panda
70614dff5e
Major changes: - Streaming: LLM统一 _BaseLLM 接口 (invoke + stream), generate/modify/correct 节点使用 get_stream_writer() 实现逐字输出, UI 节点平铺展开自动折叠 - Prompt外部化: 7个prompt拆分到 prompts/*.md, loader.py 支持热重载 - 错误自增长: backend/error_kb.py — 指纹去重 + ChromaDB持久化, correct_jrxml→validate 通过时自动入库, retrieve同时搜索错误KB - 文件上传: backend/file_parser.py — PDF/DOCX/图片/文本解析, 侧边栏多文件上传, 文本自动注入下一条消息 - A4模板识别: backend/layout_analyzer.py — 三种模式(完整A4/行片段修改/行片段新建), PaddleOCR元素提取 + 行分组 + JRXML section匹配 - 会话历史下载: jrxml_versions版本追踪 + 侧边栏历史版本下载按钮 - 预览修复: route_after_save跳过预览/导出意图的验证循环 - Ctrl+C修复: JS注入拦截Streamlit裸c键清缓存 Docs: CLAUDE.md (完整项目文档), ROADMAP.md (改进路线图) Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
106 lines
3.4 KiB
Python
106 lines
3.4 KiB
Python
"""大语言模型工厂：支持 OpenAI 兼容的云端 API、Anthropic 兼容 API 和本地 Ollama。"""
|
|
|
|
import os
|
|
from typing import Any
|
|
|
|
from dotenv import load_dotenv
|
|
|
|
load_dotenv()
|
|
|
|
|
|
class _BaseLLM:
|
|
"""LLM 统一接口基类 — 所有后端都提供 invoke() 和 stream()。"""
|
|
|
|
def invoke(self, prompt: str) -> Any:
|
|
raise NotImplementedError
|
|
|
|
def stream(self, prompt: str):
|
|
raise NotImplementedError
|
|
|
|
|
|
def get_llm():
|
|
backend = os.getenv("LLM_BACKEND", "cloud")
|
|
if backend == "local":
|
|
from langchain_ollama import ChatOllama
|
|
|
|
model = os.getenv("LOCAL_LLM_MODEL", "qwen2.5-coder:7b")
|
|
raw = ChatOllama(model=model, temperature=0.1)
|
|
|
|
class OllamaWrapper(_BaseLLM):
|
|
def invoke(self, prompt):
|
|
return raw.invoke(prompt)
|
|
|
|
def stream(self, prompt):
|
|
for chunk in raw.stream(prompt):
|
|
yield chunk.content
|
|
|
|
return OllamaWrapper()
|
|
|
|
provider = os.getenv("LLM_PROVIDER", "openai")
|
|
if provider == "anthropic":
|
|
from anthropic import Anthropic
|
|
|
|
api_key = os.getenv("OPENAI_API_KEY", "")
|
|
base_url = os.getenv("OPENAI_BASE_URL", "https://api.minimaxi.com/anthropic")
|
|
model = os.getenv("LLM_MODEL", "minimax-2.7")
|
|
temperature = 0.1
|
|
max_tokens = 4096
|
|
|
|
os.environ["NO_PROXY"] = "*"
|
|
|
|
client = Anthropic(api_key=api_key, base_url=base_url, timeout=120)
|
|
|
|
class MiniMaxLLM(_BaseLLM):
|
|
def invoke(self, prompt: str) -> Any:
|
|
resp = client.messages.create(
|
|
model=model,
|
|
max_tokens=max_tokens,
|
|
temperature=temperature,
|
|
messages=[{"role": "user", "content": [{"type": "text", "text": prompt}]}],
|
|
)
|
|
for block in resp.content:
|
|
if block.type == "text":
|
|
return type("Response", (), {"content": block.text})()
|
|
return type("Response", (), {"content": ""})()
|
|
|
|
def stream(self, prompt: str):
|
|
with client.messages.stream(
|
|
model=model,
|
|
max_tokens=max_tokens,
|
|
temperature=temperature,
|
|
messages=[{"role": "user", "content": [{"type": "text", "text": prompt}]}],
|
|
) as s:
|
|
for text in s.text_stream:
|
|
yield text
|
|
|
|
def get_num_tokens(self, text: str) -> int:
|
|
resp = client.messages.count_tokens(
|
|
model=model,
|
|
messages=[{"role": "user", "content": [{"type": "text", "text": text}]}],
|
|
)
|
|
return resp.input_tokens
|
|
|
|
return MiniMaxLLM()
|
|
else:
|
|
from langchain_openai import ChatOpenAI
|
|
|
|
raw = ChatOpenAI(
|
|
model=os.getenv("LLM_MODEL", "gpt-4o"),
|
|
api_key=os.getenv("OPENAI_API_KEY"),
|
|
base_url=os.getenv("OPENAI_BASE_URL", "https://api.openai.com/v1"),
|
|
temperature=0.1,
|
|
)
|
|
|
|
class OpenAIWrapper(_BaseLLM):
|
|
def invoke(self, prompt):
|
|
return raw.invoke(prompt)
|
|
|
|
def stream(self, prompt):
|
|
for chunk in raw.stream(prompt):
|
|
yield chunk.content
|
|
|
|
return OpenAIWrapper()
|
|
|
|
|
|
def get_llm_for_correction():
|
|
return get_llm() |