Files
ragflow/docker/docker-compose-base.yml

357 lines
9.3 KiB
YAML
Raw Permalink Normal View History

services:
es01:
profiles:
- elasticsearch
image: elasticsearch:${STACK_VERSION}
volumes:
- esdata01:/usr/share/elasticsearch/data
fix(docker): mount tmpfs on es01 /tmp for entrypoint permissions (#15655) ### What problem does this PR solve? On some Linux hosts (e.g. x86_64 with enforced POSIX ACL on overlay storage), the official `elasticsearch` Docker image cannot start because `docker-entrypoint.sh` needs to create temporary files under `/tmp` for bash here-documents, while the image ACL grants `user:elasticsearch` only `r-x` on `/tmp`: ``` /usr/local/bin/docker-entrypoint.sh: line 73/84: cannot create temp file for here-document: Permission denied ``` RAGFlow users hit this when running `docker compose` with the default `es01` service. See also Refs #284. ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue) ## Summary Mount a writable `tmpfs` at `/tmp` for the `es01` service so Elasticsearch entrypoint scripts can run on ACL-enforced environments. Closes the startup failure described in #284 for non-ARM deployments. ## Changes - Add `tmpfs: /tmp:mode=1777,size=512m` to `es01` in `docker/docker-compose-base.yml` - Document why the mount is required (ES image `/tmp` ACL vs entrypoint here-documents) ## Test plan - [x] Verified on Linux (x86_64): `docker run --rm elasticsearch:8.11.3 bash -c 'mktemp'` fails without tmpfs and succeeds with `--tmpfs /tmp:mode=1777,size=512m` - [x] Verified `es01` becomes healthy after `docker compose up -d es01` with this change - [ ] Upstream maintainers: `docker compose -f docker/docker-compose-base.yml --profile elasticsearch up -d es01` on a host where ACL is enforced Made with [Cursor](https://cursor.com) Co-authored-by: Cursor <cursoragent@cursor.com>
2026-06-04 23:19:31 +08:00
# Official ES image ACL on /tmp denies writes for user elasticsearch (r-x only).
# entrypoint.sh needs a writable temp dir for bash here-documents.
tmpfs:
- /tmp:mode=1777,size=512m
ports:
- ${ES_PORT}:9200
env_file: .env
environment:
- node.name=es01
- ELASTIC_PASSWORD=${ELASTIC_PASSWORD}
- bootstrap.memory_lock=false
- discovery.type=single-node
- xpack.security.enabled=true
- xpack.security.http.ssl.enabled=false
- xpack.security.transport.ssl.enabled=false
- cluster.routing.allocation.disk.watermark.low=5gb
- cluster.routing.allocation.disk.watermark.high=3gb
- cluster.routing.allocation.disk.watermark.flood_stage=2gb
mem_limit: ${MEM_LIMIT}
ulimits:
memlock:
soft: -1
hard: -1
healthcheck:
test: ["CMD-SHELL", "curl http://localhost:9200"]
interval: 10s
timeout: 10s
retries: 120
networks:
- ragflow
restart: unless-stopped
Feat: Adds OpenSearch2.19.1 as the vector_database support (#7140) ### What problem does this PR solve? This PR adds the support for latest OpenSearch2.19.1 as the store engine & search engine option for RAGFlow. ### Main Benefit 1. OpenSearch2.19.1 is licensed under the [Apache v2.0 License] which is much better than Elasticsearch 2. For search, OpenSearch2.19.1 supports full-text search、vector_search、hybrid_search those are similar with Elasticsearch on schema 3. For store, OpenSearch2.19.1 stores text、vector those are quite simliar with Elasticsearch on schema ### Changes - Support opensearch_python_connetor. I make a lot of adaptions since the schema and api/method between ES and Opensearch differs in many ways(especially the knn_search has a significant gap) : rag/utils/opensearch_coon.py - Support static config adaptions by changing: conf/service_conf.yaml、api/settings.py、rag/settings.py - Supprt some store&search schema changes between OpenSearch and ES: conf/os_mapping.json - Support OpenSearch python sdk : pyproject.toml - Support docker config for OpenSearch2.19.1 : docker/.env、docker/docker-compose-base.yml、docker/service_conf.yaml.template ### How to use - I didn't change the priority that ES as the default doc/search engine. Only if in docker/.env , we set DOC_ENGINE=${DOC_ENGINE:-opensearch}, it will work. ### Others Our team tested a lot of docs in our environment by using OpenSearch as the vector database ,it works very well. All the conifg for OpenSearch is necessary. ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
2025-04-24 16:03:31 +08:00
opensearch01:
profiles:
- opensearch
image: opensearchproject/opensearch:2.19.1
Feat: Adds OpenSearch2.19.1 as the vector_database support (#7140) ### What problem does this PR solve? This PR adds the support for latest OpenSearch2.19.1 as the store engine & search engine option for RAGFlow. ### Main Benefit 1. OpenSearch2.19.1 is licensed under the [Apache v2.0 License] which is much better than Elasticsearch 2. For search, OpenSearch2.19.1 supports full-text search、vector_search、hybrid_search those are similar with Elasticsearch on schema 3. For store, OpenSearch2.19.1 stores text、vector those are quite simliar with Elasticsearch on schema ### Changes - Support opensearch_python_connetor. I make a lot of adaptions since the schema and api/method between ES and Opensearch differs in many ways(especially the knn_search has a significant gap) : rag/utils/opensearch_coon.py - Support static config adaptions by changing: conf/service_conf.yaml、api/settings.py、rag/settings.py - Supprt some store&search schema changes between OpenSearch and ES: conf/os_mapping.json - Support OpenSearch python sdk : pyproject.toml - Support docker config for OpenSearch2.19.1 : docker/.env、docker/docker-compose-base.yml、docker/service_conf.yaml.template ### How to use - I didn't change the priority that ES as the default doc/search engine. Only if in docker/.env , we set DOC_ENGINE=${DOC_ENGINE:-opensearch}, it will work. ### Others Our team tested a lot of docs in our environment by using OpenSearch as the vector database ,it works very well. All the conifg for OpenSearch is necessary. ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
2025-04-24 16:03:31 +08:00
volumes:
- osdata01:/usr/share/opensearch/data
ports:
- ${OS_PORT}:9201
env_file: .env
environment:
- node.name=opensearch01
- OPENSEARCH_PASSWORD=${OPENSEARCH_PASSWORD}
- OPENSEARCH_INITIAL_ADMIN_PASSWORD=${OPENSEARCH_PASSWORD}
- bootstrap.memory_lock=false
- discovery.type=single-node
- plugins.security.disabled=false
- plugins.security.ssl.http.enabled=false
- plugins.security.ssl.transport.enabled=true
- cluster.routing.allocation.disk.watermark.low=5gb
- cluster.routing.allocation.disk.watermark.high=3gb
- cluster.routing.allocation.disk.watermark.flood_stage=2gb
- http.port=9201
mem_limit: ${MEM_LIMIT}
ulimits:
memlock:
soft: -1
hard: -1
healthcheck:
test: ["CMD-SHELL", "curl http://localhost:9201"]
interval: 10s
timeout: 10s
retries: 120
networks:
- ragflow
restart: unless-stopped
Feat: Adds OpenSearch2.19.1 as the vector_database support (#7140) ### What problem does this PR solve? This PR adds the support for latest OpenSearch2.19.1 as the store engine & search engine option for RAGFlow. ### Main Benefit 1. OpenSearch2.19.1 is licensed under the [Apache v2.0 License] which is much better than Elasticsearch 2. For search, OpenSearch2.19.1 supports full-text search、vector_search、hybrid_search those are similar with Elasticsearch on schema 3. For store, OpenSearch2.19.1 stores text、vector those are quite simliar with Elasticsearch on schema ### Changes - Support opensearch_python_connetor. I make a lot of adaptions since the schema and api/method between ES and Opensearch differs in many ways(especially the knn_search has a significant gap) : rag/utils/opensearch_coon.py - Support static config adaptions by changing: conf/service_conf.yaml、api/settings.py、rag/settings.py - Supprt some store&search schema changes between OpenSearch and ES: conf/os_mapping.json - Support OpenSearch python sdk : pyproject.toml - Support docker config for OpenSearch2.19.1 : docker/.env、docker/docker-compose-base.yml、docker/service_conf.yaml.template ### How to use - I didn't change the priority that ES as the default doc/search engine. Only if in docker/.env , we set DOC_ENGINE=${DOC_ENGINE:-opensearch}, it will work. ### Others Our team tested a lot of docs in our environment by using OpenSearch as the vector database ,it works very well. All the conifg for OpenSearch is necessary. ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
2025-04-24 16:03:31 +08:00
infinity:
profiles:
- infinity
image: infiniflow/infinity:v0.7.0
volumes:
- infinity_data:/var/infinity
- ./infinity_conf.toml:/infinity_conf.toml
command: ["-f", "/infinity_conf.toml"]
ports:
- ${INFINITY_THRIFT_PORT}:23817
- ${INFINITY_HTTP_PORT}:23820
- ${INFINITY_PSQL_PORT}:5432
env_file: .env
mem_limit: ${MEM_LIMIT}
ulimits:
nofile:
soft: 500000
hard: 500000
networks:
- ragflow
healthcheck:
test: ["CMD", "curl", "http://localhost:23820/admin/node/current"]
interval: 10s
timeout: 10s
retries: 120
restart: unless-stopped
oceanbase:
profiles:
- oceanbase
image: oceanbase/oceanbase-ce:4.4.1.0-100000032025101610
entrypoint: ["bash", "/root/boot/ragflow-oceanbase-entrypoint.sh"]
ulimits:
nofile:
soft: 655350
hard: 655350
volumes:
- ./oceanbase/data:/root/ob
- ./oceanbase/conf:/root/.obd/cluster
- ./oceanbase/init.d:/root/boot/init.d
- ./oceanbase-entrypoint.sh:/root/boot/ragflow-oceanbase-entrypoint.sh:ro
ports:
- ${OCEANBASE_PORT:-2881}:2881
env_file: .env
environment:
- MODE=normal
- OB_SERVER_IP=127.0.0.1
mem_limit: ${MEM_LIMIT}
healthcheck:
test: [ 'CMD-SHELL', 'obclient -h127.0.0.1 -P2881 -uroot@${OB_TENANT_NAME:-ragflow} -p${OB_TENANT_PASSWORD:-infini_rag_flow} -e "CREATE DATABASE IF NOT EXISTS ${OCEANBASE_DOC_DBNAME:-ragflow_doc};"' ]
interval: 10s
retries: 30
start_period: 30s
timeout: 10s
networks:
- ragflow
restart: unless-stopped
seekdb:
profiles:
- seekdb
image: oceanbase/seekdb:latest
container_name: seekdb
volumes:
- ./seekdb:/var/lib/oceanbase
ports:
- ${SEEKDB_PORT:-2881}:2881
env_file: .env
environment:
- ROOT_PASSWORD=${SEEKDB_PASSWORD:-infini_rag_flow}
- MEMORY_LIMIT=${SEEKDB_MEMORY_LIMIT:-2G}
- REPORTER=ragflow-seekdb
mem_limit: ${MEM_LIMIT}
healthcheck:
test: ['CMD-SHELL', 'mysql -h127.0.0.1 -P2881 -uroot -p${SEEKDB_PASSWORD:-infini_rag_flow} -e "CREATE DATABASE IF NOT EXISTS ${SEEKDB_DOC_DBNAME:-ragflow_doc};"']
interval: 5s
retries: 60
timeout: 5s
networks:
- ragflow
restart: unless-stopped
sandbox-executor-manager:
profiles:
- sandbox
image: ${SANDBOX_EXECUTOR_MANAGER_IMAGE-infiniflow/sandbox-executor-manager:latest}
privileged: true
ports:
- ${SANDBOX_EXECUTOR_MANAGER_PORT-9385}:9385
env_file: .env
volumes:
- /var/run/docker.sock:/var/run/docker.sock
networks:
- ragflow
security_opt:
- no-new-privileges:true
environment:
- SANDBOX_EXECUTOR_MANAGER_POOL_SIZE=${SANDBOX_EXECUTOR_MANAGER_POOL_SIZE:-3}
- SANDBOX_BASE_PYTHON_IMAGE=${SANDBOX_BASE_PYTHON_IMAGE:-infiniflow/sandbox-base-python:latest}
- SANDBOX_BASE_NODEJS_IMAGE=${SANDBOX_BASE_NODEJS_IMAGE:-infiniflow/sandbox-base-nodejs:latest}
- SANDBOX_ENABLE_SECCOMP=${SANDBOX_ENABLE_SECCOMP:-false}
- SANDBOX_MAX_MEMORY=${SANDBOX_MAX_MEMORY:-256m}
- SANDBOX_TIMEOUT=${SANDBOX_TIMEOUT:-10s}
healthcheck:
test: ["CMD", "curl", "http://localhost:9385/healthz"]
interval: 10s
timeout: 10s
retries: 120
restart: unless-stopped
mysql:
# mysql:5.7 linux/arm64 image is unavailable.
image: mysql:8.0.39
env_file: .env
environment:
- MYSQL_ROOT_PASSWORD=${MYSQL_PASSWORD}
command:
--max_connections=1000
--character-set-server=utf8mb4
--collation-server=utf8mb4_unicode_ci
--default-authentication-plugin=mysql_native_password
--tls_version="TLSv1.2,TLSv1.3"
--init-file /data/application/init.sql
--binlog_expire_logs_seconds=604800
ports:
- ${EXPOSE_MYSQL_PORT}:3306
volumes:
- mysql_data:/var/lib/mysql
- ./init.sql:/data/application/init.sql
networks:
- ragflow
healthcheck:
test: ["CMD", "mysqladmin" ,"ping", "-uroot", "-p${MYSQL_PASSWORD}"]
interval: 10s
timeout: 10s
retries: 120
restart: unless-stopped
minio:
image: pgsty/minio:RELEASE.2026-03-25T00-00-00Z
command: ["server", "--console-address", ":9001", "/data"]
ports:
- ${MINIO_PORT}:9000
- ${MINIO_CONSOLE_PORT}:9001
env_file: .env
environment:
- MINIO_ROOT_USER=${MINIO_USER}
- MINIO_ROOT_PASSWORD=${MINIO_PASSWORD}
volumes:
- minio_data:/data
networks:
- ragflow
restart: unless-stopped
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:9000/minio/health/live"]
interval: 10s
timeout: 10s
retries: 120
redis:
# swr.cn-north-4.myhuaweicloud.com/ddn-k8s/docker.io/valkey/valkey:8
image: valkey/valkey:8
command: ["redis-server", "--requirepass", "${REDIS_PASSWORD}", "--maxmemory", "128mb", "--maxmemory-policy", "allkeys-lru"]
env_file: .env
ports:
- ${REDIS_PORT}:6379
volumes:
- redis_data:/data
networks:
- ragflow
restart: unless-stopped
healthcheck:
test: ["CMD", "redis-cli", "-a", "${REDIS_PASSWORD}", "ping"]
interval: 10s
timeout: 10s
retries: 120
Go: use NATS as the message queue (#15327) ### What problem does this PR solve? ``` RAGFlow(admin)> mq publish 'msg2'; SUCCESS RAGFlow(admin)> mq publish 'msg3'; SUCCESS RAGFlow(admin)> mq list; +---------+---------------+ | message | subject | +---------+---------------+ | msg1 | tasks.RAGFLOW | | msg2 | tasks.RAGFLOW | | msg3 | tasks.RAGFLOW | +---------+---------------+ RAGFlow(admin)> mq pull 2; +---------+---------------+ | message | subject | +---------+---------------+ | msg1 | tasks.RAGFLOW | | msg2 | tasks.RAGFLOW | +---------+---------------+ RAGFlow(admin)> mq pull noack; +---------+---------------+ | message | subject | +---------+---------------+ | abc | tasks.RAGFLOW | +---------+---------------+ RAGFlow(admin)> mq show +-------------------+----------------+--------+---------------+---------------+-------------------+---------------+ | ack_pending_count | consumer_count | memory | message_count | pending_count | redelivered_count | waiting_count | +-------------------+----------------+--------+---------------+---------------+-------------------+---------------+ | 2 | 1 | 0 | 2 | 0 | 1 | 0 | +-------------------+----------------+--------+---------------+---------------+-------------------+---------------+ RAGFlow(admin)> list ingestors; +--------------+-------------------------------------------+--------+ | host | name | status | +--------------+-------------------------------------------+--------+ | 192.168.1.38 | ingestor-8f0e4bd5650a4ac58b0151969fbf6935 | alive | +--------------+-------------------------------------------+--------+ RAGFlow(admin)> list ingestion tasks; +----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+ | document_id | id | status | step | user | user_id | +----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+ | ffe64fae423411f1a2d938a74640adcc | 90d3d0f6528941c1ac8eb0360effccc4 | COMPLETED | 5 | aaa@aaa.com | 2ba4881420fa11f19e9c38a74640adcc | +----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+ RAGFlow(admin)> remove ingestion tasks '90d3d0f6528941c1ac8eb0360effccc4'; +---------+----------------------------------+ | delete | task_id | +---------+----------------------------------+ | success | 90d3d0f6528941c1ac8eb0360effccc4 | +---------+----------------------------------+ RAGFlow(admin)> stop ingestion tasks 'e89e20d9a25848a1b79bd9345ddbfe1d'; +----------+----------------------------------+ | status | task_id | +----------+----------------------------------+ | STOPPING | e89e20d9a25848a1b79bd9345ddbfe1d | +----------+----------------------------------+ # Publish a message RAGFlow(admin)> mq publish 'cdd'; SUCCESS # List current tasks in the message queue RAGFlow(admin)> mq list +----------------------------------+---------------+ | message | subject | +----------------------------------+---------------+ | 7ce392a3c1624cd2be4b5276e8825059 | tasks.RAGFLOW | +----------------------------------+---------------+ # Consume a task from the message queue RAGFlow(admin)> mq pull +------+-----+----------------+ | ack | id | type | +------+-----+----------------+ | true | cdd | ingestion_test | +------+-----+----------------+ # User mode # List ingestion tasks, followed by dataset id RAGFlow(user)> list ingestion tasks from '0abe79f9423311f1ad8d38a74640adcc'; +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | create_date | create_time | dataset_id | document_id | id | schema | status | update_date | update_time | user_id | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | 2026-05-30T20:21:06+08:00 | 1780143666289 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | 8d758cd14a8b4ba8ab505003fb52017d | | COMPLETED | 2026-05-30T20:21:26+08:00 | 1780143686431 | 2ba4881420fa11f19e9c38a74640adcc | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ RAGFlow(user)> list ingestion tasks; +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | create_date | create_time | dataset_id | document_id | id | schema | status | update_date | update_time | user_id | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | 2026-06-02T19:02:31+08:00 | 1780398151417 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | e89e20d9a25848a1b79bd9345ddbfe1d | | COMPLETED | 2026-06-02T19:02:52+08:00 | 1780398172208 | 2ba4881420fa11f19e9c38a74640adcc | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ # Create an ingestion task # First argument is document id, second argument is dataset id RAGFlow(user)> start ingestion 'ffe64fae423411f1a2d938a74640adcc' from '0abe79f9423311f1ad8d38a74640adcc'; +----------------------------------+-------------------------------------------+ | document_id | result | +----------------------------------+-------------------------------------------+ | ffe64fae423411f1a2d938a74640adcc | task_id: 8d758cd14a8b4ba8ab505003fb52017d | +----------------------------------+-------------------------------------------+ # Pause an ingestion task, first argument is ingestion id RAGFlow(user)> stop ingestion '8d758cd14a8b4ba8ab505003fb52017d'; +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | create_date | create_time | dataset_id | document_id | id | schema | status | update_date | update_time | user_id | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | 2026-05-30T20:21:06+08:00 | 1780143666289 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | 8d758cd14a8b4ba8ab505003fb52017d | | COMPLETED | 2026-05-30T20:21:26+08:00 | 1780143686431 | 2ba4881420fa11f19e9c38a74640adcc | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ # Delete an ingestion task RAGFlow(api/default)> remove ingestion tasks 'f366450a27d54677aec1c7090add30f0'; +---------+----------------------------------+ | remove | task_id | +---------+----------------------------------+ | success | f366450a27d54677aec1c7090add30f0 | +---------+----------------------------------+ ``` ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-06-12 14:56:44 +08:00
nats:
profiles:
- ragflow-go
image: nats:2.14.2
Go: use NATS as the message queue (#15327) ### What problem does this PR solve? ``` RAGFlow(admin)> mq publish 'msg2'; SUCCESS RAGFlow(admin)> mq publish 'msg3'; SUCCESS RAGFlow(admin)> mq list; +---------+---------------+ | message | subject | +---------+---------------+ | msg1 | tasks.RAGFLOW | | msg2 | tasks.RAGFLOW | | msg3 | tasks.RAGFLOW | +---------+---------------+ RAGFlow(admin)> mq pull 2; +---------+---------------+ | message | subject | +---------+---------------+ | msg1 | tasks.RAGFLOW | | msg2 | tasks.RAGFLOW | +---------+---------------+ RAGFlow(admin)> mq pull noack; +---------+---------------+ | message | subject | +---------+---------------+ | abc | tasks.RAGFLOW | +---------+---------------+ RAGFlow(admin)> mq show +-------------------+----------------+--------+---------------+---------------+-------------------+---------------+ | ack_pending_count | consumer_count | memory | message_count | pending_count | redelivered_count | waiting_count | +-------------------+----------------+--------+---------------+---------------+-------------------+---------------+ | 2 | 1 | 0 | 2 | 0 | 1 | 0 | +-------------------+----------------+--------+---------------+---------------+-------------------+---------------+ RAGFlow(admin)> list ingestors; +--------------+-------------------------------------------+--------+ | host | name | status | +--------------+-------------------------------------------+--------+ | 192.168.1.38 | ingestor-8f0e4bd5650a4ac58b0151969fbf6935 | alive | +--------------+-------------------------------------------+--------+ RAGFlow(admin)> list ingestion tasks; +----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+ | document_id | id | status | step | user | user_id | +----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+ | ffe64fae423411f1a2d938a74640adcc | 90d3d0f6528941c1ac8eb0360effccc4 | COMPLETED | 5 | aaa@aaa.com | 2ba4881420fa11f19e9c38a74640adcc | +----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+ RAGFlow(admin)> remove ingestion tasks '90d3d0f6528941c1ac8eb0360effccc4'; +---------+----------------------------------+ | delete | task_id | +---------+----------------------------------+ | success | 90d3d0f6528941c1ac8eb0360effccc4 | +---------+----------------------------------+ RAGFlow(admin)> stop ingestion tasks 'e89e20d9a25848a1b79bd9345ddbfe1d'; +----------+----------------------------------+ | status | task_id | +----------+----------------------------------+ | STOPPING | e89e20d9a25848a1b79bd9345ddbfe1d | +----------+----------------------------------+ # Publish a message RAGFlow(admin)> mq publish 'cdd'; SUCCESS # List current tasks in the message queue RAGFlow(admin)> mq list +----------------------------------+---------------+ | message | subject | +----------------------------------+---------------+ | 7ce392a3c1624cd2be4b5276e8825059 | tasks.RAGFLOW | +----------------------------------+---------------+ # Consume a task from the message queue RAGFlow(admin)> mq pull +------+-----+----------------+ | ack | id | type | +------+-----+----------------+ | true | cdd | ingestion_test | +------+-----+----------------+ # User mode # List ingestion tasks, followed by dataset id RAGFlow(user)> list ingestion tasks from '0abe79f9423311f1ad8d38a74640adcc'; +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | create_date | create_time | dataset_id | document_id | id | schema | status | update_date | update_time | user_id | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | 2026-05-30T20:21:06+08:00 | 1780143666289 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | 8d758cd14a8b4ba8ab505003fb52017d | | COMPLETED | 2026-05-30T20:21:26+08:00 | 1780143686431 | 2ba4881420fa11f19e9c38a74640adcc | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ RAGFlow(user)> list ingestion tasks; +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | create_date | create_time | dataset_id | document_id | id | schema | status | update_date | update_time | user_id | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | 2026-06-02T19:02:31+08:00 | 1780398151417 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | e89e20d9a25848a1b79bd9345ddbfe1d | | COMPLETED | 2026-06-02T19:02:52+08:00 | 1780398172208 | 2ba4881420fa11f19e9c38a74640adcc | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ # Create an ingestion task # First argument is document id, second argument is dataset id RAGFlow(user)> start ingestion 'ffe64fae423411f1a2d938a74640adcc' from '0abe79f9423311f1ad8d38a74640adcc'; +----------------------------------+-------------------------------------------+ | document_id | result | +----------------------------------+-------------------------------------------+ | ffe64fae423411f1a2d938a74640adcc | task_id: 8d758cd14a8b4ba8ab505003fb52017d | +----------------------------------+-------------------------------------------+ # Pause an ingestion task, first argument is ingestion id RAGFlow(user)> stop ingestion '8d758cd14a8b4ba8ab505003fb52017d'; +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | create_date | create_time | dataset_id | document_id | id | schema | status | update_date | update_time | user_id | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | 2026-05-30T20:21:06+08:00 | 1780143666289 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | 8d758cd14a8b4ba8ab505003fb52017d | | COMPLETED | 2026-05-30T20:21:26+08:00 | 1780143686431 | 2ba4881420fa11f19e9c38a74640adcc | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ # Delete an ingestion task RAGFlow(api/default)> remove ingestion tasks 'f366450a27d54677aec1c7090add30f0'; +---------+----------------------------------+ | remove | task_id | +---------+----------------------------------+ | success | f366450a27d54677aec1c7090add30f0 | +---------+----------------------------------+ ``` ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-06-12 14:56:44 +08:00
ports:
- ${NATS_PORT}:4222
- "8222:8222"
volumes:
- nats_data:/data
command: -js -sd /data
env_file: .env
networks:
- ragflow
restart: unless-stopped
healthcheck:
test: ["CMD", "nc", "-z", "localhost", "${NATS_PORT}"]
interval: 10s
timeout: 10s
retries: 120
tei-cpu:
profiles:
- tei-cpu
image: ${TEI_IMAGE_CPU}
hostname: tei
ports:
- ${TEI_PORT-6380}:80
env_file: .env
networks:
- ragflow
command: ["--model-id", "/data/${TEI_MODEL}", "--auto-truncate"]
restart: unless-stopped
tei-gpu:
profiles:
- tei-gpu
image: ${TEI_IMAGE_GPU}
hostname: tei
ports:
- ${TEI_PORT-6380}:80
env_file: .env
networks:
- ragflow
command: ["--model-id", "/data/${TEI_MODEL}", "--auto-truncate"]
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
restart: unless-stopped
kibana:
profiles:
- kibana
image: kibana:${STACK_VERSION}
ports:
- ${KIBANA_PORT-5601}:5601
env_file: .env
volumes:
- kibana_data:/usr/share/kibana/data
depends_on:
es01:
condition: service_started
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:5601/api/status"]
interval: 10s
timeout: 10s
retries: 120
networks:
- ragflow
restart: unless-stopped
volumes:
esdata01:
driver: local
Feat: Adds OpenSearch2.19.1 as the vector_database support (#7140) ### What problem does this PR solve? This PR adds the support for latest OpenSearch2.19.1 as the store engine & search engine option for RAGFlow. ### Main Benefit 1. OpenSearch2.19.1 is licensed under the [Apache v2.0 License] which is much better than Elasticsearch 2. For search, OpenSearch2.19.1 supports full-text search、vector_search、hybrid_search those are similar with Elasticsearch on schema 3. For store, OpenSearch2.19.1 stores text、vector those are quite simliar with Elasticsearch on schema ### Changes - Support opensearch_python_connetor. I make a lot of adaptions since the schema and api/method between ES and Opensearch differs in many ways(especially the knn_search has a significant gap) : rag/utils/opensearch_coon.py - Support static config adaptions by changing: conf/service_conf.yaml、api/settings.py、rag/settings.py - Supprt some store&search schema changes between OpenSearch and ES: conf/os_mapping.json - Support OpenSearch python sdk : pyproject.toml - Support docker config for OpenSearch2.19.1 : docker/.env、docker/docker-compose-base.yml、docker/service_conf.yaml.template ### How to use - I didn't change the priority that ES as the default doc/search engine. Only if in docker/.env , we set DOC_ENGINE=${DOC_ENGINE:-opensearch}, it will work. ### Others Our team tested a lot of docs in our environment by using OpenSearch as the vector database ,it works very well. All the conifg for OpenSearch is necessary. ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Co-authored-by: Yongteng Lei <yongtengrey@outlook.com> Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com> Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
2025-04-24 16:03:31 +08:00
osdata01:
driver: local
infinity_data:
driver: local
ob_data:
driver: local
seekdb_data:
driver: local
mysql_data:
driver: local
minio_data:
driver: local
redis_data:
driver: local
tei_data:
driver: local
kibana_data:
driver: local
Go: use NATS as the message queue (#15327) ### What problem does this PR solve? ``` RAGFlow(admin)> mq publish 'msg2'; SUCCESS RAGFlow(admin)> mq publish 'msg3'; SUCCESS RAGFlow(admin)> mq list; +---------+---------------+ | message | subject | +---------+---------------+ | msg1 | tasks.RAGFLOW | | msg2 | tasks.RAGFLOW | | msg3 | tasks.RAGFLOW | +---------+---------------+ RAGFlow(admin)> mq pull 2; +---------+---------------+ | message | subject | +---------+---------------+ | msg1 | tasks.RAGFLOW | | msg2 | tasks.RAGFLOW | +---------+---------------+ RAGFlow(admin)> mq pull noack; +---------+---------------+ | message | subject | +---------+---------------+ | abc | tasks.RAGFLOW | +---------+---------------+ RAGFlow(admin)> mq show +-------------------+----------------+--------+---------------+---------------+-------------------+---------------+ | ack_pending_count | consumer_count | memory | message_count | pending_count | redelivered_count | waiting_count | +-------------------+----------------+--------+---------------+---------------+-------------------+---------------+ | 2 | 1 | 0 | 2 | 0 | 1 | 0 | +-------------------+----------------+--------+---------------+---------------+-------------------+---------------+ RAGFlow(admin)> list ingestors; +--------------+-------------------------------------------+--------+ | host | name | status | +--------------+-------------------------------------------+--------+ | 192.168.1.38 | ingestor-8f0e4bd5650a4ac58b0151969fbf6935 | alive | +--------------+-------------------------------------------+--------+ RAGFlow(admin)> list ingestion tasks; +----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+ | document_id | id | status | step | user | user_id | +----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+ | ffe64fae423411f1a2d938a74640adcc | 90d3d0f6528941c1ac8eb0360effccc4 | COMPLETED | 5 | aaa@aaa.com | 2ba4881420fa11f19e9c38a74640adcc | +----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+ RAGFlow(admin)> remove ingestion tasks '90d3d0f6528941c1ac8eb0360effccc4'; +---------+----------------------------------+ | delete | task_id | +---------+----------------------------------+ | success | 90d3d0f6528941c1ac8eb0360effccc4 | +---------+----------------------------------+ RAGFlow(admin)> stop ingestion tasks 'e89e20d9a25848a1b79bd9345ddbfe1d'; +----------+----------------------------------+ | status | task_id | +----------+----------------------------------+ | STOPPING | e89e20d9a25848a1b79bd9345ddbfe1d | +----------+----------------------------------+ # Publish a message RAGFlow(admin)> mq publish 'cdd'; SUCCESS # List current tasks in the message queue RAGFlow(admin)> mq list +----------------------------------+---------------+ | message | subject | +----------------------------------+---------------+ | 7ce392a3c1624cd2be4b5276e8825059 | tasks.RAGFLOW | +----------------------------------+---------------+ # Consume a task from the message queue RAGFlow(admin)> mq pull +------+-----+----------------+ | ack | id | type | +------+-----+----------------+ | true | cdd | ingestion_test | +------+-----+----------------+ # User mode # List ingestion tasks, followed by dataset id RAGFlow(user)> list ingestion tasks from '0abe79f9423311f1ad8d38a74640adcc'; +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | create_date | create_time | dataset_id | document_id | id | schema | status | update_date | update_time | user_id | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | 2026-05-30T20:21:06+08:00 | 1780143666289 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | 8d758cd14a8b4ba8ab505003fb52017d | | COMPLETED | 2026-05-30T20:21:26+08:00 | 1780143686431 | 2ba4881420fa11f19e9c38a74640adcc | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ RAGFlow(user)> list ingestion tasks; +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | create_date | create_time | dataset_id | document_id | id | schema | status | update_date | update_time | user_id | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | 2026-06-02T19:02:31+08:00 | 1780398151417 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | e89e20d9a25848a1b79bd9345ddbfe1d | | COMPLETED | 2026-06-02T19:02:52+08:00 | 1780398172208 | 2ba4881420fa11f19e9c38a74640adcc | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ # Create an ingestion task # First argument is document id, second argument is dataset id RAGFlow(user)> start ingestion 'ffe64fae423411f1a2d938a74640adcc' from '0abe79f9423311f1ad8d38a74640adcc'; +----------------------------------+-------------------------------------------+ | document_id | result | +----------------------------------+-------------------------------------------+ | ffe64fae423411f1a2d938a74640adcc | task_id: 8d758cd14a8b4ba8ab505003fb52017d | +----------------------------------+-------------------------------------------+ # Pause an ingestion task, first argument is ingestion id RAGFlow(user)> stop ingestion '8d758cd14a8b4ba8ab505003fb52017d'; +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | create_date | create_time | dataset_id | document_id | id | schema | status | update_date | update_time | user_id | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ | 2026-05-30T20:21:06+08:00 | 1780143666289 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | 8d758cd14a8b4ba8ab505003fb52017d | | COMPLETED | 2026-05-30T20:21:26+08:00 | 1780143686431 | 2ba4881420fa11f19e9c38a74640adcc | +---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+ # Delete an ingestion task RAGFlow(api/default)> remove ingestion tasks 'f366450a27d54677aec1c7090add30f0'; +---------+----------------------------------+ | remove | task_id | +---------+----------------------------------+ | success | f366450a27d54677aec1c7090add30f0 | +---------+----------------------------------+ ``` ### Type of change - [x] New Feature (non-breaking change which adds functionality) --------- Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-06-12 14:56:44 +08:00
nats_data:
driver: local
networks:
ragflow:
driver: bridge