Files
ailine/backend/requirements.txt
root b5c15ef445
All checks were successful
构建并部署 AI Agent 服务 / deploy (push) Successful in 12m9s
refactor: 单图方案重构 + 动态模型选择 + chat_services优化
## 核心改动

### 1. 单图方案重构
- 删除了多图(self.graphs),改为单图(self.graph)
- 新增 MainGraphState.current_model 字段用于运行时注入模型
- llm_call 节点改为动态选择模型(create_dynamic_llm_call_node)

### 2. chat_services 优化
- 添加 _cached_services 缓存,避免重复初始化
- 新增 get_cached_chat_services() 函数,用于单图注入
- 新增 _check_http_service_available() 统一HTTP探测逻辑
- 减少重复代码,LocalVLLMChatProvider和LocalSmallModelProvider共用探测方法

### 3. AIAgentService 重构
- initialize() 只构建一次图,传入 chat_services 字典
- 新增 _resolve_model() 模型回退逻辑
- 新增 _build_invocation() 统一构建调用参数
- process_message() 和 process_message_stream() 改为注入 current_model
- 流式处理代码拆分,增加可读性

### 4. 新增和删除文件
- 新增:backend/app/main_graph/main_graph_builder.py(图构建)
- 新增:backend/app/main_graph/subgraph_wrapper.py(子图封装)
- 新增:tools/test/test_tavily_search.py(测试)
- 删除:backend/app/main_graph/graph.py(旧图)
- 删除:backend/app/main_graph/utils/main_graph_builder.py(旧构建器)
- 删除:backend/app/main_graph/utils/__init__.py

### 5. 其他更新
- README.md:新增模型服务使用情况详解章节
- backend/app/model_services/__init__.py:新增 get_cached_chat_services 导出

## 方案优势

- 内存优化:N张图 → 1张图
- 灵活性:运行时动态选择模型,支持同会话不同模型
- 性能:模型服务缓存,初始化仅一次
- 可维护性:减少重复代码,统一HTTP探测逻辑
2026-05-05 17:30:55 +08:00

53 lines
1003 B
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

typing-extensions>=4.15.0
python-dotenv>=1.2.2
pydantic>=2.12.5
requests>=2.32.5
# LangChain
langchain>=1.2.15
langchain-community>=0.4.1
langchain-core>=1.2.28
langchain-openai>=1.1.12
langchain-qdrant>=1.1.0
langgraph>=1.1.6
langgraph-checkpoint-postgres>=3.0.5
tiktoken>=0.12.0
# Zhipu AI
zhipuai>=2.0.1
# Vector DB
qdrant-client>=1.17.1
fastembed>=0.3.0 # 用于 Qdrant BM25 稀疏向量
# Memory
mem0ai>=1.0.11
# Backend
fastapi>=0.135.3
uvicorn[standard]>=0.44.0
# Database
asyncpg>=0.31.0
psycopg[binary]>=3.3.3
# HTTP
httpx>=0.28.1
aiohttp>=3.13.5
# Utilities
tenacity>=9.1.4
rich>=15.0.0
PyYAML>=6.0.3
numpy>=1.26.2
pyjwt>=2.8.0
ddgs>=6.0.0 # 免费联网搜索(原 duckduckgo-search 已重命名)
tavily-python>=0.5.0 # Tavily 搜索 API需要 API Key质量更高
matplotlib>=3.9.0 # 可视化图表
# Document Processing
unstructured>=0.22.21
pypdf>=6.10.0
beautifulsoup4>=4.14.3
lxml>=6.1.0
spacy>=3.8.14 # unstructured 可能依赖