opensource/dify
3
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-10-24 23:33:12 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'myori/main' into feat/collaboration2

Browse Source
This commit is contained in:
hjlarry
2026-01-17 10:22:41 +08:00
parent b549d669d6 c98870c3f4
commit fc291e4ca2
6266 changed files with 544206 additions and 224644 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docker/.env.example
+169 -36
View File
@@ -58,8 +58,8 @@ FILES_URL=
INTERNAL_FILES_URL=
# Ensure UTF-8 encoding
LANG=en_US.UTF-8
LC_ALL=en_US.UTF-8
LANG=C.UTF-8
LC_ALL=C.UTF-8
PYTHONIOENCODING=utf-8
# ------------------------------
@@ -69,6 +69,8 @@ PYTHONIOENCODING=utf-8
# The log level for the application.
# Supported values are `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL`
LOG_LEVEL=INFO
# Log output format: text or json
LOG_OUTPUT_FORMAT=text
# Log file path
LOG_FILE=/app/logs/server.log
# Log file max size, the unit is MB
@@ -137,6 +139,8 @@ ACCESS_TOKEN_EXPIRE_MINUTES=60
# Refresh token expiration time in days
REFRESH_TOKEN_EXPIRE_DAYS=30
# The default number of active requests for the application, where 0 means unlimited, should be a non-negative integer.
APP_DEFAULT_ACTIVE_REQUESTS=0
# The maximum number of active requests for the application, where 0 means unlimited, should be a non-negative integer.
APP_MAX_ACTIVE_REQUESTS=0
APP_MAX_EXECUTION_TIME=1200
@@ -229,15 +233,20 @@ NEXT_PUBLIC_ENABLE_SINGLE_DOLLAR_LATEX=false
# ------------------------------
# Database Configuration
# The database uses PostgreSQL. Please use the public schema.
# It is consistent with the configuration in the 'db' service below.
# The database uses PostgreSQL or MySQL. OceanBase and seekdb are also supported. Please use the public schema.
# It is consistent with the configuration in the database service below.
# You can adjust the database configuration according to your needs.
# ------------------------------
# Database type, supported values are `postgresql`, `mysql`, `oceanbase`, `seekdb`
DB_TYPE=postgresql
# For MySQL, only `root` user is supported for now
DB_USERNAME=postgres
DB_PASSWORD=difyai123456
DB_HOST=db
DB_HOST=db_postgres
DB_PORT=5432
DB_DATABASE=dify
# The size of the database connection pool.
# The default is 30 connections, which can be appropriately increased.
SQLALCHEMY_POOL_SIZE=30
@@ -299,6 +308,29 @@ POSTGRES_STATEMENT_TIMEOUT=0
# A value of 0 prevents the server from terminating idle sessions.
POSTGRES_IDLE_IN_TRANSACTION_SESSION_TIMEOUT=0
# MySQL Performance Configuration
# Maximum number of connections to MySQL
#
# Default is 1000
MYSQL_MAX_CONNECTIONS=1000
# InnoDB buffer pool size
# Default is 512M
# Recommended value: 70-80% of available memory for dedicated MySQL server
# Reference: https://dev.mysql.com/doc/refman/8.0/en/innodb-parameters.html#sysvar_innodb_buffer_pool_size
MYSQL_INNODB_BUFFER_POOL_SIZE=512M
# InnoDB log file size
# Default is 128M
# Reference: https://dev.mysql.com/doc/refman/8.0/en/innodb-parameters.html#sysvar_innodb_log_file_size
MYSQL_INNODB_LOG_FILE_SIZE=128M
# InnoDB flush log at transaction commit
# Default is 2 (flush to OS cache, sync every second)
# Options: 0 (no flush), 1 (flush and sync), 2 (flush to OS cache)
# Reference: https://dev.mysql.com/doc/refman/8.0/en/innodb-parameters.html#sysvar_innodb_flush_log_at_trx_commit
MYSQL_INNODB_FLUSH_LOG_AT_TRX_COMMIT=2
# ------------------------------
# Redis Configuration
# This Redis configuration is used for caching and for pub/sub during conversation.
@@ -370,11 +402,11 @@ WEB_API_CORS_ALLOW_ORIGINS=*
# Specifies the allowed origins for cross-origin requests to the console API,
# e.g. https://cloud.dify.ai or * for all origins.
CONSOLE_CORS_ALLOW_ORIGINS=*
# Set COOKIE_DOMAIN when the console frontend and API are on different subdomains.
# Provide the registrable domain (e.g. example.com); leading dots are optional.
# When the frontend and backend run on different subdomains, set COOKIE_DOMAIN to the site’s top-level domain (e.g., `example.com`). Leading dots are optional.
COOKIE_DOMAIN=
# The frontend reads NEXT_PUBLIC_COOKIE_DOMAIN to align cookie handling with the API.
# When the frontend and backend run on different subdomains, set NEXT_PUBLIC_COOKIE_DOMAIN=1.
NEXT_PUBLIC_COOKIE_DOMAIN=
NEXT_PUBLIC_BATCH_CONCURRENCY=5
# ------------------------------
# File Storage Configuration
@@ -422,6 +454,15 @@ S3_SECRET_KEY=
# If set to false, the access key and secret key must be provided.
S3_USE_AWS_MANAGED_IAM=false
# Workflow run and Conversation archive storage (S3-compatible)
ARCHIVE_STORAGE_ENABLED=false
ARCHIVE_STORAGE_ENDPOINT=
ARCHIVE_STORAGE_ARCHIVE_BUCKET=
ARCHIVE_STORAGE_EXPORT_BUCKET=
ARCHIVE_STORAGE_ACCESS_KEY=
ARCHIVE_STORAGE_SECRET_KEY=
ARCHIVE_STORAGE_REGION=auto
# Azure Blob Configuration
#
AZURE_BLOB_ACCOUNT_NAME=difyai
@@ -444,6 +485,7 @@ ALIYUN_OSS_REGION=ap-southeast-1
ALIYUN_OSS_AUTH_VERSION=v4
# Don't start with '/'. OSS doesn't support leading slash in object names.
ALIYUN_OSS_PATH=your-path
ALIYUN_CLOUDBOX_ID=your-cloudbox-id
# Tencent COS Configuration
#
@@ -452,6 +494,7 @@ TENCENT_COS_SECRET_KEY=your-secret-key
TENCENT_COS_SECRET_ID=your-secret-id
TENCENT_COS_REGION=your-region
TENCENT_COS_SCHEME=your-scheme
TENCENT_COS_CUSTOM_DOMAIN=your-custom-domain
# Oracle Storage Configuration
#
@@ -467,6 +510,7 @@ HUAWEI_OBS_BUCKET_NAME=your-bucket-name
HUAWEI_OBS_SECRET_KEY=your-secret-key
HUAWEI_OBS_ACCESS_KEY=your-access-key
HUAWEI_OBS_SERVER=your-server-url
HUAWEI_OBS_PATH_STYLE=false
# Volcengine TOS Configuration
#
@@ -494,7 +538,7 @@ SUPABASE_URL=your-server-url
# ------------------------------
# The type of vector store to use.
# Supported values are `weaviate`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `pgvecto-rs`, `chroma`, `opensearch`, `oracle`, `tencent`, `elasticsearch`, `elasticsearch-ja`, `analyticdb`, `couchbase`, `vikingdb`, `oceanbase`, `opengauss`, `tablestore`,`vastbase`,`tidb`,`tidb_on_qdrant`,`baidu`,`lindorm`,`huawei_cloud`,`upstash`, `matrixone`, `clickzetta`, `alibabacloud_mysql`.
# Supported values are `weaviate`, `oceanbase`, `seekdb`, `qdrant`, `milvus`, `myscale`, `relyt`, `pgvector`, `pgvecto-rs`, `chroma`, `opensearch`, `oracle`, `tencent`, `elasticsearch`, `elasticsearch-ja`, `analyticdb`, `couchbase`, `vikingdb`, `opengauss`, `tablestore`, `vastbase`, `tidb`, `tidb_on_qdrant`, `baidu`, `lindorm`, `huawei_cloud`, `upstash`, `matrixone`, `clickzetta`, `alibabacloud_mysql`, `iris`.
VECTOR_STORE=weaviate
# Prefix used to create collection name in vector database
VECTOR_INDEX_NAME_PREFIX=Vector_index
@@ -503,6 +547,24 @@ VECTOR_INDEX_NAME_PREFIX=Vector_index
WEAVIATE_ENDPOINT=http://weaviate:8080
WEAVIATE_API_KEY=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
WEAVIATE_GRPC_ENDPOINT=grpc://weaviate:50051
WEAVIATE_TOKENIZATION=word
# For OceanBase metadata database configuration, available when `DB_TYPE` is `oceanbase`.
# For OceanBase vector database configuration, available when `VECTOR_STORE` is `oceanbase`
# If you want to use OceanBase as both vector database and metadata database, you need to set both `DB_TYPE` and `VECTOR_STORE` to `oceanbase`, and set Database Configuration is the same as the vector database.
# seekdb is the lite version of OceanBase and shares the connection configuration with OceanBase.
OCEANBASE_VECTOR_HOST=oceanbase
OCEANBASE_VECTOR_PORT=2881
OCEANBASE_VECTOR_USER=root@test
OCEANBASE_VECTOR_PASSWORD=difyai123456
OCEANBASE_VECTOR_DATABASE=test
OCEANBASE_CLUSTER_NAME=difyai
OCEANBASE_MEMORY_LIMIT=6G
OCEANBASE_ENABLE_HYBRID_SEARCH=false
# For OceanBase vector database, built-in fulltext parsers are `ngram`, `beng`, `space`, `ngram2`, `ik`
# For OceanBase vector database, external fulltext parsers (require plugin installation) are `japanese_ftparser`, `thai_ftparser`
OCEANBASE_FULLTEXT_PARSER=ik
SEEKDB_MEMORY_LIMIT=2G
# The Qdrant endpoint URL. Only available when VECTOR_STORE is `qdrant`.
QDRANT_URL=http://qdrant:6333
@@ -709,19 +771,6 @@ LINDORM_PASSWORD=admin
LINDORM_USING_UGC=True
LINDORM_QUERY_TIMEOUT=1
# OceanBase Vector configuration, only available when VECTOR_STORE is `oceanbase`
# Built-in fulltext parsers are `ngram`, `beng`, `space`, `ngram2`, `ik`
# External fulltext parsers (require plugin installation) are `japanese_ftparser`, `thai_ftparser`
OCEANBASE_VECTOR_HOST=oceanbase
OCEANBASE_VECTOR_PORT=2881
OCEANBASE_VECTOR_USER=root@test
OCEANBASE_VECTOR_PASSWORD=difyai123456
OCEANBASE_VECTOR_DATABASE=test
OCEANBASE_CLUSTER_NAME=difyai
OCEANBASE_MEMORY_LIMIT=6G
OCEANBASE_ENABLE_HYBRID_SEARCH=false
OCEANBASE_FULLTEXT_PARSER=ik
# opengauss configurations, only available when VECTOR_STORE is `opengauss`
OPENGAUSS_HOST=opengauss
OPENGAUSS_PORT=6600
@@ -763,6 +812,21 @@ CLICKZETTA_ANALYZER_TYPE=chinese
CLICKZETTA_ANALYZER_MODE=smart
CLICKZETTA_VECTOR_DISTANCE_FUNCTION=cosine_distance
# InterSystems IRIS configuration, only available when VECTOR_STORE is `iris`
IRIS_HOST=iris
IRIS_SUPER_SERVER_PORT=1972
IRIS_WEB_SERVER_PORT=52773
IRIS_USER=_SYSTEM
IRIS_PASSWORD=Dify@1234
IRIS_DATABASE=USER
IRIS_SCHEMA=dify
IRIS_CONNECTION_URL=
IRIS_MIN_CONNECTION=1
IRIS_MAX_CONNECTION=3
IRIS_TEXT_INDEX=true
IRIS_TEXT_INDEX_LANGUAGE=en
IRIS_TIMEZONE=UTC
# ------------------------------
# Knowledge Configuration
# ------------------------------
@@ -779,6 +843,19 @@ UPLOAD_FILE_BATCH_LIMIT=5
# Recommended: exe,bat,cmd,com,scr,vbs,ps1,msi,dll
UPLOAD_FILE_EXTENSION_BLACKLIST=
# Maximum number of files allowed in a single chunk attachment, default 10.
SINGLE_CHUNK_ATTACHMENT_LIMIT=10
# Maximum number of files allowed in a image batch upload operation
IMAGE_FILE_BATCH_LIMIT=10
# Maximum allowed image file size for attachments in megabytes, default 2.
ATTACHMENT_IMAGE_FILE_SIZE_LIMIT=2
# Timeout for downloading image attachments in seconds, default 60.
ATTACHMENT_IMAGE_DOWNLOAD_TIMEOUT=60
# ETL type, support: `dify`, `Unstructured`
# `dify` Dify's proprietary file extraction scheme
# `Unstructured` Unstructured.io file extraction scheme
@@ -896,6 +973,8 @@ SMTP_USERNAME=
SMTP_PASSWORD=
SMTP_USE_TLS=true
SMTP_OPPORTUNISTIC_TLS=false
# Optional: override the local hostname used for SMTP HELO/EHLO
SMTP_LOCAL_HOSTNAME=
# Sendgid configuration
SENDGRID_API_KEY=
@@ -965,18 +1044,26 @@ WORKFLOW_NODE_EXECUTION_STORAGE=rdbms
# Options:
# - core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository (default)
# - core.repositories.celery_workflow_execution_repository.CeleryWorkflowExecutionRepository
# - extensions.logstore.repositories.logstore_workflow_execution_repository.LogstoreWorkflowExecutionRepository
CORE_WORKFLOW_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository
# Core workflow node execution repository implementation
# Options:
# - core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository (default)
# - core.repositories.celery_workflow_node_execution_repository.CeleryWorkflowNodeExecutionRepository
# - extensions.logstore.repositories.logstore_workflow_node_execution_repository.LogstoreWorkflowNodeExecutionRepository
CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository
# API workflow run repository implementation
# Options:
# - repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository (default)
# - extensions.logstore.repositories.logstore_api_workflow_run_repository.LogstoreAPIWorkflowRunRepository
API_WORKFLOW_RUN_REPOSITORY=repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository
# API workflow node execution repository implementation
# Options:
# - repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository (default)
# - extensions.logstore.repositories.logstore_api_workflow_node_execution_repository.LogstoreAPIWorkflowNodeExecutionRepository
API_WORKFLOW_NODE_EXECUTION_REPOSITORY=repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository
# Workflow log cleanup configuration
@@ -987,6 +1074,29 @@ WORKFLOW_LOG_RETENTION_DAYS=30
# Batch size for workflow log cleanup operations (default: 100)
WORKFLOW_LOG_CLEANUP_BATCH_SIZE=100
# Aliyun SLS Logstore Configuration
# Aliyun Access Key ID
ALIYUN_SLS_ACCESS_KEY_ID=
# Aliyun Access Key Secret
ALIYUN_SLS_ACCESS_KEY_SECRET=
# Aliyun SLS Endpoint (e.g., cn-hangzhou.log.aliyuncs.com)
ALIYUN_SLS_ENDPOINT=
# Aliyun SLS Region (e.g., cn-hangzhou)
ALIYUN_SLS_REGION=
# Aliyun SLS Project Name
ALIYUN_SLS_PROJECT_NAME=
# Number of days to retain workflow run logs (default: 365 days， 3650 for permanent storage)
ALIYUN_SLS_LOGSTORE_TTL=365
# Enable dual-write to both SLS LogStore and SQL database (default: false)
LOGSTORE_DUAL_WRITE_ENABLED=false
# Enable dual-read fallback to SQL database when LogStore returns no results (default: true)
# Useful for migration scenarios where historical data exists only in SQL database
LOGSTORE_DUAL_READ_ENABLED=true
# Control flag for whether to write the `graph` field to LogStore.
# If LOGSTORE_ENABLE_PUT_GRAPH_FIELD is "true", write the full `graph` field;
# otherwise write an empty {} instead. Defaults to writing the `graph` field.
LOGSTORE_ENABLE_PUT_GRAPH_FIELD=true
# HTTP request node in workflow configuration
HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760
HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576
@@ -1045,18 +1155,14 @@ ALLOW_UNSAFE_DATA_SCHEME=false
MAX_TREE_DEPTH=50
# ------------------------------
# Environment Variables for db Service
# Environment Variables for database Service
# ------------------------------
# The name of the default postgres user.
POSTGRES_USER=${DB_USERNAME}
# The password for the default postgres user.
POSTGRES_PASSWORD=${DB_PASSWORD}
# The name of the default postgres database.
POSTGRES_DB=${DB_DATABASE}
# postgres data directory
# Postgres data directory
PGDATA=/var/lib/postgresql/data/pgdata
# MySQL Default Configuration
MYSQL_HOST_VOLUME=./volumes/mysql/data
# ------------------------------
# Environment Variables for sandbox Service
# ------------------------------
@@ -1090,6 +1196,10 @@ WEAVIATE_AUTHENTICATION_APIKEY_ALLOWED_KEYS=WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih
WEAVIATE_AUTHENTICATION_APIKEY_USERS=hello@dify.ai
WEAVIATE_AUTHORIZATION_ADMINLIST_ENABLED=true
WEAVIATE_AUTHORIZATION_ADMINLIST_USERS=hello@dify.ai
WEAVIATE_DISABLE_TELEMETRY=false
WEAVIATE_ENABLE_TOKENIZER_GSE=false
WEAVIATE_ENABLE_TOKENIZER_KAGOME_JA=false
WEAVIATE_ENABLE_TOKENIZER_KAGOME_KR=false
# ------------------------------
# Environment Variables for Chroma
@@ -1172,7 +1282,7 @@ NGINX_SSL_PORT=443
# and modify the env vars below accordingly.
NGINX_SSL_CERT_FILENAME=dify.crt
NGINX_SSL_CERT_KEY_FILENAME=dify.key
NGINX_SSL_PROTOCOLS=TLSv1.1 TLSv1.2 TLSv1.3
NGINX_SSL_PROTOCOLS=TLSv1.2 TLSv1.3
# Nginx performance tuning
NGINX_WORKER_PROCESSES=auto
@@ -1216,12 +1326,12 @@ SSRF_POOL_MAX_KEEPALIVE_CONNECTIONS=20
SSRF_POOL_KEEPALIVE_EXPIRY=5.0
# ------------------------------
# docker env var for specifying vector db type at startup
# (based on the vector db type, the corresponding docker
# docker env var for specifying vector db and metadata db type at startup
# (based on the vector db and metadata db type, the corresponding docker
# compose profile will be used)
# if you want to use unstructured, add ',unstructured' to the end
# ------------------------------
COMPOSE_PROFILES=${VECTOR_STORE:-weaviate}
COMPOSE_PROFILES=${VECTOR_STORE:-weaviate},${DB_TYPE:-postgresql}
# ------------------------------
# Docker Compose Service Expose Host Port Configurations
@@ -1293,7 +1403,10 @@ PLUGIN_STDIO_BUFFER_SIZE=1024
PLUGIN_STDIO_MAX_BUFFER_SIZE=5242880
PLUGIN_PYTHON_ENV_INIT_TIMEOUT=120
# Plugin Daemon side timeout (configure to match the API side below)
PLUGIN_MAX_EXECUTION_TIMEOUT=600
# API side timeout (configure to match the Plugin Daemon side above)
PLUGIN_DAEMON_TIMEOUT=600.0
# PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple
PIP_MIRROR_URL=
@@ -1364,7 +1477,7 @@ QUEUE_MONITOR_ALERT_EMAILS=
QUEUE_MONITOR_INTERVAL=30
# Swagger UI configuration
SWAGGER_UI_ENABLED=true
SWAGGER_UI_ENABLED=false
SWAGGER_UI_PATH=/swagger-ui.html
# Whether to encrypt dataset IDs when exporting DSL files (default: true)
@@ -1380,6 +1493,7 @@ ENABLE_CLEAN_UNUSED_DATASETS_TASK=false
ENABLE_CREATE_TIDB_SERVERLESS_TASK=false
ENABLE_UPDATE_TIDB_SERVERLESS_STATUS_TASK=false
ENABLE_CLEAN_MESSAGES=false
ENABLE_WORKFLOW_RUN_CLEANUP_TASK=false
ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK=false
ENABLE_DATASETS_QUEUE_MONITOR=false
ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK=true
@@ -1390,3 +1504,22 @@ WORKFLOW_SCHEDULE_MAX_DISPATCH_PER_TICK=0
# Tenant isolated task queue configuration
TENANT_ISOLATED_TASK_CONCURRENCY=1
# Maximum allowed CSV file size for annotation import in megabytes
ANNOTATION_IMPORT_FILE_SIZE_LIMIT=2
#Maximum number of annotation records allowed in a single import
ANNOTATION_IMPORT_MAX_RECORDS=10000
# Minimum number of annotation records required in a single import
ANNOTATION_IMPORT_MIN_RECORDS=1
ANNOTATION_IMPORT_RATE_LIMIT_PER_MINUTE=5
ANNOTATION_IMPORT_RATE_LIMIT_PER_HOUR=20
# Maximum number of concurrent annotation import tasks per tenant
ANNOTATION_IMPORT_MAX_CONCURRENT=5
# The API key of amplitude
AMPLITUDE_API_KEY=
# Sandbox expired records clean configuration
SANDBOX_EXPIRED_RECORDS_CLEAN_GRACEFUL_PERIOD=21
SANDBOX_EXPIRED_RECORDS_CLEAN_BATCH_SIZE=1000
SANDBOX_EXPIRED_RECORDS_RETENTION_DAYS=30