mirror of
https://github.com/infiniflow/ragflow.git
synced 2025-12-08 20:42:30 +08:00
c8c3b756b0
### 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>
99 lines
2.7 KiB
Plaintext
99 lines
2.7 KiB
Plaintext
ragflow:
|
|
host: ${RAGFLOW_HOST:-0.0.0.0}
|
|
http_port: 9380
|
|
mysql:
|
|
name: '${MYSQL_DBNAME:-rag_flow}'
|
|
user: '${MYSQL_USER:-root}'
|
|
password: '${MYSQL_PASSWORD:-infini_rag_flow}'
|
|
host: '${MYSQL_HOST:-mysql}'
|
|
port: 3306
|
|
max_connections: 100
|
|
stale_timeout: 30
|
|
minio:
|
|
user: '${MINIO_USER:-rag_flow}'
|
|
password: '${MINIO_PASSWORD:-infini_rag_flow}'
|
|
host: '${MINIO_HOST:-minio}:9000'
|
|
es:
|
|
hosts: 'http://${ES_HOST:-es01}:9200'
|
|
username: '${ES_USER:-elastic}'
|
|
password: '${ELASTIC_PASSWORD:-infini_rag_flow}'
|
|
os:
|
|
hosts: 'http://${OS_HOST:-opensearch01}:9201'
|
|
username: '${OS_USER:-admin}'
|
|
password: '${OPENSEARCHH_PASSWORD:-infini_rag_flow_OS_01}'
|
|
infinity:
|
|
uri: '${INFINITY_HOST:-infinity}:23817'
|
|
db_name: 'default_db'
|
|
redis:
|
|
db: 1
|
|
password: '${REDIS_PASSWORD:-infini_rag_flow}'
|
|
host: '${REDIS_HOST:-redis}:6379'
|
|
|
|
# postgres:
|
|
# name: '${POSTGRES_DBNAME:-rag_flow}'
|
|
# user: '${POSTGRES_USER:-rag_flow}'
|
|
# password: '${POSTGRES_PASSWORD:-infini_rag_flow}'
|
|
# host: '${POSTGRES_HOST:-postgres}'
|
|
# port: 5432
|
|
# max_connections: 100
|
|
# stale_timeout: 30
|
|
# s3:
|
|
# access_key: 'access_key'
|
|
# secret_key: 'secret_key'
|
|
# region: 'region'
|
|
# endpoint_url: 'endpoint_url'
|
|
# bucket: 'bucket'
|
|
# prefix_path: 'prefix_path'
|
|
# signature_version: 'v4'
|
|
# addressing_style: 'path'
|
|
# oss:
|
|
# access_key: '${ACCESS_KEY}'
|
|
# secret_key: '${SECRET_KEY}'
|
|
# endpoint_url: '${ENDPOINT}'
|
|
# region: '${REGION}'
|
|
# bucket: '${BUCKET}'
|
|
# prefix_path: '${OSS_PREFIX_PATH}'
|
|
# azure:
|
|
# auth_type: 'sas'
|
|
# container_url: 'container_url'
|
|
# sas_token: 'sas_token'
|
|
# azure:
|
|
# auth_type: 'spn'
|
|
# account_url: 'account_url'
|
|
# client_id: 'client_id'
|
|
# secret: 'secret'
|
|
# tenant_id: 'tenant_id'
|
|
# container_name: 'container_name'
|
|
# user_default_llm:
|
|
# factory: 'Tongyi-Qianwen'
|
|
# api_key: 'sk-xxxxxxxxxxxxx'
|
|
# base_url: ''
|
|
# default_models:
|
|
# chat_model: 'qwen-plus'
|
|
# embedding_model: 'BAAI/bge-large-zh-v1.5@BAAI'
|
|
# rerank_model: ''
|
|
# asr_model: ''
|
|
# image2text_model: ''
|
|
# oauth:
|
|
# github:
|
|
# client_id: xxxxxxxxxxxxxxxxxxxxxxxxx
|
|
# secret_key: xxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
|
# url: https://github.com/login/oauth/access_token
|
|
# feishu:
|
|
# app_id: cli_xxxxxxxxxxxxxxxxxxx
|
|
# app_secret: xxxxxxxxxxxxxxxxxxxxxxxxxxxx
|
|
# app_access_token_url: https://open.feishu.cn/open-apis/auth/v3/app_access_token/internal
|
|
# user_access_token_url: https://open.feishu.cn/open-apis/authen/v1/oidc/access_token
|
|
# grant_type: 'authorization_code'
|
|
# authentication:
|
|
# client:
|
|
# switch: false
|
|
# http_app_key:
|
|
# http_secret_key:
|
|
# site:
|
|
# switch: false
|
|
# permission:
|
|
# switch: false
|
|
# component: false
|
|
# dataset: false
|