WrenAI+ollama 本地部署实现自然语言读取数据库

原创

已于 2025-11-10 12:32:14 修改 · 434 阅读

2 ·

CC 4.0 BY-SA版权

文章标签：

#语言模型 #自然语言处理

于 2025-11-10 12:31:44 首次发布

WrenAI+Ollama 本地部署实现自然语言读取数据库

作者:coder_fang

WrenAI 是开源且比较成熟的SQL AI，可以使用Ollama本地模型进行部署，本文是作者多次踩坑后能正确运行的配置,相比官网进行了少许改动。
运行环境:Wrenai:0.27.0,ollama:0.12.5,Windows11 Docker Desktop，3080TI显卡

安装Desktop Docker ,Ollama，本文需要的模型有：qwen2.5:14b，nomic-embed-text:latest，使用ollama pull进行下拉。
创建wren工作目录，目录结构如图：
.env

COMPOSE_PROJECT_NAME=wrenai
PLATFORM=linux/amd64

PROJECT_DIR=.

# service port
WREN_ENGINE_PORT=8080
WREN_ENGINE_SQL_PORT=7432
WREN_AI_SERVICE_PORT=5555
WREN_UI_PORT=3000
IBIS_SERVER_PORT=8000
WREN_UI_ENDPOINT=http://wren-ui:${
   
   WREN_UI_PORT}

# ai service settings
QDRANT_HOST=qdrant
SHOULD_FORCE_DEPLOY=1

EMBEDDER_OLLAMA_URL=192.168.1.37
EMBEDDING_MODEL=nomic-embed-text
# vendor keys
OPENAI_API_KEY=

# version
# CHANGE THIS TO THE LATEST VERSION
WREN_PRODUCT_VERSION=0.27.0
WREN_ENGINE_VERSION=0.18.3
WREN_AI_SERVICE_VERSION=0.27.1
IBIS_SERVER_VERSION=0.18.3
WREN_UI_VERSION=0.31.1
WREN_BOOTSTRAP_VERSION=0.1.5

# user id (uuid v4)
USER_UUID=

# for other services
POSTHOG_API_KEY=phc_nhF32aj4xHXOZb0oqr2cn4Oy9uiWzz6CCP4KZmRq9aE
POSTHOG_HOST=https://app.posthog.com
TELEMETRY_ENABLED=true
# this is for telemetry to know the model, i think ai-service might be able to provide a endpoint to get the information
GENERATION_MODEL=gpt-4o-mini
LANGFUSE_SECRET_KEY=
LANGFUSE_PUBLIC_KEY=

# the port exposes to the host
# OPTIONAL: change the port if you have a conflict
HOST_PORT=3000
AI_SERVICE_FORWARD_PORT=5555

# Wren UI
EXPERIMENTAL_ENGINE_RUST_VERSION=false

# Wren Engine
# OPTIONAL: set if you want to use local storage for the Wren Engine
LOCAL_STORAGE=.

config.yaml

type: llm
provider: litellm_llm
models:
  - api_base: http://host.docker.internal:11434 # if you are using mac/windows, don't change this; if you are using linux, please search "Run Ollama in docker container" in this page: https://docs.getwren.ai/oss/installation/custom_llm#running-wren-ai-with-your-custom-llm-embedder
    model: ollama_chat/qwen2.5-coder:14b    # ollama_chat/<ollama_model_name>
    timeout: 600
    alias: default
    kwargs:
      n: 1
      temperature: 0
---
type: embedder
provider: litellm_embedder
models:
  - model: ollama/nomic-embed-text  # put your ollama embedder model name here, openai/<ollama_model_name>
    api_base: http://host.docker.internal:11434  # if you are using mac/windows, don't change this; if you are using linux, please search "Run Ollama in docker container" in this page: https://docs.getwren.ai/oss/installation/custom_llm#running-wren-ai-with-your-custom-llm-embedder
    timeout: 600
    alias: default
---
type: engine
provider: wren_ui
endpoint: http://wren-ui:3000

---
type: engine
provider: wren_ibis
endpoint: http://ibis-server:8000

---
type: document_store
provider: qdrant
location: http://qdrant:6333
embedding_model_dim: 768
timeout: 120
recreate_index: true

---
type: pipeline
pipes:
  - name: db_schema_indexing
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: historical_question_indexing
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: table_description_indexing
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: db_schema_retrieval
    llm: litellm_llm.default