From 50a4a98821393d2e1f41b9810857864b4ff23d71 Mon Sep 17 00:00:00 2001 From: wangys <3401275564@qq.com> Date: Thu, 27 Nov 2025 16:17:05 +0800 Subject: [PATCH] =?UTF-8?q?dify=E6=9C=AC=E5=9C=B0=E9=83=A8=E7=BD=B2ollama?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- .gitignore | 3 +- docker/dify/.env | 1431 ++++++++++++++++++++++ docker/dify/.env.example | 3 + docker/dify/.gitignore | 28 - docker/dify/backup.sh | 48 - docker/dify/docker-compose-template.yaml | 16 +- docker/dify/docker-compose.yaml | 30 +- docker/dify/nginx/conf.d/default.conf | 58 + docker/dify/restore.sh | 76 -- docker/dify/version | 1 + 10 files changed, 1519 insertions(+), 175 deletions(-) create mode 100644 docker/dify/.env delete mode 100644 docker/dify/.gitignore delete mode 100755 docker/dify/backup.sh create mode 100644 docker/dify/nginx/conf.d/default.conf delete mode 100755 docker/dify/restore.sh create mode 100644 docker/dify/version diff --git a/.gitignore b/.gitignore index a0ae21b..bbbcc1a 100644 --- a/.gitignore +++ b/.gitignore @@ -4,4 +4,5 @@ build_output # Docker volumes（运行时数据，不纳入版本控制） docker/schoolNews/volumes/ docker/schoolNews/crawler -docker.zip \ No newline at end of file +docker.zip +docker/dify/volumes \ No newline at end of file diff --git a/docker/dify/.env b/docker/dify/.env new file mode 100644 index 0000000..09063a5 --- /dev/null +++ b/docker/dify/.env @@ -0,0 +1,1431 @@ +# ------------------------------ +# Environment Variables for API service & worker +# ------------------------------ + +# ------------------------------ +# Common Variables +# ------------------------------ + +# The backend URL of the console API, +# used to concatenate the authorization callback. +# If empty, it is the same domain. +# Example: https://api.console.dify.ai +CONSOLE_API_URL= + +# The front-end URL of the console web, +# used to concatenate some front-end addresses and for CORS configuration use. +# If empty, it is the same domain. +# Example: https://console.dify.ai +CONSOLE_WEB_URL= + +# Service API Url, +# used to display Service API Base Url to the front-end. +# If empty, it is the same domain. +# Example: https://api.dify.ai +SERVICE_API_URL= + +# Trigger external URL +# used to display trigger endpoint API Base URL to the front-end. +# Example: https://api.dify.ai +TRIGGER_URL=http://localhost + +# WebApp API backend Url, +# used to declare the back-end URL for the front-end API. +# If empty, it is the same domain. +# Example: https://api.app.dify.ai +APP_API_URL= + +# WebApp Url, +# used to display WebAPP API Base Url to the front-end. +# If empty, it is the same domain. +# Example: https://app.dify.ai +APP_WEB_URL= + +# File preview or download Url prefix. +# used to display File preview or download Url to the front-end or as Multi-model inputs; +# Url is signed and has expiration time. +# Setting FILES_URL is required for file processing plugins. +# - For https://example.com, use FILES_URL=https://example.com +# - For http://example.com, use FILES_URL=http://example.com +# Recommendation: use a dedicated domain (e.g., https://upload.example.com). +# Alternatively, use http://:5001 or http://api:5001, +# ensuring port 5001 is externally accessible (see docker-compose.yaml). +FILES_URL= + +# INTERNAL_FILES_URL is used for plugin daemon communication within Docker network. +# Set this to the internal Docker service URL for proper plugin file access. +# Example: INTERNAL_FILES_URL=http://api:5001 +INTERNAL_FILES_URL= + +# Ensure UTF-8 encoding +LANG=en_US.UTF-8 +LC_ALL=en_US.UTF-8 +PYTHONIOENCODING=utf-8 + +# ------------------------------ +# Server Configuration +# ------------------------------ + +# The log level for the application. +# Supported values are `DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL` +LOG_LEVEL=INFO +# Log file path +LOG_FILE=/app/logs/server.log +# Log file max size, the unit is MB +LOG_FILE_MAX_SIZE=20 +# Log file max backup count +LOG_FILE_BACKUP_COUNT=5 +# Log dateformat +LOG_DATEFORMAT=%Y-%m-%d %H:%M:%S +# Log Timezone +LOG_TZ=UTC + +# Debug mode, default is false. +# It is recommended to turn on this configuration for local development +# to prevent some problems caused by monkey patch. +DEBUG=false + +# Flask debug mode, it can output trace information at the interface when turned on, +# which is convenient for debugging. +FLASK_DEBUG=false + +# Enable request logging, which will log the request and response information. +# And the log level is DEBUG +ENABLE_REQUEST_LOGGING=False + +# A secret key that is used for securely signing the session cookie +# and encrypting sensitive information on the database. +# You can generate a strong key using `openssl rand -base64 42`. +SECRET_KEY=sk-9f73s3ljTXVcMT3Blb3ljTqtsKiGHXVcMT3BlbkFJLK7U + +# Password for admin user initialization. +# If left unset, admin user will not be prompted for a password +# when creating the initial admin account. +# The length of the password cannot exceed 30 characters. +INIT_PASSWORD= + +# Deployment environment. +# Supported values are `PRODUCTION`, `TESTING`. Default is `PRODUCTION`. +# Testing environment. There will be a distinct color label on the front-end page, +# indicating that this environment is a testing environment. +DEPLOY_ENV=PRODUCTION + +# Whether to enable the version check policy. +# If set to empty, https://updates.dify.ai will be called for version check. +CHECK_UPDATE_URL=https://updates.dify.ai + +# Used to change the OpenAI base address, default is https://api.openai.com/v1. +# When OpenAI cannot be accessed in China, replace it with a domestic mirror address, +# or when a local model provides OpenAI compatible API, it can be replaced. +OPENAI_API_BASE=https://api.openai.com/v1 + +# When enabled, migrations will be executed prior to application startup +# and the application will start after the migrations have completed. +MIGRATION_ENABLED=true + +# File Access Time specifies a time interval in seconds for the file to be accessed. +# The default value is 300 seconds. +FILES_ACCESS_TIMEOUT=300 + +# Access token expiration time in minutes +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 + +# ------------------------------ +# Container Startup Related Configuration +# Only effective when starting with docker image or docker-compose. +# ------------------------------ + +# API service binding address, default: 0.0.0.0, i.e., all addresses can be accessed. +DIFY_BIND_ADDRESS=0.0.0.0 + +# API service binding port number, default 5001. +DIFY_PORT=5001 + +# The number of API server workers, i.e., the number of workers. +# Formula: number of cpu cores x 2 + 1 for sync, 1 for Gevent +# Reference: https://docs.gunicorn.org/en/stable/design.html#how-many-workers +SERVER_WORKER_AMOUNT=1 + +# Defaults to gevent. If using windows, it can be switched to sync or solo. +# +# Warning: Changing this parameter requires disabling patching for +# psycopg2 and gRPC (see `gunicorn.conf.py` and `celery_entrypoint.py`). +# Modifying it may also decrease throughput. +# +# It is strongly discouraged to change this parameter. +SERVER_WORKER_CLASS=gevent + +# Default number of worker connections, the default is 10. +SERVER_WORKER_CONNECTIONS=10 + +# Similar to SERVER_WORKER_CLASS. +# If using windows, it can be switched to sync or solo. +# +# Warning: Changing this parameter requires disabling patching for +# psycopg2 and gRPC (see `gunicorn_conf.py` and `celery_entrypoint.py`). +# Modifying it may also decrease throughput. +# +# It is strongly discouraged to change this parameter. +CELERY_WORKER_CLASS= + +# Request handling timeout. The default is 200, +# it is recommended to set it to 360 to support a longer sse connection time. +GUNICORN_TIMEOUT=360 + +# The number of Celery workers. The default is 1, and can be set as needed. +CELERY_WORKER_AMOUNT= + +# Flag indicating whether to enable autoscaling of Celery workers. +# +# Autoscaling is useful when tasks are CPU intensive and can be dynamically +# allocated and deallocated based on the workload. +# +# When autoscaling is enabled, the maximum and minimum number of workers can +# be specified. The autoscaling algorithm will dynamically adjust the number +# of workers within the specified range. +# +# Default is false (i.e., autoscaling is disabled). +# +# Example: +# CELERY_AUTO_SCALE=true +CELERY_AUTO_SCALE=false + +# The maximum number of Celery workers that can be autoscaled. +# This is optional and only used when autoscaling is enabled. +# Default is not set. +CELERY_MAX_WORKERS= + +# The minimum number of Celery workers that can be autoscaled. +# This is optional and only used when autoscaling is enabled. +# Default is not set. +CELERY_MIN_WORKERS= + +# API Tool configuration +API_TOOL_DEFAULT_CONNECT_TIMEOUT=10 +API_TOOL_DEFAULT_READ_TIMEOUT=60 + +# ------------------------------- +# Datasource Configuration +# -------------------------------- +ENABLE_WEBSITE_JINAREADER=true +ENABLE_WEBSITE_FIRECRAWL=true +ENABLE_WEBSITE_WATERCRAWL=true + +# Enable inline LaTeX rendering with single dollar signs ($...$) in the web frontend +# Default is false for security reasons to prevent conflicts with regular text +NEXT_PUBLIC_ENABLE_SINGLE_DOLLAR_LATEX=false + +# ------------------------------ +# Database Configuration +# 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` and `mysql` +DB_TYPE=postgresql + +DB_USERNAME=postgres +DB_PASSWORD=difyai123456 +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 +# The default is 10 connections, which allows temporary overflow beyond the pool size. +SQLALCHEMY_MAX_OVERFLOW=10 +# Database connection pool recycling time, the default is 3600 seconds. +SQLALCHEMY_POOL_RECYCLE=3600 +# Whether to print SQL, default is false. +SQLALCHEMY_ECHO=false +# If True, will test connections for liveness upon each checkout +SQLALCHEMY_POOL_PRE_PING=false +# Whether to enable the Last in first out option or use default FIFO queue if is false +SQLALCHEMY_POOL_USE_LIFO=false +# Number of seconds to wait for a connection from the pool before raising a timeout error. +# Default is 30 +SQLALCHEMY_POOL_TIMEOUT=30 + +# Maximum number of connections to the database +# Default is 100 +# +# Reference: https://www.postgresql.org/docs/current/runtime-config-connection.html#GUC-MAX-CONNECTIONS +POSTGRES_MAX_CONNECTIONS=100 + +# Sets the amount of shared memory used for postgres's shared buffers. +# Default is 128MB +# Recommended value: 25% of available memory +# Reference: https://www.postgresql.org/docs/current/runtime-config-resource.html#GUC-SHARED-BUFFERS +POSTGRES_SHARED_BUFFERS=128MB + +# Sets the amount of memory used by each database worker for working space. +# Default is 4MB +# +# Reference: https://www.postgresql.org/docs/current/runtime-config-resource.html#GUC-WORK-MEM +POSTGRES_WORK_MEM=4MB + +# Sets the amount of memory reserved for maintenance activities. +# Default is 64MB +# +# Reference: https://www.postgresql.org/docs/current/runtime-config-resource.html#GUC-MAINTENANCE-WORK-MEM +POSTGRES_MAINTENANCE_WORK_MEM=64MB + +# Sets the planner's assumption about the effective cache size. +# Default is 4096MB +# +# Reference: https://www.postgresql.org/docs/current/runtime-config-query.html#GUC-EFFECTIVE-CACHE-SIZE +POSTGRES_EFFECTIVE_CACHE_SIZE=4096MB + +# Sets the maximum allowed duration of any statement before termination. +# Default is 0 (no timeout). +# +# Reference: https://www.postgresql.org/docs/current/runtime-config-client.html#GUC-STATEMENT-TIMEOUT +# A value of 0 prevents the server from timing out statements. +POSTGRES_STATEMENT_TIMEOUT=0 + +# Sets the maximum allowed duration of any idle in-transaction session before termination. +# Default is 0 (no timeout). +# +# Reference: https://www.postgresql.org/docs/current/runtime-config-client.html#GUC-IDLE-IN-TRANSACTION-SESSION-TIMEOUT +# 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. +# ------------------------------ + +REDIS_HOST=redis +REDIS_PORT=6379 +REDIS_USERNAME= +REDIS_PASSWORD=difyai123456 +REDIS_USE_SSL=false +# SSL configuration for Redis (when REDIS_USE_SSL=true) +REDIS_SSL_CERT_REQS=CERT_NONE +# Options: CERT_NONE, CERT_OPTIONAL, CERT_REQUIRED +REDIS_SSL_CA_CERTS= +# Path to CA certificate file for SSL verification +REDIS_SSL_CERTFILE= +# Path to client certificate file for SSL authentication +REDIS_SSL_KEYFILE= +# Path to client private key file for SSL authentication +REDIS_DB=0 + +# Whether to use Redis Sentinel mode. +# If set to true, the application will automatically discover and connect to the master node through Sentinel. +REDIS_USE_SENTINEL=false + +# List of Redis Sentinel nodes. If Sentinel mode is enabled, provide at least one Sentinel IP and port. +# Format: `:,:,:` +REDIS_SENTINELS= +REDIS_SENTINEL_SERVICE_NAME= +REDIS_SENTINEL_USERNAME= +REDIS_SENTINEL_PASSWORD= +REDIS_SENTINEL_SOCKET_TIMEOUT=0.1 + +# List of Redis Cluster nodes. If Cluster mode is enabled, provide at least one Cluster IP and port. +# Format: `:,:,:` +REDIS_USE_CLUSTERS=false +REDIS_CLUSTERS= +REDIS_CLUSTERS_PASSWORD= + +# ------------------------------ +# Celery Configuration +# ------------------------------ + +# Use standalone redis as the broker, and redis db 1 for celery broker. (redis_username is usually set by default as empty) +# Format as follows: `redis://:@:/`. +# Example: redis://:difyai123456@redis:6379/1 +# If use Redis Sentinel, format as follows: `sentinel://:@:/` +# For high availability, you can configure multiple Sentinel nodes (if provided) separated by semicolons like below example: +# Example: sentinel://:difyai123456@localhost:26379/1;sentinel://:difyai12345@localhost:26379/1;sentinel://:difyai12345@localhost:26379/1 +CELERY_BROKER_URL=redis://:difyai123456@redis:6379/1 +CELERY_BACKEND=redis +BROKER_USE_SSL=false + +# If you are using Redis Sentinel for high availability, configure the following settings. +CELERY_USE_SENTINEL=false +CELERY_SENTINEL_MASTER_NAME= +CELERY_SENTINEL_PASSWORD= +CELERY_SENTINEL_SOCKET_TIMEOUT=0.1 + +# ------------------------------ +# CORS Configuration +# Used to set the front-end cross-domain access policy. +# ------------------------------ + +# Specifies the allowed origins for cross-origin requests to the Web API, +# e.g. https://dify.app or * for all origins. +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=* +# 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= +# When the frontend and backend run on different subdomains, set NEXT_PUBLIC_COOKIE_DOMAIN=1. +NEXT_PUBLIC_COOKIE_DOMAIN= + +# ------------------------------ +# File Storage Configuration +# ------------------------------ + +# The type of storage to use for storing user files. +STORAGE_TYPE=opendal + +# Apache OpenDAL Configuration +# The configuration for OpenDAL consists of the following format: OPENDAL__. +# You can find all the service configurations (CONFIG_NAME) in the repository at: https://github.com/apache/opendal/tree/main/core/src/services. +# Dify will scan configurations starting with OPENDAL_ and automatically apply them. +# The scheme name for the OpenDAL storage. +OPENDAL_SCHEME=fs +# Configurations for OpenDAL Local File System. +OPENDAL_FS_ROOT=storage + +# ClickZetta Volume Configuration (for storage backend) +# To use ClickZetta Volume as storage backend, set STORAGE_TYPE=clickzetta-volume +# Note: ClickZetta Volume will reuse the existing CLICKZETTA_* connection parameters + +# Volume type selection (three types available): +# - user: Personal/small team use, simple config, user-level permissions +# - table: Enterprise multi-tenant, smart routing, table-level + user-level permissions +# - external: Data lake integration, external storage connection, volume-level + storage-level permissions +CLICKZETTA_VOLUME_TYPE=user + +# External Volume name (required only when TYPE=external) +CLICKZETTA_VOLUME_NAME= + +# Table Volume table prefix (used only when TYPE=table) +CLICKZETTA_VOLUME_TABLE_PREFIX=dataset_ + +# Dify file directory prefix (isolates from other apps, recommended to keep default) +CLICKZETTA_VOLUME_DIFY_PREFIX=dify_km + +# S3 Configuration +# +S3_ENDPOINT= +S3_REGION=us-east-1 +S3_BUCKET_NAME=difyai +S3_ACCESS_KEY= +S3_SECRET_KEY= +# Whether to use AWS managed IAM roles for authenticating with the S3 service. +# If set to false, the access key and secret key must be provided. +S3_USE_AWS_MANAGED_IAM=false + +# Azure Blob Configuration +# +AZURE_BLOB_ACCOUNT_NAME=difyai +AZURE_BLOB_ACCOUNT_KEY=difyai +AZURE_BLOB_CONTAINER_NAME=difyai-container +AZURE_BLOB_ACCOUNT_URL=https://.blob.core.windows.net + +# Google Storage Configuration +# +GOOGLE_STORAGE_BUCKET_NAME=your-bucket-name +GOOGLE_STORAGE_SERVICE_ACCOUNT_JSON_BASE64= + +# The Alibaba Cloud OSS configurations, +# +ALIYUN_OSS_BUCKET_NAME=your-bucket-name +ALIYUN_OSS_ACCESS_KEY=your-access-key +ALIYUN_OSS_SECRET_KEY=your-secret-key +ALIYUN_OSS_ENDPOINT=https://oss-ap-southeast-1-internal.aliyuncs.com +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 + +# Tencent COS Configuration +# +TENCENT_COS_BUCKET_NAME=your-bucket-name +TENCENT_COS_SECRET_KEY=your-secret-key +TENCENT_COS_SECRET_ID=your-secret-id +TENCENT_COS_REGION=your-region +TENCENT_COS_SCHEME=your-scheme + +# Oracle Storage Configuration +# +OCI_ENDPOINT=https://your-object-storage-namespace.compat.objectstorage.us-ashburn-1.oraclecloud.com +OCI_BUCKET_NAME=your-bucket-name +OCI_ACCESS_KEY=your-access-key +OCI_SECRET_KEY=your-secret-key +OCI_REGION=us-ashburn-1 + +# Huawei OBS Configuration +# +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 + +# Volcengine TOS Configuration +# +VOLCENGINE_TOS_BUCKET_NAME=your-bucket-name +VOLCENGINE_TOS_SECRET_KEY=your-secret-key +VOLCENGINE_TOS_ACCESS_KEY=your-access-key +VOLCENGINE_TOS_ENDPOINT=your-server-url +VOLCENGINE_TOS_REGION=your-region + +# Baidu OBS Storage Configuration +# +BAIDU_OBS_BUCKET_NAME=your-bucket-name +BAIDU_OBS_SECRET_KEY=your-secret-key +BAIDU_OBS_ACCESS_KEY=your-access-key +BAIDU_OBS_ENDPOINT=your-server-url + +# Supabase Storage Configuration +# +SUPABASE_BUCKET_NAME=your-bucket-name +SUPABASE_API_KEY=your-access-key +SUPABASE_URL=your-server-url + +# ------------------------------ +# Vector Database Configuration +# ------------------------------ + +# The type of vector store to use. +# Supported values are `weaviate`, `oceanbase`, `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`. +VECTOR_STORE=weaviate +# Prefix used to create collection name in vector database +VECTOR_INDEX_NAME_PREFIX=Vector_index + +# The Weaviate endpoint URL. Only available when VECTOR_STORE is `weaviate`. +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 `mysql` and `COMPOSE_PROFILES` includes `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 `DB_TYPE` to `mysql`, `COMPOSE_PROFILES` is `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 +QDRANT_API_KEY=difyai123456 +QDRANT_CLIENT_TIMEOUT=20 +QDRANT_GRPC_ENABLED=false +QDRANT_GRPC_PORT=6334 +QDRANT_REPLICATION_FACTOR=1 + +# Milvus configuration. Only available when VECTOR_STORE is `milvus`. +# The milvus uri. +MILVUS_URI=http://host.docker.internal:19530 +MILVUS_DATABASE= +MILVUS_TOKEN= +MILVUS_USER= +MILVUS_PASSWORD= +MILVUS_ENABLE_HYBRID_SEARCH=False +MILVUS_ANALYZER_PARAMS= + +# MyScale configuration, only available when VECTOR_STORE is `myscale` +# For multi-language support, please set MYSCALE_FTS_PARAMS with referring to: +# https://myscale.com/docs/en/text-search/#understanding-fts-index-parameters +MYSCALE_HOST=myscale +MYSCALE_PORT=8123 +MYSCALE_USER=default +MYSCALE_PASSWORD= +MYSCALE_DATABASE=dify +MYSCALE_FTS_PARAMS= + +# Couchbase configurations, only available when VECTOR_STORE is `couchbase` +# The connection string must include hostname defined in the docker-compose file (couchbase-server in this case) +COUCHBASE_CONNECTION_STRING=couchbase://couchbase-server +COUCHBASE_USER=Administrator +COUCHBASE_PASSWORD=password +COUCHBASE_BUCKET_NAME=Embeddings +COUCHBASE_SCOPE_NAME=_default + +# pgvector configurations, only available when VECTOR_STORE is `pgvector` +PGVECTOR_HOST=pgvector +PGVECTOR_PORT=5432 +PGVECTOR_USER=postgres +PGVECTOR_PASSWORD=difyai123456 +PGVECTOR_DATABASE=dify +PGVECTOR_MIN_CONNECTION=1 +PGVECTOR_MAX_CONNECTION=5 +PGVECTOR_PG_BIGM=false +PGVECTOR_PG_BIGM_VERSION=1.2-20240606 + +# vastbase configurations, only available when VECTOR_STORE is `vastbase` +VASTBASE_HOST=vastbase +VASTBASE_PORT=5432 +VASTBASE_USER=dify +VASTBASE_PASSWORD=Difyai123456 +VASTBASE_DATABASE=dify +VASTBASE_MIN_CONNECTION=1 +VASTBASE_MAX_CONNECTION=5 + +# pgvecto-rs configurations, only available when VECTOR_STORE is `pgvecto-rs` +PGVECTO_RS_HOST=pgvecto-rs +PGVECTO_RS_PORT=5432 +PGVECTO_RS_USER=postgres +PGVECTO_RS_PASSWORD=difyai123456 +PGVECTO_RS_DATABASE=dify + +# analyticdb configurations, only available when VECTOR_STORE is `analyticdb` +ANALYTICDB_KEY_ID=your-ak +ANALYTICDB_KEY_SECRET=your-sk +ANALYTICDB_REGION_ID=cn-hangzhou +ANALYTICDB_INSTANCE_ID=gp-ab123456 +ANALYTICDB_ACCOUNT=testaccount +ANALYTICDB_PASSWORD=testpassword +ANALYTICDB_NAMESPACE=dify +ANALYTICDB_NAMESPACE_PASSWORD=difypassword +ANALYTICDB_HOST=gp-test.aliyuncs.com +ANALYTICDB_PORT=5432 +ANALYTICDB_MIN_CONNECTION=1 +ANALYTICDB_MAX_CONNECTION=5 + +# TiDB vector configurations, only available when VECTOR_STORE is `tidb_vector` +TIDB_VECTOR_HOST=tidb +TIDB_VECTOR_PORT=4000 +TIDB_VECTOR_USER= +TIDB_VECTOR_PASSWORD= +TIDB_VECTOR_DATABASE=dify + +# Matrixone vector configurations. +MATRIXONE_HOST=matrixone +MATRIXONE_PORT=6001 +MATRIXONE_USER=dump +MATRIXONE_PASSWORD=111 +MATRIXONE_DATABASE=dify + +# Tidb on qdrant configuration, only available when VECTOR_STORE is `tidb_on_qdrant` +TIDB_ON_QDRANT_URL=http://127.0.0.1 +TIDB_ON_QDRANT_API_KEY=dify +TIDB_ON_QDRANT_CLIENT_TIMEOUT=20 +TIDB_ON_QDRANT_GRPC_ENABLED=false +TIDB_ON_QDRANT_GRPC_PORT=6334 +TIDB_PUBLIC_KEY=dify +TIDB_PRIVATE_KEY=dify +TIDB_API_URL=http://127.0.0.1 +TIDB_IAM_API_URL=http://127.0.0.1 +TIDB_REGION=regions/aws-us-east-1 +TIDB_PROJECT_ID=dify +TIDB_SPEND_LIMIT=100 + +# Chroma configuration, only available when VECTOR_STORE is `chroma` +CHROMA_HOST=127.0.0.1 +CHROMA_PORT=8000 +CHROMA_TENANT=default_tenant +CHROMA_DATABASE=default_database +CHROMA_AUTH_PROVIDER=chromadb.auth.token_authn.TokenAuthClientProvider +CHROMA_AUTH_CREDENTIALS= + +# Oracle configuration, only available when VECTOR_STORE is `oracle` +ORACLE_USER=dify +ORACLE_PASSWORD=dify +ORACLE_DSN=oracle:1521/FREEPDB1 +ORACLE_CONFIG_DIR=/app/api/storage/wallet +ORACLE_WALLET_LOCATION=/app/api/storage/wallet +ORACLE_WALLET_PASSWORD=dify +ORACLE_IS_AUTONOMOUS=false + +# AlibabaCloud MySQL configuration, only available when VECTOR_STORE is `alibabcloud_mysql` +ALIBABACLOUD_MYSQL_HOST=127.0.0.1 +ALIBABACLOUD_MYSQL_PORT=3306 +ALIBABACLOUD_MYSQL_USER=root +ALIBABACLOUD_MYSQL_PASSWORD=difyai123456 +ALIBABACLOUD_MYSQL_DATABASE=dify +ALIBABACLOUD_MYSQL_MAX_CONNECTION=5 +ALIBABACLOUD_MYSQL_HNSW_M=6 + +# relyt configurations, only available when VECTOR_STORE is `relyt` +RELYT_HOST=db +RELYT_PORT=5432 +RELYT_USER=postgres +RELYT_PASSWORD=difyai123456 +RELYT_DATABASE=postgres + +# open search configuration, only available when VECTOR_STORE is `opensearch` +OPENSEARCH_HOST=opensearch +OPENSEARCH_PORT=9200 +OPENSEARCH_SECURE=true +OPENSEARCH_VERIFY_CERTS=true +OPENSEARCH_AUTH_METHOD=basic +OPENSEARCH_USER=admin +OPENSEARCH_PASSWORD=admin +# If using AWS managed IAM, e.g. Managed Cluster or OpenSearch Serverless +OPENSEARCH_AWS_REGION=ap-southeast-1 +OPENSEARCH_AWS_SERVICE=aoss + +# tencent vector configurations, only available when VECTOR_STORE is `tencent` +TENCENT_VECTOR_DB_URL=http://127.0.0.1 +TENCENT_VECTOR_DB_API_KEY=dify +TENCENT_VECTOR_DB_TIMEOUT=30 +TENCENT_VECTOR_DB_USERNAME=dify +TENCENT_VECTOR_DB_DATABASE=dify +TENCENT_VECTOR_DB_SHARD=1 +TENCENT_VECTOR_DB_REPLICAS=2 +TENCENT_VECTOR_DB_ENABLE_HYBRID_SEARCH=false + +# ElasticSearch configuration, only available when VECTOR_STORE is `elasticsearch` +ELASTICSEARCH_HOST=0.0.0.0 +ELASTICSEARCH_PORT=9200 +ELASTICSEARCH_USERNAME=elastic +ELASTICSEARCH_PASSWORD=elastic +KIBANA_PORT=5601 + +# Using ElasticSearch Cloud Serverless, or not. +ELASTICSEARCH_USE_CLOUD=false +ELASTICSEARCH_CLOUD_URL=YOUR-ELASTICSEARCH_CLOUD_URL +ELASTICSEARCH_API_KEY=YOUR-ELASTICSEARCH_API_KEY + +ELASTICSEARCH_VERIFY_CERTS=False +ELASTICSEARCH_CA_CERTS= +ELASTICSEARCH_REQUEST_TIMEOUT=100000 +ELASTICSEARCH_RETRY_ON_TIMEOUT=True +ELASTICSEARCH_MAX_RETRIES=10 + +# baidu vector configurations, only available when VECTOR_STORE is `baidu` +BAIDU_VECTOR_DB_ENDPOINT=http://127.0.0.1:5287 +BAIDU_VECTOR_DB_CONNECTION_TIMEOUT_MS=30000 +BAIDU_VECTOR_DB_ACCOUNT=root +BAIDU_VECTOR_DB_API_KEY=dify +BAIDU_VECTOR_DB_DATABASE=dify +BAIDU_VECTOR_DB_SHARD=1 +BAIDU_VECTOR_DB_REPLICAS=3 +BAIDU_VECTOR_DB_INVERTED_INDEX_ANALYZER=DEFAULT_ANALYZER +BAIDU_VECTOR_DB_INVERTED_INDEX_PARSER_MODE=COARSE_MODE + +# VikingDB configurations, only available when VECTOR_STORE is `vikingdb` +VIKINGDB_ACCESS_KEY=your-ak +VIKINGDB_SECRET_KEY=your-sk +VIKINGDB_REGION=cn-shanghai +VIKINGDB_HOST=api-vikingdb.xxx.volces.com +VIKINGDB_SCHEMA=http +VIKINGDB_CONNECTION_TIMEOUT=30 +VIKINGDB_SOCKET_TIMEOUT=30 + +# Lindorm configuration, only available when VECTOR_STORE is `lindorm` +LINDORM_URL=http://localhost:30070 +LINDORM_USERNAME=admin +LINDORM_PASSWORD=admin +LINDORM_USING_UGC=True +LINDORM_QUERY_TIMEOUT=1 + +# opengauss configurations, only available when VECTOR_STORE is `opengauss` +OPENGAUSS_HOST=opengauss +OPENGAUSS_PORT=6600 +OPENGAUSS_USER=postgres +OPENGAUSS_PASSWORD=Dify@123 +OPENGAUSS_DATABASE=dify +OPENGAUSS_MIN_CONNECTION=1 +OPENGAUSS_MAX_CONNECTION=5 +OPENGAUSS_ENABLE_PQ=false + +# huawei cloud search service vector configurations, only available when VECTOR_STORE is `huawei_cloud` +HUAWEI_CLOUD_HOSTS=https://127.0.0.1:9200 +HUAWEI_CLOUD_USER=admin +HUAWEI_CLOUD_PASSWORD=admin + +# Upstash Vector configuration, only available when VECTOR_STORE is `upstash` +UPSTASH_VECTOR_URL=https://xxx-vector.upstash.io +UPSTASH_VECTOR_TOKEN=dify + +# TableStore Vector configuration +# (only used when VECTOR_STORE is tablestore) +TABLESTORE_ENDPOINT=https://instance-name.cn-hangzhou.ots.aliyuncs.com +TABLESTORE_INSTANCE_NAME=instance-name +TABLESTORE_ACCESS_KEY_ID=xxx +TABLESTORE_ACCESS_KEY_SECRET=xxx +TABLESTORE_NORMALIZE_FULLTEXT_BM25_SCORE=false + +# Clickzetta configuration, only available when VECTOR_STORE is `clickzetta` +CLICKZETTA_USERNAME= +CLICKZETTA_PASSWORD= +CLICKZETTA_INSTANCE= +CLICKZETTA_SERVICE=api.clickzetta.com +CLICKZETTA_WORKSPACE=quick_start +CLICKZETTA_VCLUSTER=default_ap +CLICKZETTA_SCHEMA=dify +CLICKZETTA_BATCH_SIZE=100 +CLICKZETTA_ENABLE_INVERTED_INDEX=true +CLICKZETTA_ANALYZER_TYPE=chinese +CLICKZETTA_ANALYZER_MODE=smart +CLICKZETTA_VECTOR_DISTANCE_FUNCTION=cosine_distance + +# ------------------------------ +# Knowledge Configuration +# ------------------------------ + +# Upload file size limit, default 15M. +UPLOAD_FILE_SIZE_LIMIT=15 + +# The maximum number of files that can be uploaded at a time, default 5. +UPLOAD_FILE_BATCH_LIMIT=5 + +# Comma-separated list of file extensions blocked from upload for security reasons. +# Extensions should be lowercase without dots (e.g., exe,bat,sh,dll). +# Empty by default to allow all file types. +# Recommended: exe,bat,cmd,com,scr,vbs,ps1,msi,dll +UPLOAD_FILE_EXTENSION_BLACKLIST= + +# ETL type, support: `dify`, `Unstructured` +# `dify` Dify's proprietary file extraction scheme +# `Unstructured` Unstructured.io file extraction scheme +ETL_TYPE=dify + +# Unstructured API path and API key, needs to be configured when ETL_TYPE is Unstructured +# Or using Unstructured for document extractor node for pptx. +# For example: http://unstructured:8000/general/v0/general +UNSTRUCTURED_API_URL= +UNSTRUCTURED_API_KEY= +SCARF_NO_ANALYTICS=true + +# ------------------------------ +# Model Configuration +# ------------------------------ + +# The maximum number of tokens allowed for prompt generation. +# This setting controls the upper limit of tokens that can be used by the LLM +# when generating a prompt in the prompt generation tool. +# Default: 512 tokens. +PROMPT_GENERATION_MAX_TOKENS=512 + +# The maximum number of tokens allowed for code generation. +# This setting controls the upper limit of tokens that can be used by the LLM +# when generating code in the code generation tool. +# Default: 1024 tokens. +CODE_GENERATION_MAX_TOKENS=1024 + +# Enable or disable plugin based token counting. If disabled, token counting will return 0. +# This can improve performance by skipping token counting operations. +# Default: false (disabled). +PLUGIN_BASED_TOKEN_COUNTING_ENABLED=false + +# ------------------------------ +# Multi-modal Configuration +# ------------------------------ + +# The format of the image/video/audio/document sent when the multi-modal model is input, +# the default is base64, optional url. +# The delay of the call in url mode will be lower than that in base64 mode. +# It is generally recommended to use the more compatible base64 mode. +# If configured as url, you need to configure FILES_URL as an externally accessible address so that the multi-modal model can access the image/video/audio/document. +MULTIMODAL_SEND_FORMAT=base64 +# Upload image file size limit, default 10M. +UPLOAD_IMAGE_FILE_SIZE_LIMIT=10 +# Upload video file size limit, default 100M. +UPLOAD_VIDEO_FILE_SIZE_LIMIT=100 +# Upload audio file size limit, default 50M. +UPLOAD_AUDIO_FILE_SIZE_LIMIT=50 + +# ------------------------------ +# Sentry Configuration +# Used for application monitoring and error log tracking. +# ------------------------------ +SENTRY_DSN= + +# API Service Sentry DSN address, default is empty, when empty, +# all monitoring information is not reported to Sentry. +# If not set, Sentry error reporting will be disabled. +API_SENTRY_DSN= +# API Service The reporting ratio of Sentry events, if it is 0.01, it is 1%. +API_SENTRY_TRACES_SAMPLE_RATE=1.0 +# API Service The reporting ratio of Sentry profiles, if it is 0.01, it is 1%. +API_SENTRY_PROFILES_SAMPLE_RATE=1.0 + +# Web Service Sentry DSN address, default is empty, when empty, +# all monitoring information is not reported to Sentry. +# If not set, Sentry error reporting will be disabled. +WEB_SENTRY_DSN= + +# Plugin_daemon Service Sentry DSN address, default is empty, when empty, +# all monitoring information is not reported to Sentry. +# If not set, Sentry error reporting will be disabled. +PLUGIN_SENTRY_ENABLED=false +PLUGIN_SENTRY_DSN= + +# ------------------------------ +# Notion Integration Configuration +# Variables can be obtained by applying for Notion integration: https://www.notion.so/my-integrations +# ------------------------------ + +# Configure as "public" or "internal". +# Since Notion's OAuth redirect URL only supports HTTPS, +# if deploying locally, please use Notion's internal integration. +NOTION_INTEGRATION_TYPE=public +# Notion OAuth client secret (used for public integration type) +NOTION_CLIENT_SECRET= +# Notion OAuth client id (used for public integration type) +NOTION_CLIENT_ID= +# Notion internal integration secret. +# If the value of NOTION_INTEGRATION_TYPE is "internal", +# you need to configure this variable. +NOTION_INTERNAL_SECRET= + +# ------------------------------ +# Mail related configuration +# ------------------------------ + +# Mail type, support: resend, smtp, sendgrid +MAIL_TYPE=resend + +# Default send from email address, if not specified +# If using SendGrid, use the 'from' field for authentication if necessary. +MAIL_DEFAULT_SEND_FROM= + +# API-Key for the Resend email provider, used when MAIL_TYPE is `resend`. +RESEND_API_URL=https://api.resend.com +RESEND_API_KEY=your-resend-api-key + + +# SMTP server configuration, used when MAIL_TYPE is `smtp` +SMTP_SERVER= +SMTP_PORT=465 +SMTP_USERNAME= +SMTP_PASSWORD= +SMTP_USE_TLS=true +SMTP_OPPORTUNISTIC_TLS=false + +# Sendgid configuration +SENDGRID_API_KEY= + +# ------------------------------ +# Others Configuration +# ------------------------------ + +# Maximum length of segmentation tokens for indexing +INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=4000 + +# Member invitation link valid time (hours), +# Default: 72. +INVITE_EXPIRY_HOURS=72 + +# Reset password token valid time (minutes), +RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5 +EMAIL_REGISTER_TOKEN_EXPIRY_MINUTES=5 +CHANGE_EMAIL_TOKEN_EXPIRY_MINUTES=5 +OWNER_TRANSFER_TOKEN_EXPIRY_MINUTES=5 + +# The sandbox service endpoint. +CODE_EXECUTION_ENDPOINT=http://sandbox:8194 +CODE_EXECUTION_API_KEY=dify-sandbox +CODE_EXECUTION_SSL_VERIFY=True +CODE_EXECUTION_POOL_MAX_CONNECTIONS=100 +CODE_EXECUTION_POOL_MAX_KEEPALIVE_CONNECTIONS=20 +CODE_EXECUTION_POOL_KEEPALIVE_EXPIRY=5.0 +CODE_MAX_NUMBER=9223372036854775807 +CODE_MIN_NUMBER=-9223372036854775808 +CODE_MAX_DEPTH=5 +CODE_MAX_PRECISION=20 +CODE_MAX_STRING_LENGTH=400000 +CODE_MAX_STRING_ARRAY_LENGTH=30 +CODE_MAX_OBJECT_ARRAY_LENGTH=30 +CODE_MAX_NUMBER_ARRAY_LENGTH=1000 +CODE_EXECUTION_CONNECT_TIMEOUT=10 +CODE_EXECUTION_READ_TIMEOUT=60 +CODE_EXECUTION_WRITE_TIMEOUT=10 +TEMPLATE_TRANSFORM_MAX_LENGTH=400000 + +# Workflow runtime configuration +WORKFLOW_MAX_EXECUTION_STEPS=500 +WORKFLOW_MAX_EXECUTION_TIME=1200 +WORKFLOW_CALL_MAX_DEPTH=5 +MAX_VARIABLE_SIZE=204800 +WORKFLOW_FILE_UPLOAD_LIMIT=10 + +# GraphEngine Worker Pool Configuration +# Minimum number of workers per GraphEngine instance (default: 1) +GRAPH_ENGINE_MIN_WORKERS=1 +# Maximum number of workers per GraphEngine instance (default: 10) +GRAPH_ENGINE_MAX_WORKERS=10 +# Queue depth threshold that triggers worker scale up (default: 3) +GRAPH_ENGINE_SCALE_UP_THRESHOLD=3 +# Seconds of idle time before scaling down workers (default: 5.0) +GRAPH_ENGINE_SCALE_DOWN_IDLE_TIME=5.0 + +# Workflow storage configuration +# Options: rdbms, hybrid +# rdbms: Use only the relational database (default) +# hybrid: Save new data to object storage, read from both object storage and RDBMS +WORKFLOW_NODE_EXECUTION_STORAGE=rdbms + +# Repository configuration +# Core workflow execution repository implementation +# Options: +# - core.repositories.sqlalchemy_workflow_execution_repository.SQLAlchemyWorkflowExecutionRepository (default) +# - core.repositories.celery_workflow_execution_repository.CeleryWorkflowExecutionRepository +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 +CORE_WORKFLOW_NODE_EXECUTION_REPOSITORY=core.repositories.sqlalchemy_workflow_node_execution_repository.SQLAlchemyWorkflowNodeExecutionRepository + +# API workflow run repository implementation +API_WORKFLOW_RUN_REPOSITORY=repositories.sqlalchemy_api_workflow_run_repository.DifyAPISQLAlchemyWorkflowRunRepository + +# API workflow node execution repository implementation +API_WORKFLOW_NODE_EXECUTION_REPOSITORY=repositories.sqlalchemy_api_workflow_node_execution_repository.DifyAPISQLAlchemyWorkflowNodeExecutionRepository + +# Workflow log cleanup configuration +# Enable automatic cleanup of workflow run logs to manage database size +WORKFLOW_LOG_CLEANUP_ENABLED=false +# Number of days to retain workflow run logs (default: 30 days) +WORKFLOW_LOG_RETENTION_DAYS=30 +# Batch size for workflow log cleanup operations (default: 100) +WORKFLOW_LOG_CLEANUP_BATCH_SIZE=100 + +# HTTP request node in workflow configuration +HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760 +HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576 +HTTP_REQUEST_NODE_SSL_VERIFY=True + +# HTTP request node timeout configuration +# Maximum timeout values (in seconds) that users can set in HTTP request nodes +# - Connect timeout: Time to wait for establishing connection (default: 10s) +# - Read timeout: Time to wait for receiving response data (default: 600s, 10 minutes) +# - Write timeout: Time to wait for sending request data (default: 600s, 10 minutes) +HTTP_REQUEST_MAX_CONNECT_TIMEOUT=10 +HTTP_REQUEST_MAX_READ_TIMEOUT=600 +HTTP_REQUEST_MAX_WRITE_TIMEOUT=600 + +# Base64 encoded CA certificate data for custom certificate verification (PEM format, optional) +# HTTP_REQUEST_NODE_SSL_CERT_DATA=LS0tLS1CRUdJTi... +# Base64 encoded client certificate data for mutual TLS authentication (PEM format, optional) +# HTTP_REQUEST_NODE_SSL_CLIENT_CERT_DATA=LS0tLS1CRUdJTi... +# Base64 encoded client private key data for mutual TLS authentication (PEM format, optional) +# HTTP_REQUEST_NODE_SSL_CLIENT_KEY_DATA=LS0tLS1CRUdJTi... + +# Webhook request configuration +WEBHOOK_REQUEST_BODY_MAX_SIZE=10485760 + +# Respect X-* headers to redirect clients +RESPECT_XFORWARD_HEADERS_ENABLED=false + +# SSRF Proxy server HTTP URL +SSRF_PROXY_HTTP_URL=http://ssrf_proxy:3128 +# SSRF Proxy server HTTPS URL +SSRF_PROXY_HTTPS_URL=http://ssrf_proxy:3128 + +# Maximum loop count in the workflow +LOOP_NODE_MAX_COUNT=100 + +# The maximum number of tools that can be used in the agent. +MAX_TOOLS_NUM=10 + +# Maximum number of Parallelism branches in the workflow +MAX_PARALLEL_LIMIT=10 + +# The maximum number of iterations for agent setting +MAX_ITERATIONS_NUM=99 + +# ------------------------------ +# Environment Variables for web Service +# ------------------------------ + +# The timeout for the text generation in millisecond +TEXT_GENERATION_TIMEOUT_MS=60000 + +# Allow rendering unsafe URLs which have "data:" scheme. +ALLOW_UNSAFE_DATA_SCHEME=false + +# Maximum number of tree depth in the workflow +MAX_TREE_DEPTH=50 + +# ------------------------------ +# 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=${DB_DATABASE} +# Postgres data directory +PGDATA=/var/lib/postgresql/data/pgdata + +# MySQL Default Configuration +# The name of the default mysql user. +MYSQL_USERNAME=${DB_USERNAME} +# The password for the default mysql user. +MYSQL_PASSWORD=${DB_PASSWORD} +# The name of the default mysql database. +MYSQL_DATABASE=${DB_DATABASE} +# MySQL data directory +MYSQL_HOST_VOLUME=./volumes/mysql/data + +# ------------------------------ +# Environment Variables for sandbox Service +# ------------------------------ + +# The API key for the sandbox service +SANDBOX_API_KEY=dify-sandbox +# The mode in which the Gin framework runs +SANDBOX_GIN_MODE=release +# The timeout for the worker in seconds +SANDBOX_WORKER_TIMEOUT=15 +# Enable network for the sandbox service +SANDBOX_ENABLE_NETWORK=true +# HTTP proxy URL for SSRF protection +SANDBOX_HTTP_PROXY=http://ssrf_proxy:3128 +# HTTPS proxy URL for SSRF protection +SANDBOX_HTTPS_PROXY=http://ssrf_proxy:3128 +# The port on which the sandbox service runs +SANDBOX_PORT=8194 + +# ------------------------------ +# Environment Variables for weaviate Service +# (only used when VECTOR_STORE is weaviate) +# ------------------------------ +WEAVIATE_PERSISTENCE_DATA_PATH=/var/lib/weaviate +WEAVIATE_QUERY_DEFAULTS_LIMIT=25 +WEAVIATE_AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=true +WEAVIATE_DEFAULT_VECTORIZER_MODULE=none +WEAVIATE_CLUSTER_HOSTNAME=node1 +WEAVIATE_AUTHENTICATION_APIKEY_ENABLED=true +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 + +# ------------------------------ +# Environment Variables for Chroma +# (only used when VECTOR_STORE is chroma) +# ------------------------------ + +# Authentication credentials for Chroma server +CHROMA_SERVER_AUTHN_CREDENTIALS=difyai123456 +# Authentication provider for Chroma server +CHROMA_SERVER_AUTHN_PROVIDER=chromadb.auth.token_authn.TokenAuthenticationServerProvider +# Persistence setting for Chroma server +CHROMA_IS_PERSISTENT=TRUE + +# ------------------------------ +# Environment Variables for Oracle Service +# (only used when VECTOR_STORE is oracle) +# ------------------------------ +ORACLE_PWD=Dify123456 +ORACLE_CHARACTERSET=AL32UTF8 + +# ------------------------------ +# Environment Variables for milvus Service +# (only used when VECTOR_STORE is milvus) +# ------------------------------ +# ETCD configuration for auto compaction mode +ETCD_AUTO_COMPACTION_MODE=revision +# ETCD configuration for auto compaction retention in terms of number of revisions +ETCD_AUTO_COMPACTION_RETENTION=1000 +# ETCD configuration for backend quota in bytes +ETCD_QUOTA_BACKEND_BYTES=4294967296 +# ETCD configuration for the number of changes before triggering a snapshot +ETCD_SNAPSHOT_COUNT=50000 +# MinIO access key for authentication +MINIO_ACCESS_KEY=minioadmin +# MinIO secret key for authentication +MINIO_SECRET_KEY=minioadmin +# ETCD service endpoints +ETCD_ENDPOINTS=etcd:2379 +# MinIO service address +MINIO_ADDRESS=minio:9000 +# Enable or disable security authorization +MILVUS_AUTHORIZATION_ENABLED=true + +# ------------------------------ +# Environment Variables for pgvector / pgvector-rs Service +# (only used when VECTOR_STORE is pgvector / pgvector-rs) +# ------------------------------ +PGVECTOR_PGUSER=postgres +# The password for the default postgres user. +PGVECTOR_POSTGRES_PASSWORD=difyai123456 +# The name of the default postgres database. +PGVECTOR_POSTGRES_DB=dify +# postgres data directory +PGVECTOR_PGDATA=/var/lib/postgresql/data/pgdata + +# ------------------------------ +# Environment Variables for opensearch +# (only used when VECTOR_STORE is opensearch) +# ------------------------------ +OPENSEARCH_DISCOVERY_TYPE=single-node +OPENSEARCH_BOOTSTRAP_MEMORY_LOCK=true +OPENSEARCH_JAVA_OPTS_MIN=512m +OPENSEARCH_JAVA_OPTS_MAX=1024m +OPENSEARCH_INITIAL_ADMIN_PASSWORD=Qazwsxedc!@#123 +OPENSEARCH_MEMLOCK_SOFT=-1 +OPENSEARCH_MEMLOCK_HARD=-1 +OPENSEARCH_NOFILE_SOFT=65536 +OPENSEARCH_NOFILE_HARD=65536 + +# ------------------------------ +# Environment Variables for Nginx reverse proxy +# ------------------------------ +NGINX_SERVER_NAME=_ +NGINX_HTTPS_ENABLED=false +# HTTP port +NGINX_PORT=80 +# SSL settings are only applied when HTTPS_ENABLED is true +NGINX_SSL_PORT=443 +# if HTTPS_ENABLED is true, you're required to add your own SSL certificates/keys to the `./nginx/ssl` directory +# 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 performance tuning +NGINX_WORKER_PROCESSES=auto +NGINX_CLIENT_MAX_BODY_SIZE=100M +NGINX_KEEPALIVE_TIMEOUT=65 + +# Proxy settings +NGINX_PROXY_READ_TIMEOUT=3600s +NGINX_PROXY_SEND_TIMEOUT=3600s + +# Set true to accept requests for /.well-known/acme-challenge/ +NGINX_ENABLE_CERTBOT_CHALLENGE=false + +# ------------------------------ +# Certbot Configuration +# ------------------------------ + +# Email address (required to get certificates from Let's Encrypt) +CERTBOT_EMAIL=your_email@example.com + +# Domain name +CERTBOT_DOMAIN=your_domain.com + +# certbot command options +# i.e: --force-renewal --dry-run --test-cert --debug +CERTBOT_OPTIONS= + +# ------------------------------ +# Environment Variables for SSRF Proxy +# ------------------------------ +SSRF_HTTP_PORT=3128 +SSRF_COREDUMP_DIR=/var/spool/squid +SSRF_REVERSE_PROXY_PORT=8194 +SSRF_SANDBOX_HOST=sandbox +SSRF_DEFAULT_TIME_OUT=5 +SSRF_DEFAULT_CONNECT_TIME_OUT=5 +SSRF_DEFAULT_READ_TIME_OUT=5 +SSRF_DEFAULT_WRITE_TIME_OUT=5 +SSRF_POOL_MAX_CONNECTIONS=100 +SSRF_POOL_MAX_KEEPALIVE_CONNECTIONS=20 +SSRF_POOL_KEEPALIVE_EXPIRY=5.0 + +# ------------------------------ +# 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=${VECTOR_STORE:-weaviate},${DB_TYPE:-postgresql} + +# ------------------------------ +# Docker Compose Service Expose Host Port Configurations +# ------------------------------ +EXPOSE_NGINX_PORT=80 +EXPOSE_NGINX_SSL_PORT=443 + +# ---------------------------------------------------------------------------- +# ModelProvider & Tool Position Configuration +# Used to specify the model providers and tools that can be used in the app. +# ---------------------------------------------------------------------------- + +# Pin, include, and exclude tools +# Use comma-separated values with no spaces between items. +# Example: POSITION_TOOL_PINS=bing,google +POSITION_TOOL_PINS= +POSITION_TOOL_INCLUDES= +POSITION_TOOL_EXCLUDES= + +# Pin, include, and exclude model providers +# Use comma-separated values with no spaces between items. +# Example: POSITION_PROVIDER_PINS=openai,openllm +POSITION_PROVIDER_PINS= +POSITION_PROVIDER_INCLUDES= +POSITION_PROVIDER_EXCLUDES= + +# CSP https://developer.mozilla.org/en-US/docs/Web/HTTP/CSP +CSP_WHITELIST= + +# Enable or disable create tidb service job +CREATE_TIDB_SERVICE_JOB_ENABLED=false + +# Maximum number of submitted thread count in a ThreadPool for parallel node execution +MAX_SUBMIT_COUNT=100 + +# The maximum number of top-k value for RAG. +TOP_K_MAX_VALUE=10 + +# ------------------------------ +# Plugin Daemon Configuration +# ------------------------------ + +DB_PLUGIN_DATABASE=dify_plugin +EXPOSE_PLUGIN_DAEMON_PORT=5002 +PLUGIN_DAEMON_PORT=5002 +PLUGIN_DAEMON_KEY=lYkiYYT6owG+71oLerGzA7GXCgOT++6ovaezWAjpCjf+Sjc3ZtU+qUEi +PLUGIN_DAEMON_URL=http://plugin_daemon:5002 +PLUGIN_MAX_PACKAGE_SIZE=52428800 +PLUGIN_PPROF_ENABLED=false + +PLUGIN_DEBUGGING_HOST=0.0.0.0 +PLUGIN_DEBUGGING_PORT=5003 +EXPOSE_PLUGIN_DEBUGGING_HOST=localhost +EXPOSE_PLUGIN_DEBUGGING_PORT=5003 + +# If this key is changed, DIFY_INNER_API_KEY in plugin_daemon service must also be updated or agent node will fail. +PLUGIN_DIFY_INNER_API_KEY=QaHbTe77CtuXmsfyhR7+vRjI/+XbV1AaFy691iy+kGDv2Jvy0/eAh8Y1 +PLUGIN_DIFY_INNER_API_URL=http://api:5001 + +ENDPOINT_URL_TEMPLATE=http://localhost/e/{hook_id} + +MARKETPLACE_ENABLED=true +MARKETPLACE_API_URL=https://marketplace.dify.ai + +FORCE_VERIFYING_SIGNATURE=true +ENFORCE_LANGGENIUS_PLUGIN_SIGNATURES=true + +PLUGIN_STDIO_BUFFER_SIZE=1024 +PLUGIN_STDIO_MAX_BUFFER_SIZE=5242880 + +PLUGIN_PYTHON_ENV_INIT_TIMEOUT=120 +PLUGIN_MAX_EXECUTION_TIMEOUT=600 +# PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple +PIP_MIRROR_URL=https://pypi.tuna.tsinghua.edu.cn/simple + +# https://github.com/langgenius/dify-plugin-daemon/blob/main/.env.example +# Plugin storage type, local aws_s3 tencent_cos azure_blob aliyun_oss volcengine_tos +PLUGIN_STORAGE_TYPE=local +PLUGIN_STORAGE_LOCAL_ROOT=/app/storage +PLUGIN_WORKING_PATH=/app/storage/cwd +PLUGIN_INSTALLED_PATH=plugin +PLUGIN_PACKAGE_CACHE_PATH=plugin_packages +PLUGIN_MEDIA_CACHE_PATH=assets +# Plugin oss bucket +PLUGIN_STORAGE_OSS_BUCKET= +# Plugin oss s3 credentials +PLUGIN_S3_USE_AWS=false +PLUGIN_S3_USE_AWS_MANAGED_IAM=false +PLUGIN_S3_ENDPOINT= +PLUGIN_S3_USE_PATH_STYLE=false +PLUGIN_AWS_ACCESS_KEY= +PLUGIN_AWS_SECRET_KEY= +PLUGIN_AWS_REGION= +# Plugin oss azure blob +PLUGIN_AZURE_BLOB_STORAGE_CONTAINER_NAME= +PLUGIN_AZURE_BLOB_STORAGE_CONNECTION_STRING= +# Plugin oss tencent cos +PLUGIN_TENCENT_COS_SECRET_KEY= +PLUGIN_TENCENT_COS_SECRET_ID= +PLUGIN_TENCENT_COS_REGION= +# Plugin oss aliyun oss +PLUGIN_ALIYUN_OSS_REGION= +PLUGIN_ALIYUN_OSS_ENDPOINT= +PLUGIN_ALIYUN_OSS_ACCESS_KEY_ID= +PLUGIN_ALIYUN_OSS_ACCESS_KEY_SECRET= +PLUGIN_ALIYUN_OSS_AUTH_VERSION=v4 +PLUGIN_ALIYUN_OSS_PATH= +# Plugin oss volcengine tos +PLUGIN_VOLCENGINE_TOS_ENDPOINT= +PLUGIN_VOLCENGINE_TOS_ACCESS_KEY= +PLUGIN_VOLCENGINE_TOS_SECRET_KEY= +PLUGIN_VOLCENGINE_TOS_REGION= + +# ------------------------------ +# OTLP Collector Configuration +# ------------------------------ +ENABLE_OTEL=false +OTLP_TRACE_ENDPOINT= +OTLP_METRIC_ENDPOINT= +OTLP_BASE_ENDPOINT=http://localhost:4318 +OTLP_API_KEY= +OTEL_EXPORTER_OTLP_PROTOCOL= +OTEL_EXPORTER_TYPE=otlp +OTEL_SAMPLING_RATE=0.1 +OTEL_BATCH_EXPORT_SCHEDULE_DELAY=5000 +OTEL_MAX_QUEUE_SIZE=2048 +OTEL_MAX_EXPORT_BATCH_SIZE=512 +OTEL_METRIC_EXPORT_INTERVAL=60000 +OTEL_BATCH_EXPORT_TIMEOUT=10000 +OTEL_METRIC_EXPORT_TIMEOUT=30000 + +# Prevent Clickjacking +ALLOW_EMBED=false + +# Dataset queue monitor configuration +QUEUE_MONITOR_THRESHOLD=200 +# You can configure multiple ones, separated by commas. eg: test1@dify.ai,test2@dify.ai +QUEUE_MONITOR_ALERT_EMAILS= +# Monitor interval in minutes, default is 30 minutes +QUEUE_MONITOR_INTERVAL=30 + +# Swagger UI configuration +SWAGGER_UI_ENABLED=true +SWAGGER_UI_PATH=/swagger-ui.html + +# Whether to encrypt dataset IDs when exporting DSL files (default: true) +# Set to false to export dataset IDs as plain text for easier cross-environment import +DSL_EXPORT_ENCRYPT_DATASET_ID=true + +# Maximum number of segments for dataset segments API (0 for unlimited) +DATASET_MAX_SEGMENTS_PER_REQUEST=0 + +# Celery schedule tasks configuration +ENABLE_CLEAN_EMBEDDING_CACHE_TASK=false +ENABLE_CLEAN_UNUSED_DATASETS_TASK=false +ENABLE_CREATE_TIDB_SERVERLESS_TASK=false +ENABLE_UPDATE_TIDB_SERVERLESS_STATUS_TASK=false +ENABLE_CLEAN_MESSAGES=false +ENABLE_MAIL_CLEAN_DOCUMENT_NOTIFY_TASK=false +ENABLE_DATASETS_QUEUE_MONITOR=false +ENABLE_CHECK_UPGRADABLE_PLUGIN_TASK=true +ENABLE_WORKFLOW_SCHEDULE_POLLER_TASK=true +WORKFLOW_SCHEDULE_POLLER_INTERVAL=1 +WORKFLOW_SCHEDULE_POLLER_BATCH_SIZE=100 +WORKFLOW_SCHEDULE_MAX_DISPATCH_PER_TICK=0 + +# Tenant isolated task queue configuration +TENANT_ISOLATED_TASK_CONCURRENCY=1 \ No newline at end of file diff --git a/docker/dify/.env.example b/docker/dify/.env.example index 7e2e9aa..c9981ba 100644 --- a/docker/dify/.env.example +++ b/docker/dify/.env.example @@ -133,6 +133,8 @@ 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 @@ -525,6 +527,7 @@ 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 `mysql` and `COMPOSE_PROFILES` includes `oceanbase`. # For OceanBase vector database configuration, available when `VECTOR_STORE` is `oceanbase` diff --git a/docker/dify/.gitignore b/docker/dify/.gitignore deleted file mode 100644 index eec8ce3..0000000 --- a/docker/dify/.gitignore +++ /dev/null @@ -1,28 +0,0 @@ -############################## -# Dify docker volumes -############################## - -# 1. 默认忽略 volumes 下所有内容 -volumes/** -nginx/ -backups/* -# 2. 保留当前已存在的目录本身（目录结构），方便写入 .gitkeep / 初始化文件 -!volumes/ -!volumes/app/ -!volumes/certbot/ -!volumes/db/ -!volumes/myscale/ -!volumes/oceanbase/ -!volumes/opensearch/ -!volumes/plugin_daemon/ -!volumes/redis/ -!volumes/sandbox/ -!volumes/weaviate/ - -# 3. 如需在这些目录下保留特定文件（如 .gitkeep、README.md）， -# 只需在对应目录新建文件，并在本文件中按需增加 !volumes/xxx/filename 规则。 -!volumes/myscale/config/users.d/custom_users_config.xml -!volumes/oceanbase/init.d/vec_memory.sql -!volumes/opensearch/opensearch_dashboards.yml -!volumes/sandbox/conf/config.yaml -!volumes/sandbox/conf/config.yaml.example diff --git a/docker/dify/backup.sh b/docker/dify/backup.sh deleted file mode 100755 index 9cbb857..0000000 --- a/docker/dify/backup.sh +++ /dev/null @@ -1,48 +0,0 @@ -#!/usr/bin/env bash -set -euo pipefail - -# Dify docker backup script -# 备份内容： -# 1) Postgres 数据库 dify -# 2) 整个 volumes/ 目录（包括插件、向量库等数据） - -SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" -cd "$SCRIPT_DIR" - -BACKUP_DIR="$SCRIPT_DIR/backups" -TIMESTAMP="$(date +%Y%m%d_%H%M%S)" -DB_FILE="$BACKUP_DIR/dify_db_${TIMESTAMP}.sql" -VOL_FILE="$BACKUP_DIR/dify_volumes_${TIMESTAMP}.tar.gz" - -mkdir -p "$BACKUP_DIR" - -DB_USER="${POSTGRES_USER:-postgres}" -DB_NAME="${POSTGRES_DB:-dify}" - -# 自动检测 db_postgres 容器名，匹配形如 "-db_postgres-1" -DB_CONTAINER="${DB_CONTAINER:-}" -if [ -z "$DB_CONTAINER" ]; then - DB_CONTAINER="$(docker ps --format '{{.Names}}' | grep 'db_postgres-1$' | head -n1 || true)" -fi - -if [ -z "$DB_CONTAINER" ]; then - echo "错误：未找到名称类似 '*-db_postgres-1' 的运行中容器，请确认 db_postgres 服务已启动。" >&2 - exit 1 -fi - -echo "[1/2] 导出 Postgres 数据库 ${DB_NAME} (容器: ${DB_CONTAINER}) ..." - -docker exec -t "${DB_CONTAINER}" \ - pg_dump -U "${DB_USER}" -d "${DB_NAME}" > "${DB_FILE}" - -echo "数据库已备份到: ${DB_FILE}" - -echo "[2/2] 打包 volumes/ 目录 ..." -if [ ! -d "volumes" ]; then - echo "警告：当前目录下不存在 volumes/ 目录，跳过卷备份。" >&2 -else - tar czf "${VOL_FILE}" volumes/ - echo "卷数据已打包到: ${VOL_FILE}" -fi - -echo "备份完成。" diff --git a/docker/dify/docker-compose-template.yaml b/docker/dify/docker-compose-template.yaml index eb0733e..703a60e 100644 --- a/docker/dify/docker-compose-template.yaml +++ b/docker/dify/docker-compose-template.yaml @@ -2,7 +2,7 @@ x-shared-env: &shared-api-worker-env services: # API service api: - image: langgenius/dify-api:1.10.0 + image: langgenius/dify-api:1.10.1 restart: always environment: # Use the shared environment variables. @@ -41,7 +41,7 @@ services: # worker service # The Celery worker for processing all queues (dataset, workflow, mail, etc.) worker: - image: langgenius/dify-api:1.10.0 + image: langgenius/dify-api:1.10.1 restart: always environment: # Use the shared environment variables. @@ -78,7 +78,7 @@ services: # worker_beat service # Celery beat for scheduling periodic tasks. worker_beat: - image: langgenius/dify-api:1.10.0 + image: langgenius/dify-api:1.10.1 restart: always environment: # Use the shared environment variables. @@ -106,7 +106,7 @@ services: # Frontend web application. web: - image: langgenius/dify-web:1.10.0 + image: langgenius/dify-web:1.10.1 restart: always environment: CONSOLE_API_URL: ${CONSOLE_API_URL:-} @@ -131,7 +131,7 @@ services: ENABLE_WEBSITE_JINAREADER: ${ENABLE_WEBSITE_JINAREADER:-true} ENABLE_WEBSITE_FIRECRAWL: ${ENABLE_WEBSITE_FIRECRAWL:-true} ENABLE_WEBSITE_WATERCRAWL: ${ENABLE_WEBSITE_WATERCRAWL:-true} - + # The PostgreSQL database. db_postgres: image: postgres:15-alpine @@ -459,7 +459,7 @@ services: timeout: 10s # seekdb vector database - seekdb: + seekdb: image: oceanbase/seekdb:latest container_name: seekdb profiles: @@ -486,7 +486,7 @@ services: # Qdrant vector store. # (if used, you need to set VECTOR_STORE to qdrant in the api & worker service.) qdrant: - image: langgenius/qdrant:v1.7.3 + image: langgenius/qdrant:v1.8.3 profiles: - qdrant restart: always @@ -676,7 +676,7 @@ services: milvus-standalone: container_name: milvus-standalone - image: milvusdb/milvus:v2.5.15 + image: milvusdb/milvus:v2.6.3 profiles: - milvus command: ["milvus", "run", "standalone"] diff --git a/docker/dify/docker-compose.yaml b/docker/dify/docker-compose.yaml index 932f6c6..de2e394 100644 --- a/docker/dify/docker-compose.yaml +++ b/docker/dify/docker-compose.yaml @@ -34,6 +34,7 @@ x-shared-env: &shared-api-worker-env FILES_ACCESS_TIMEOUT: ${FILES_ACCESS_TIMEOUT:-300} ACCESS_TOKEN_EXPIRE_MINUTES: ${ACCESS_TOKEN_EXPIRE_MINUTES:-60} REFRESH_TOKEN_EXPIRE_DAYS: ${REFRESH_TOKEN_EXPIRE_DAYS:-30} + APP_DEFAULT_ACTIVE_REQUESTS: ${APP_DEFAULT_ACTIVE_REQUESTS:-0} APP_MAX_ACTIVE_REQUESTS: ${APP_MAX_ACTIVE_REQUESTS:-0} APP_MAX_EXECUTION_TIME: ${APP_MAX_EXECUTION_TIME:-1200} DIFY_BIND_ADDRESS: ${DIFY_BIND_ADDRESS:-0.0.0.0} @@ -164,6 +165,7 @@ x-shared-env: &shared-api-worker-env WEAVIATE_ENDPOINT: ${WEAVIATE_ENDPOINT:-http://weaviate:8080} WEAVIATE_API_KEY: ${WEAVIATE_API_KEY:-WVF5YThaHlkYwhGUSmCRgsX3tD5ngdN8pkih} WEAVIATE_GRPC_ENDPOINT: ${WEAVIATE_GRPC_ENDPOINT:-grpc://weaviate:50051} + WEAVIATE_TOKENIZATION: ${WEAVIATE_TOKENIZATION:-word} OCEANBASE_VECTOR_HOST: ${OCEANBASE_VECTOR_HOST:-oceanbase} OCEANBASE_VECTOR_PORT: ${OCEANBASE_VECTOR_PORT:-2881} OCEANBASE_VECTOR_USER: ${OCEANBASE_VECTOR_USER:-root@test} @@ -532,7 +534,7 @@ x-shared-env: &shared-api-worker-env SSRF_POOL_MAX_CONNECTIONS: ${SSRF_POOL_MAX_CONNECTIONS:-100} SSRF_POOL_MAX_KEEPALIVE_CONNECTIONS: ${SSRF_POOL_MAX_KEEPALIVE_CONNECTIONS:-20} SSRF_POOL_KEEPALIVE_EXPIRY: ${SSRF_POOL_KEEPALIVE_EXPIRY:-5.0} - EXPOSE_NGINX_PORT: ${EXPOSE_NGINX_PORT:-8000} + EXPOSE_NGINX_PORT: ${EXPOSE_NGINX_PORT:-80} EXPOSE_NGINX_SSL_PORT: ${EXPOSE_NGINX_SSL_PORT:-443} POSITION_TOOL_PINS: ${POSITION_TOOL_PINS:-} POSITION_TOOL_INCLUDES: ${POSITION_TOOL_INCLUDES:-} @@ -635,7 +637,7 @@ x-shared-env: &shared-api-worker-env services: # API service api: - image: langgenius/dify-api:1.10.0 + image: langgenius/dify-api:1.10.1 restart: always environment: # Use the shared environment variables. @@ -674,7 +676,7 @@ services: # worker service # The Celery worker for processing all queues (dataset, workflow, mail, etc.) worker: - image: langgenius/dify-api:1.10.0 + image: langgenius/dify-api:1.10.1 restart: always environment: # Use the shared environment variables. @@ -711,7 +713,7 @@ services: # worker_beat service # Celery beat for scheduling periodic tasks. worker_beat: - image: langgenius/dify-api:1.10.0 + image: langgenius/dify-api:1.10.1 restart: always environment: # Use the shared environment variables. @@ -739,7 +741,7 @@ services: # Frontend web application. web: - image: langgenius/dify-web:1.10.0 + image: langgenius/dify-web:1.10.1 restart: always environment: CONSOLE_API_URL: ${CONSOLE_API_URL:-} @@ -764,12 +766,12 @@ services: ENABLE_WEBSITE_JINAREADER: ${ENABLE_WEBSITE_JINAREADER:-true} ENABLE_WEBSITE_FIRECRAWL: ${ENABLE_WEBSITE_FIRECRAWL:-true} ENABLE_WEBSITE_WATERCRAWL: ${ENABLE_WEBSITE_WATERCRAWL:-true} - + # The PostgreSQL database. db_postgres: image: postgres:15-alpine - # profiles: # 避免分部启动时意外启动 - # - postgresql + profiles: + - postgresql restart: always environment: POSTGRES_USER: ${POSTGRES_USER:-postgres} @@ -1033,14 +1035,14 @@ services: - api - web ports: - - "${EXPOSE_NGINX_PORT:-8000}:${NGINX_PORT:-80}" + - "${EXPOSE_NGINX_PORT:-80}:${NGINX_PORT:-80}" - "${EXPOSE_NGINX_SSL_PORT:-443}:${NGINX_SSL_PORT:-443}" # The Weaviate vector store. weaviate: image: semitechnologies/weaviate:1.27.0 - # profiles: #避免分部启动 - # - weaviate + profiles: + - weaviate restart: always volumes: # Mount the Weaviate data directory to the con tainer. @@ -1092,7 +1094,7 @@ services: timeout: 10s # seekdb vector database - seekdb: + seekdb: image: oceanbase/seekdb:latest container_name: seekdb profiles: @@ -1119,7 +1121,7 @@ services: # Qdrant vector store. # (if used, you need to set VECTOR_STORE to qdrant in the api & worker service.) qdrant: - image: langgenius/qdrant:v1.7.3 + image: langgenius/qdrant:v1.8.3 profiles: - qdrant restart: always @@ -1309,7 +1311,7 @@ services: milvus-standalone: container_name: milvus-standalone - image: milvusdb/milvus:v2.5.15 + image: milvusdb/milvus:v2.6.3 profiles: - milvus command: ["milvus", "run", "standalone"] diff --git a/docker/dify/nginx/conf.d/default.conf b/docker/dify/nginx/conf.d/default.conf new file mode 100644 index 0000000..047e9ce --- /dev/null +++ b/docker/dify/nginx/conf.d/default.conf @@ -0,0 +1,58 @@ +# Please do not directly edit this file. Instead, modify the .env variables related to NGINX configuration. + +server { + listen 80; + server_name _; + + location /console/api { + proxy_pass http://api:5001; + include proxy.conf; + } + + location /api { + proxy_pass http://api:5001; + include proxy.conf; + } + + location /v1 { + proxy_pass http://api:5001; + include proxy.conf; + } + + location /files { + proxy_pass http://api:5001; + include proxy.conf; + } + + location /explore { + proxy_pass http://web:3000; + include proxy.conf; + } + + location /e/ { + proxy_pass http://plugin_daemon:5002; + proxy_set_header Dify-Hook-Url $scheme://$host$request_uri; + include proxy.conf; + } + + location / { + proxy_pass http://web:3000; + include proxy.conf; + } + + location /mcp { + proxy_pass http://api:5001; + include proxy.conf; + } + + location /triggers { + proxy_pass http://api:5001; + include proxy.conf; + } + + # placeholder for acme challenge location + + + # placeholder for https config defined in https.conf.template + +} diff --git a/docker/dify/restore.sh b/docker/dify/restore.sh deleted file mode 100755 index b1bd2e8..0000000 --- a/docker/dify/restore.sh +++ /dev/null @@ -1,76 +0,0 @@ -#!/usr/bin/env bash -set -euo pipefail - -# Dify docker restore script -# 使用 backups/ 中的备份恢复： -# 1) volumes/ 目录 -# 2) Postgres 数据库 dify -# -# 用法： -# ./restore.sh # 使用最新备份 -# ./restore.sh 20251124_120000 # 使用指定时间戳的一组备份 - -SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)" -cd "$SCRIPT_DIR" - -BACKUP_DIR="$SCRIPT_DIR/backups" -TIMESTAMP="${1:-latest}" - -if [ ! -d "$BACKUP_DIR" ]; then - echo "错误：未找到备份目录 $BACKUP_DIR" >&2 - exit 1 -fi - -# 选择备份文件 -if [ "$TIMESTAMP" = "latest" ]; then - DB_FILE="$(ls -1t "$BACKUP_DIR"/dify_db_*.sql 2>/dev/null | head -n1 || true)" - VOL_FILE="$(ls -1t "$BACKUP_DIR"/dify_volumes_*.tar.gz 2>/dev/null | head -n1 || true)" -else - DB_FILE="$BACKUP_DIR/dify_db_${TIMESTAMP}.sql" - VOL_FILE="$BACKUP_DIR/dify_volumes_${TIMESTAMP}.tar.gz" -fi - -if [ -z "${DB_FILE:-}" ] || [ ! -f "$DB_FILE" ]; then - echo "错误：未找到数据库备份文件 (dify_db_*.sql)，请检查 $BACKUP_DIR" >&2 - exit 1 -fi - -if [ -z "${VOL_FILE:-}" ] || [ ! -f "$VOL_FILE" ]; then - echo "错误：未找到卷备份文件 (dify_volumes_*.tar.gz)，请检查 $BACKUP_DIR" >&2 - exit 1 -fi - -DB_USER="${POSTGRES_USER:-postgres}" -DB_NAME="${POSTGRES_DB:-dify}" - -# 自动检测 db_postgres 容器名，匹配形如 "-db_postgres-1" -DB_CONTAINER="${DB_CONTAINER:-}" -if [ -z "$DB_CONTAINER" ]; then - DB_CONTAINER="$(docker ps --format '{{.Names}}' | grep 'db_postgres-1$' | head -n1 || true)" -fi - -if [ -z "$DB_CONTAINER" ]; then - echo "错误：未找到名称类似 '*-db_postgres-1' 的运行中容器，请先启动 dify 的 db_postgres 服务。" >&2 - exit 1 -fi - -echo "将使用备份：" -echo " DB: $DB_FILE" -echo " Vol: $VOL_FILE" -read -rp "确认恢复这些备份? 这可能覆盖现有数据 [y/N]: " CONFIRM -if [[ ! "$CONFIRM" =~ ^[Yy]$ ]]; then - echo "已取消恢复。" - exit 0 -fi - -echo "[1/2] 恢复 volumes/ 目录 ..." -tar xzf "$VOL_FILE" -C "$SCRIPT_DIR" - -echo "[2/2] 恢复 Postgres 数据库 ${DB_NAME} ..." -# 可选：先清空数据库，按需修改 -# docker exec -i "$DB_CONTAINER" psql -U "$DB_USER" -d "$DB_NAME" -c 'DROP SCHEMA public CASCADE; CREATE SCHEMA public;' - -docker exec -i "$DB_CONTAINER" \ - psql -U "$DB_USER" -d "$DB_NAME" < "$DB_FILE" - -echo "恢复完成。" diff --git a/docker/dify/version b/docker/dify/version new file mode 100644 index 0000000..e33692a --- /dev/null +++ b/docker/dify/version @@ -0,0 +1 @@ +1.10.1 \ No newline at end of file