History

MerCry 7027097513 [AC-AISVC-RES-01~15] feat(retrieval): 实现检索策略Pipeline模块 - 新增策略配置模型 (config.py) - GrayscaleConfig: 灰度发布配置 - ModeRouterConfig: 模式路由配置 - MetadataInferenceConfig: 元数据推断配置 - 新增 Pipeline 实现 - DefaultPipeline: 复用现有 OptimizedRetriever 逻辑 - EnhancedPipeline: Dense + Keyword + RRF 组合检索 - 新增路由器 - StrategyRouter: 策略路由器（default/enhanced） - ModeRouter: 模式路由器（direct/react/auto） - 新增 RollbackManager: 回退与审计管理器 - 新增 MetadataInferenceService: 元数据推断统一入口 - 新增单元测试 (51 passed)		2026-03-10 20:50:16 +08:00
..
app	[AC-AISVC-RES-01~15] feat(retrieval): 实现检索策略Pipeline模块	2026-03-10 20:50:16 +08:00
docs/progress	feat(v0.7.0): 验收通过 - Dashboard统计增强、流程测试、对话追踪	2026-02-28 12:52:50 +08:00
exports	feat(v0.7.0): 验收通过 - Dashboard统计增强、流程测试、对话追踪	2026-02-28 12:52:50 +08:00
migrations	test: add unit tests and utility scripts for intent routing, slot management, and KB search [AC-TEST]	2026-03-10 12:10:22 +08:00
scripts	test: add unit tests and utility scripts for intent routing, slot management, and KB search [AC-TEST]	2026-03-10 12:10:22 +08:00
tests	[AC-AISVC-RES-01~15] feat(retrieval): 实现检索策略Pipeline模块	2026-03-10 20:50:16 +08:00
tools	chore: add utility scripts and tool definitions for KB search and metadata testing [AC-UTILS]	2026-03-10 12:11:55 +08:00
.dockerignore	feat: 添加Docker容器部署配置 [AC-AISVC-01]	2026-02-26 01:22:30 +08:00
Dockerfile	fix: Docker构建时复制README.md文件 [AC-AISVC-01]	2026-02-26 02:13:26 +08:00
README.md	feat(AISVC-T7): 嵌入模型可插拔设计与文档解析支持 [AC-AISVC-29, AC-AISVC-30, AC-AISVC-31, AC-AISVC-32, AC-AISVC-33, AC-AISVC-34, AC-AISVC-35, AC-AISVC-36, AC-AISVC-37, AC-AISVC-38, AC-AISVC-39, AC-AISVC-40, AC-AISVC-41]	2026-02-24 23:08:08 +08:00
check_kb_collections.py	chore: add utility scripts and tool definitions for KB search and metadata testing [AC-UTILS]	2026-03-10 12:11:55 +08:00
check_qdrant.py	chore: add utility scripts and tool definitions for KB search and metadata testing [AC-UTILS]	2026-03-10 12:11:55 +08:00
pyproject.toml	feat(v0.7.0): 验收通过 - Dashboard统计增强、流程测试、对话追踪	2026-02-28 12:52:50 +08:00
test_kb_metadata_search.py	chore: add utility scripts and tool definitions for KB search and metadata testing [AC-UTILS]	2026-03-10 12:11:55 +08:00
test_kb_search_with_metadata.py	chore: add utility scripts and tool definitions for KB search and metadata testing [AC-UTILS]	2026-03-10 12:11:55 +08:00
test_metadata_filter_only.py	chore: add utility scripts and tool definitions for KB search and metadata testing [AC-UTILS]	2026-03-10 12:11:55 +08:00

README.md

AI Service

Python AI Service for intelligent chat with RAG support.

Features

Multi-tenant isolation via X-Tenant-Id header
SSE streaming support via Accept: text/event-stream
RAG-powered responses with confidence scoring

Prerequisites

PostgreSQL 12+
Qdrant vector database
Python 3.10+

Installation

pip install -e ".[dev]"

Database Initialization

Option 1: Using Python script (Recommended)

# Create database and tables
python scripts/init_db.py --create-db

# Or just create tables (database must exist)
python scripts/init_db.py

Option 2: Using SQL script

# Connect to PostgreSQL and run
psql -U postgres -f scripts/init_db.sql

Configuration

Create a .env file in the project root:

AI_SERVICE_DATABASE_URL=postgresql+asyncpg://postgres:password@localhost:5432/ai_service
AI_SERVICE_QDRANT_URL=http://localhost:6333
AI_SERVICE_LLM_API_KEY=your-api-key
AI_SERVICE_LLM_BASE_URL=https://api.openai.com/v1
AI_SERVICE_LLM_MODEL=gpt-4o-mini
AI_SERVICE_DEBUG=true

Running

uvicorn app.main:app --host 0.0.0.0 --port 8000

API Endpoints

Chat API

POST /ai/chat - Generate AI reply (supports SSE streaming)
GET /ai/health - Health check

Admin API

GET /admin/kb/documents - List documents
POST /admin/kb/documents - Upload document
GET /admin/kb/index/jobs/{jobId} - Get indexing job status
DELETE /admin/kb/documents/{docId} - Delete document
POST /admin/rag/experiments/run - Run RAG experiment
GET /admin/sessions - List chat sessions
GET /admin/sessions/{sessionId} - Get session details