTER_EXTRACTION:-}
-      - DISABLE_LLM_CHUNK_FILTER=${DISABLE_LLM_CHUNK_FILTER:-}
-      - DISABLE_LLM_CHOOSE_SEARCH=${DISABLE_LLM_CHOOSE_SEARCH:-}
-      - DISABLE_LLM_QUERY_REPHRASE=${DISABLE_LLM_QUERY_REPHRASE:-}
-      - DISABLE_GENERATIVE_AI=${DISABLE_GENERATIVE_AI:-}
-      - DISABLE_LITELLM_STREAMING=${DISABLE_LITELLM_STREAMING:-}
-      - LITELLM_EXTRA_HEADERS=${LITELLM_EXTRA_HEADERS:-}
-      - BING_API_KEY=${BING_API_KEY:-}
-      # if set, allows for the use of the token budget system
-      - TOKEN_BUDGET_GLOBALLY_ENABLED=${TOKEN_BUDGET_GLOBALLY_ENABLED:-}
-      # Enables the use of bedrock models
-      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID:-}
-      - AWS_SECRET_ACCESS_KEY=${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=${HYBRID_ALPHA:-}  # Hybrid Search Alpha (0 for entirely keyword, 1 for entirely vector)
-      - EDIT_KEYWORD_QUERY=${EDIT_KEYWORD_QUERY:-}
-      - MULTILINGUAL_QUERY_EXPANSION=${MULTILINGUAL_QUERY_EXPANSION:-}
-      - LANGUAGE_HINT=${LANGUAGE_HINT:-}
-      - LANGUAGE_CHAT_NAMING_HINT=${LANGUAGE_CHAT_NAMING_HINT:-}
-      - QA_PROMPT_OVERRIDE=${QA_PROMPT_OVERRIDE:-}
-      # Other services
       - POSTGRES_HOST=relational_db
       - VESPA_HOST=index
-      - WEB_DOMAIN=${WEB_DOMAIN:-}  # For frontend redirect auth purpose
+      - MODEL_SERVER_HOST=${MODEL_SERVER_HOST:-inference_model_server}
-      # Don't change the NLP model configs unless you know what you're doing
+      - ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=True
-      - DOCUMENT_ENCODER_MODEL=${DOCUMENT_ENCODER_MODEL:-}
-      - DOC_EMBEDDING_DIM=${DOC_EMBEDDING_DIM:-}
-      - NORMALIZE_EMBEDDINGS=${NORMALIZE_EMBEDDINGS:-}
-      - ASYM_QUERY_PREFIX=${ASYM_QUERY_PREFIX:-}
-      - ENABLE_RERANKING_REAL_TIME_FLOW=${ENABLE_RERANKING_REAL_TIME_FLOW:-}
-      - ENABLE_RERANKING_ASYNC_FLOW=${ENABLE_RERANKING_ASYNC_FLOW:-}
-      - MODEL_SERVER_HOST=${MODEL_SERVER_HOST:-}
-      - MODEL_SERVER_ALLOWED_HOST=${MODEL_SERVER_HOST:-}
-      - MODEL_SERVER_PORT=${MODEL_SERVER_PORT:-}
-      # Leave this on pretty please? Nothing sensitive is collected!
-      # https://docs.danswer.dev/more/telemetry
-      - DISABLE_TELEMETRY=${DISABLE_TELEMETRY:-}
-      - LOG_LEVEL=${LOG_LEVEL:-info}  # Set to debug to get more fine-grained logs
-      - LOG_ALL_MODEL_INTERACTIONS=${LOG_ALL_MODEL_INTERACTIONS:-}  # Log all of the prompts to the LLM
-      # 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=${LOG_VESPA_TIMING_INFORMATION:-}
-      - LOG_ENDPOINT_LATENCY=${LOG_ENDPOINT_LATENCY:-}
-
-      # Enterprise Edition only
-      - ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=${ENABLE_PAID_ENTERPRISE_EDITION_FEATURES:-false}
-      - API_KEY_HASH_ROUNDS=${API_KEY_HASH_ROUNDS:-}
-      # Seeding configuration
-      - ENV_SEED_CONFIGURATION=${ENV_SEED_CONFIGURATION:-}
     extra_hosts:
       - "host.docker.internal:host-gateway"
     logging:
@@ -113,91 +41,16 @@ services:
     depends_on:
       - relational_db
       - index
-      # - inference_model_server
-      # - indexing_model_server
     restart: always
+    env_file:
+      - .env
     environment:
-      - ENCRYPTION_KEY_SECRET=${ENCRYPTION_KEY_SECRET:-}
+      - AUTH_TYPE=disabled
-      # Gen AI Settings (Needed by DanswerBot)
-      - GEN_AI_MODEL_PROVIDER=${GEN_AI_MODEL_PROVIDER:-}
-      - GEN_AI_MODEL_VERSION=${GEN_AI_MODEL_VERSION:-}
-      - FAST_GEN_AI_MODEL_VERSION=${FAST_GEN_AI_MODEL_VERSION:-}
-      - GEN_AI_API_KEY=${GEN_AI_API_KEY:-}
-      - GEN_AI_API_ENDPOINT=${GEN_AI_API_ENDPOINT:-}
-      - GEN_AI_API_VERSION=${GEN_AI_API_VERSION:-}
-      - GEN_AI_LLM_PROVIDER_TYPE=${GEN_AI_LLM_PROVIDER_TYPE:-}
-      - GEN_AI_MAX_TOKENS=${GEN_AI_MAX_TOKENS:-}
-      - QA_TIMEOUT=${QA_TIMEOUT:-}
-      - MAX_CHUNKS_FED_TO_CHAT=${MAX_CHUNKS_FED_TO_CHAT:-}
-      - DISABLE_LLM_FILTER_EXTRACTION=${DISABLE_LLM_FILTER_EXTRACTION:-}
-      - DISABLE_LLM_CHUNK_FILTER=${DISABLE_LLM_CHUNK_FILTER:-}
-      - DISABLE_LLM_CHOOSE_SEARCH=${DISABLE_LLM_CHOOSE_SEARCH:-}
-      - DISABLE_LLM_QUERY_REPHRASE=${DISABLE_LLM_QUERY_REPHRASE:-}
-      - DISABLE_GENERATIVE_AI=${DISABLE_GENERATIVE_AI:-}
-      - GENERATIVE_MODEL_ACCESS_CHECK_FREQ=${GENERATIVE_MODEL_ACCESS_CHECK_FREQ:-}
-      - DISABLE_LITELLM_STREAMING=${DISABLE_LITELLM_STREAMING:-}
-      - LITELLM_EXTRA_HEADERS=${LITELLM_EXTRA_HEADERS:-}
-      - BING_API_KEY=${BING_API_KEY:-}
-      # Query Options
-      - DOC_TIME_DECAY=${DOC_TIME_DECAY:-}  # Recency Bias for search results, decay at 1 / (1 + DOC_TIME_DECAY * x years)
-      - HYBRID_ALPHA=${HYBRID_ALPHA:-}  # Hybrid Search Alpha (0 for entirely keyword, 1 for entirely vector)
-      - EDIT_KEYWORD_QUERY=${EDIT_KEYWORD_QUERY:-}
-      - MULTILINGUAL_QUERY_EXPANSION=${MULTILINGUAL_QUERY_EXPANSION:-}
-      - LANGUAGE_HINT=${LANGUAGE_HINT:-}
-      - LANGUAGE_CHAT_NAMING_HINT=${LANGUAGE_CHAT_NAMING_HINT:-}
-      - QA_PROMPT_OVERRIDE=${QA_PROMPT_OVERRIDE:-}
-      # Other Services
       - POSTGRES_HOST=relational_db
-      - POSTGRES_USER=${POSTGRES_USER:-}
-      - POSTGRES_PASSWORD=${POSTGRES_PASSWORD:-}
-      - POSTGRES_DB=${POSTGRES_DB:-}
       - VESPA_HOST=index
-      - WEB_DOMAIN=${WEB_DOMAIN:-}  # For frontend redirect auth purpose for OAuth2 connectors
+      - MODEL_SERVER_HOST=${MODEL_SERVER_HOST:-inference_model_server}
-      # Don't change the NLP model configs unless you know what you're doing
+      - INDEXING_MODEL_SERVER_HOST=${INDEXING_MODEL_SERVER_HOST:-indexing_model_server}
-      - DOCUMENT_ENCODER_MODEL=${DOCUMENT_ENCODER_MODEL:-}
+      - ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=True
-      - DOC_EMBEDDING_DIM=${DOC_EMBEDDING_DIM:-}
-      - NORMALIZE_EMBEDDINGS=${NORMALIZE_EMBEDDINGS:-}
-      - ASYM_QUERY_PREFIX=${ASYM_QUERY_PREFIX:-}  # Needed by DanswerBot
-      - ASYM_PASSAGE_PREFIX=${ASYM_PASSAGE_PREFIX:-}
-      - MODEL_SERVER_HOST=${MODEL_SERVER_HOST:-}
-      - MODEL_SERVER_ALLOWED_HOST=${MODEL_SERVER_HOST:-}
-      - MODEL_SERVER_PORT=${MODEL_SERVER_PORT:-}
-      - INDEXING_MODEL_SERVER_HOST=${INDEXING_MODEL_SERVER_HOST:-}
-      # Indexing Configs
-      - NUM_INDEXING_WORKERS=${NUM_INDEXING_WORKERS:-}
-      - ENABLED_CONNECTOR_TYPES=${ENABLED_CONNECTOR_TYPES:-}
-      - DISABLE_INDEX_UPDATE_ON_SWAP=${DISABLE_INDEX_UPDATE_ON_SWAP:-}
-      - DASK_JOB_CLIENT_ENABLED=${DASK_JOB_CLIENT_ENABLED:-}
-      - CONTINUE_ON_CONNECTOR_FAILURE=${CONTINUE_ON_CONNECTOR_FAILURE:-}
-      - EXPERIMENTAL_CHECKPOINTING_ENABLED=${EXPERIMENTAL_CHECKPOINTING_ENABLED:-}
-      - CONFLUENCE_CONNECTOR_LABELS_TO_SKIP=${CONFLUENCE_CONNECTOR_LABELS_TO_SKIP:-}
-      - JIRA_CONNECTOR_LABELS_TO_SKIP=${JIRA_CONNECTOR_LABELS_TO_SKIP:-}
-      - WEB_CONNECTOR_VALIDATE_URLS=${WEB_CONNECTOR_VALIDATE_URLS:-}
-      - JIRA_API_VERSION=${JIRA_API_VERSION:-}
-      - GONG_CONNECTOR_START_TIME=${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
-      - DANSWER_BOT_SLACK_APP_TOKEN=${DANSWER_BOT_SLACK_APP_TOKEN:-}
-      - DANSWER_BOT_SLACK_BOT_TOKEN=${DANSWER_BOT_SLACK_BOT_TOKEN:-}
-      - 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=${DANSWER_BOT_DISABLE_COT:-}  # Currently unused
-      - NOTIFY_SLACKBOT_NO_ANSWER=${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
-      - DISABLE_TELEMETRY=${DISABLE_TELEMETRY:-}
-      - LOG_LEVEL=${LOG_LEVEL:-info}  # Set to debug to get more fine-grained logs
-      - LOG_ALL_MODEL_INTERACTIONS=${LOG_ALL_MODEL_INTERACTIONS:-}  # Log all of the prompts to the LLM
-      - LOG_VESPA_TIMING_INFORMATION=${LOG_VESPA_TIMING_INFORMATION:-}
-
-      # Enterprise Edition stuff
-      - ENABLE_PAID_ENTERPRISE_EDITION_FEATURES=${ENABLE_PAID_ENTERPRISE_EDITION_FEATURES:-false}
     extra_hosts:
       - "host.docker.internal:host-gateway"
     logging:
@@ -250,10 +103,7 @@ services:
     restart: on-failure
     environment:
       - MIN_THREADS_ML_MODELS=${MIN_THREADS_ML_MODELS:-}
-      # Set to debug to get more fine-grained logs
+      - LOG_LEVEL=${LOG_LEVEL:-debug}
-      - LOG_LEVEL=${LOG_LEVEL:-info}
-    # volumes:
-      # Not necessary, this is just to reduce download time during startup
       - inference_model_cache_huggingface:/root/.cache/huggingface/
     logging:
       driver: json-file
@@ -278,10 +128,7 @@ services:
     environment:
       - MIN_THREADS_ML_MODELS=${MIN_THREADS_ML_MODELS:-}
       - INDEXING_ONLY=True
-      # Set to debug to get more fine-grained logs
+      - LOG_LEVEL=${LOG_LEVEL:-debug}
-      - LOG_LEVEL=${LOG_LEVEL:-info}
-    # volumes:
-      # Not necessary, this is just to reduce download time during startup
       - index_model_cache_huggingface:/root/.cache/huggingface/
     logging:
       driver: json-file
@@ -289,6 +136,7 @@ services:
         max-size: "50m"
         max-file: "6"
 
+
   relational_db:
     image: postgres:15.2-alpine
     restart: always
@@ -337,7 +185,7 @@ services:
       options:
         max-size: "50m"
         max-file: "6"
-    # the specified script waits for the api_server to start up. 
+    # 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
@@ -345,13 +193,7 @@ services:
     command: > 
       /bin/sh -c "dos2unix /etc/nginx/conf.d/run-nginx.sh 
       && /etc/nginx/conf.d/run-nginx.sh app.conf.template.dev"
-        
 
-# volumes:
-#   db_volume:
-#   vespa_volume:
-#   # Created by the container itself
-#   model_cache_huggingface:
 
 volumes:
   db_volume:
@@ -366,41 +208,3 @@ volumes:
       type: none
       o: bind
       device: ${DANSWER_VESPA_DATA_DIR:-./vespa_data}
-  model_cache_huggingface:
-  #   driver: local
-  #   driver_opts:
-  #     type: none
-  #     o: bind
-  #     device: ${DANSWER_MODEL_CACHE_DIR:-./model_cache}
-  # index_model_cache_huggingface:
-  #   driver: local
-  #   driver_opts:
-  #     type: none
-  #     o: bind
-  #     device: ${DANSWER_INDEX_MODEL_CACHE_DIR:-./model_cache}
-  # inference_model_cache_huggingface:
-  #   driver: local
-  #   driver_opts:
-  #     type: none
-  #     o: bind
-  #     device: ${DANSWER_INFERENCE_MODEL_CACHE_DIR:-./model_cache}
-
-# volumes:
-#   db_volume:
-#     driver: local
-#     driver_opts:
-#       type: none
-#       o: bind
-#       device: ${DANSWER_POSTGRES_DATA_DIR:-./postgres_data}
-#   vespa_volume:
-#     driver: local
-#     driver_opts:
-#       type: none
-#       o: bind
-#       device: ${DANSWER_VESPA_DATA_DIR:-./vespa_data}
-#   model_cache_huggingface:
-#     driver: local
-#     driver_opts:
-#       type: none
-#       o: bind
-#       device: ${DANSWER_MODEL_CACHE_DIR:-./model_cache}