WrenAI+ollama 本地部署实现自然语言读取数据库

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
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: historical_question_retrieval
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: sql_generation
    llm: litellm_llm.default
    engine: wren_ui
    document_store: qdrant
  - name: sql_correction
    llm: litellm_llm.default
    engine: wren_ui
    document_store: qdrant
  - name: followup_sql_generation
    llm: litellm_llm.default
    engine: wren_ui
    document_store: qdrant
  - name: sql_answer
    llm: litellm_llm.default
  - name: semantics_description
    llm: litellm_llm.default
  - name: relationship_recommendation
    llm: litellm_llm.default
    engine: wren_ui
  - name: question_recommendation
    llm: litellm_llm.default
  - name: question_recommendation_db_schema_retrieval
    llm: litellm_llm.default
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: question_recommendation_sql_generation
    llm: litellm_llm.default
    engine: wren_ui
    document_store: qdrant
  - name: intent_classification
    llm: litellm_llm.default
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: misleading_assistance
    llm: litellm_llm.default
  - name: data_assistance
    llm: litellm_llm.default
  - name: sql_pairs_indexing
    document_store: qdrant
    embedder: litellm_embedder.default
  - name: sql_pairs_retrieval
    document_store: qdrant
    embedder: litellm_embedder.default
    llm: litellm_llm.default
  - name: preprocess_sql_data
    llm: litellm_llm.default
  - name: sql_executor
    engine: wren_ui
  - name: chart_generation
    llm: litellm_llm.default
  - name: chart_adjustment
    llm: litellm_llm.default
  - name: user_guide_assistance
    llm: litellm_llm.default
  - name: sql_question_generation
    llm: litellm_llm.default
  - name: sql_generation_reasoning
    llm: litellm_llm.default
  - name: followup_sql_generation_reasoning
    llm: litellm_llm.default
  - name: sql_regeneration
    llm: litellm_llm.default
    engine: wren_ui
  - name: instructions_indexing
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: instructions_retrieval
    embedder: litellm_embedder.default
    document_store: qdrant
  - name: sql_functions_retrieval
    engine: wren_ibis
    document_store: qdrant
  - name: project_meta_indexing
    document_store: qdrant
  - name: sql_tables_extraction
    llm: litellm_llm.default

---
settings:
  doc_endpoint: https://docs.getwren.ai
  is_oss: true
  engine_timeout: 30
  column_indexing_batch_size: 50
  table_retrieval_size: 10
  table_column_retrieval_size: 100
  allow_intent_classification: true
  allow_sql_generation_reasoning: true
  allow_sql_functions_retrieval: true
  enable_column_pruning: false
  max_sql_correction_retries: 3
  query_cache_maxsize: 1000
  query_cache_ttl: 3600
  langfuse_host: https://cloud.langfuse.com
  langfuse_enable: true
  logging_level: DEBUG
  development: false
  historical_question_retrieval_similarity_threshold: 0.9
  sql_pairs_similarity_threshold: 0.7
  sql_pairs_retrieval_max_size: 10
  instructions_similarity_threshold: 0.7
  instructions_top_k: 10

docker-compose.yaml

version: "3"

volumes:
  data:

networks:
  wren:
    driver: bridge

services:
  bootstrap:
    image: ghcr.io/canner/wren-bootstrap:${WREN_BOOTSTRAP_VERSION}
    restart: on-failure
    platform: ${PLATFORM}
    environment:
      DATA_PATH: /app/data
    volumes:
      - data:/app/data
    command: /bin/sh /app/init.sh

  wren-engine:
    image: ghcr.io/canner/wren-engine:${WREN_ENGINE_VERSION}
    restart: on-failure
    platform: ${PLATFORM}
    expose:
      - ${WREN_ENGINE_PORT}
      - ${WREN_ENGINE_SQL_PORT}
    volumes:
      - data:/usr/src/app/etc
      - ${PROJECT_DIR}/data:/usr/src/app/data
    networks:
      - wren
    depends_on:
      - bootstrap

  ibis-server:
    image: ghcr.io/canner/wren-engine-ibis:${IBIS_SERVER_VERSION}
    restart: on-failure
    platform: ${PLATFORM}
    expose:
      - ${IBIS_SERVER_PORT}
    environment:
      WREN_ENGINE_ENDPOINT: http://wren-engine:${WREN_ENGINE_PORT}
    volumes:
      - ${LOCAL_STORAGE:-.}:/usr/src/app/data
    networks:
      - wren

  wren-ai-service:
    image: ghcr.io/canner/wren-ai-service:${WREN_AI_SERVICE_VERSION}
    restart: no
    platform: ${PLATFORM}
    expose:
      - ${WREN_AI_SERVICE_PORT}
    ports:
      - ${AI_SERVICE_FORWARD_PORT}:${WREN_AI_SERVICE_PORT}
    environment:
      # sometimes the console won't show print messages,
      # using PYTHONUNBUFFERED: 1 can fix this
      PYTHONUNBUFFERED: 1
      CONFIG_PATH: /app/config.yaml
      LOG_LEVEL: DEBUG
      LOGGING_LEVEL: DEBUG
    env_file:
      - ${PROJECT_DIR}/.env
    volumes:
      - ${PROJECT_DIR}/config.yaml:/app/config.yaml:ro
      - ${PROJECT_DIR}/data:/app/data:ro
      - ${PROJECT_DIR}/entrypoint.sh:/app/entrypoint.sh:rw
    networks:
      - wren
    depends_on:
      - qdrant

  qdrant:
    image: qdrant/qdrant:v1.11.0
    restart: on-failure
    expose:
      - 6333
      - 6334
    volumes:
      - data:/qdrant/storage
    networks:
      - wren

  wren-ui:
    image: ghcr.io/canner/wren-ui:${WREN_UI_VERSION}
    restart: on-failure
    platform: ${PLATFORM}
    environment:
      DB_TYPE: sqlite
      # /app is the working directory in the container
      SQLITE_FILE: /app/data/db.sqlite3
      WREN_ENGINE_ENDPOINT: http://wren-engine:${WREN_ENGINE_PORT}
      WREN_AI_ENDPOINT: http://wren-ai-service:${WREN_AI_SERVICE_PORT}
      IBIS_SERVER_ENDPOINT: http://ibis-server:${IBIS_SERVER_PORT}
      # 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: ${GENERATION_MODEL}
      # telemetry
      WREN_ENGINE_PORT: ${WREN_ENGINE_PORT}
      WREN_AI_SERVICE_VERSION: ${WREN_AI_SERVICE_VERSION}
      WREN_UI_VERSION: ${WREN_UI_VERSION}
      WREN_ENGINE_VERSION: ${WREN_ENGINE_VERSION}
      USER_UUID: ${USER_UUID}
      POSTHOG_API_KEY: ${POSTHOG_API_KEY}
      POSTHOG_HOST: ${POSTHOG_HOST}
      TELEMETRY_ENABLED: ${TELEMETRY_ENABLED}
      # client side
      NEXT_PUBLIC_USER_UUID: ${USER_UUID}
      NEXT_PUBLIC_POSTHOG_API_KEY: ${POSTHOG_API_KEY}
      NEXT_PUBLIC_POSTHOG_HOST: ${POSTHOG_HOST}
      NEXT_PUBLIC_TELEMETRY_ENABLED: ${TELEMETRY_ENABLED}
      EXPERIMENTAL_ENGINE_RUST_VERSION: ${EXPERIMENTAL_ENGINE_RUST_VERSION}
      # configs
      WREN_PRODUCT_VERSION: ${WREN_PRODUCT_VERSION}
    ports:
      # HOST_PORT is the port you want to expose to the host machine
      - ${HOST_PORT}:3000
    volumes:
      - data:/app/data
    networks:
      - wren
    depends_on:
      - wren-ai-service
      - wren-engine

entrypoint.sh，此文件映射出来的目的是修改TIMEOUT时间，因为在机器性能不是很强的情况下，wrenai-wren-ai-service 会出现timeout问题，60秒就会自动退出，导致服务无法启动，在本机中设置成100即可正常启动

#!/bin/bash
set -e

INTERVAL=1
TIMEOUT=100

# Wait for qdrant to be responsive
echo "Waiting for qdrant to start..."
current=0

while ! nc -z $QDRANT_HOST 6333; do
    sleep $INTERVAL
    current=$((current + INTERVAL))
    if [ $current -eq $TIMEOUT ]; then
        echo "Timeout: qdrant did not start within $TIMEOUT seconds"
        exit 1
    fi
done
echo "qdrant has started."

# Start wren-ai-service in the background
uvicorn src.__main__:app --host 0.0.0.0 --port $WREN_AI_SERVICE_PORT --loop uvloop --http httptools &

if [[ -n "$SHOULD_FORCE_DEPLOY" ]]; then

    # Wait for the server to be responsive
    echo "Waiting for wren-ai-service to start..."
    current=0

    while ! nc -z localhost $WREN_AI_SERVICE_PORT; do
        sleep $INTERVAL
        current=$((current + INTERVAL))
        if [ $current -eq $TIMEOUT ]; then
            echo "Timeout: wren-ai-service did not start within $TIMEOUT seconds"
            exit 1
        fi
    done
    echo "wren-ai-service has started."

    # Wait for wren-ui to be responsive
    echo "Waiting for wren-ui to start..."
    current=0

    while ! nc -z wren-ui $WREN_UI_PORT && ! nc -z host.docker.internal $WREN_UI_PORT; do
        sleep $INTERVAL
        current=$((current + INTERVAL))
        if [ $current -eq $TIMEOUT ]; then
            echo "Timeout: wren-ui did not start within $TIMEOUT seconds"
            exit 1
        fi
    done
    echo "wren-ui has started."

    echo "Forcing deployment..."
    python -m src.force_deploy
fi

# Bring wren-ai-service to the foreground
wait

进入到工作目录，使用命令行运行，docker-compose up -d,首次会下拉相关镜像,启动成功后如图：

运行localhost:3000,根据官网进行数据库配置，模型配置，完成部署：