From aa805dddbbe347773544c3b19cdb15d266177412 Mon Sep 17 00:00:00 2001 From: HuangHai <10402852@qq.com> Date: Fri, 18 Jul 2025 15:07:20 +0800 Subject: [PATCH 1/2] 'commit' --- .../Config/__pycache__/Config.cpython-310.pyc | Bin 1016 -> 1016 bytes dsLightRag/Start.py | 341 ------------------ .../JiHe/kv_store_llm_response_cache.json | 13 + dsLightRag/WxGzh/T1_LoginGetCookie.py | 78 ---- dsLightRag/WxGzh/T2_CollectArticle.py | 251 ------------- dsLightRag/WxGzh/__init__.py | 0 dsLightRag/WxGzh/cookies.txt | 17 - 7 files changed, 13 insertions(+), 687 deletions(-) delete mode 100644 dsLightRag/Start.py delete mode 100644 dsLightRag/WxGzh/T1_LoginGetCookie.py delete mode 100644 dsLightRag/WxGzh/T2_CollectArticle.py delete mode 100644 dsLightRag/WxGzh/__init__.py delete mode 100644 dsLightRag/WxGzh/cookies.txt diff --git a/dsLightRag/Config/__pycache__/Config.cpython-310.pyc b/dsLightRag/Config/__pycache__/Config.cpython-310.pyc index 19f47c1d661a24f05df6d906d0d504091866ce4c..d65c6fc0e751164ce5f1051783dd671f30522d1f 100644 GIT binary patch delta 19 Zcmeyt{)3$>pO=@50SHpwZRC2#3;;L#1)2Z= delta 19 Zcmeyt{)3$>pO=@50SIj0ZsdB$3;;I_1#$oY diff --git a/dsLightRag/Start.py b/dsLightRag/Start.py deleted file mode 100644 index cfa584c2..00000000 --- a/dsLightRag/Start.py +++ /dev/null @@ -1,341 +0,0 @@ -import json -import subprocess -import tempfile -import urllib -import uuid -from io import BytesIO - -import fastapi -import uvicorn -from fastapi import FastAPI, HTTPException -from lightrag import QueryParam -from sse_starlette import EventSourceResponse -from starlette.responses import StreamingResponse -from starlette.staticfiles import StaticFiles - -from Util.LightRagUtil import * -from Util.PostgreSQLUtil import init_postgres_pool - -# 更详细地控制日志输出 -logger = logging.getLogger('lightrag') -logger.setLevel(logging.INFO) -handler = logging.StreamHandler() -handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')) -logger.addHandler(handler) - - -async def lifespan(app: FastAPI): - yield - -app = FastAPI(lifespan=lifespan) - -# 挂载静态文件目录 -app.mount("/static", StaticFiles(directory="Static"), name="static") - - -@app.post("/api/rag") -async def rag(request: fastapi.Request): - data = await request.json() - topic = data.get("topic") # Chinese, Math - mode = data.get("mode", "hybrid") # 默认为hybrid模式 - # 拼接路径 - WORKING_PATH = "./Topic/" + topic - # 查询的问题 - query = data.get("query") - # 关闭参考资料 - user_prompt = "\n 1、不要输出参考资料 或者 References ！" - user_prompt = user_prompt + "\n 2、资料中提供化学反应方程式的，严格按提供的Latex公式输出，绝不允许对Latex公式进行修改！" - user_prompt = user_prompt + "\n 3、如果资料中提供了图片的，需要仔细检查图片下方描述文字是否与主题相关,不相关的不要提供！相关的一定要严格按照原文提供图片输出，不允许省略或不输出！" - user_prompt = user_prompt + "\n 4、如果问题与提供的知识库内容不符，则明确告诉未在知识库范围内提到！" - user_prompt = user_prompt + "\n 5、发现输出内容中包含Latex公式的，一定要检查是不是包含了$$或$的包含符号,不能让Latex无包含符号出现！" - - async def generate_response_stream(query: str): - try: - rag = await initialize_rag(WORKING_PATH) - await rag.initialize_storages() - await initialize_pipeline_status() - resp = await rag.aquery( - query=query, - param=QueryParam(mode=mode, stream=True, user_prompt=user_prompt, enable_rerank=True)) - - async for chunk in resp: - if not chunk: - continue - yield f"data: {json.dumps({'reply': chunk})}\n\n" - print(chunk, end='', flush=True) - except Exception as e: - yield f"data: {json.dumps({'error': str(e)})}\n\n" - finally: - # 清理资源 - await rag.finalize_storages() - - return EventSourceResponse(generate_response_stream(query=query)) - - -@app.post("/api/save-word") -async def save_to_word(request: fastapi.Request): - output_file = None - try: - # Parse request data - try: - data = await request.json() - markdown_content = data.get('markdown_content', '') - if not markdown_content: - raise ValueError("Empty MarkDown content") - except Exception as e: - logger.error(f"Request parsing failed: {str(e)}") - raise HTTPException(status_code=400, detail=f"Invalid request: {str(e)}") - - # 创建临时Markdown文件 - temp_md = os.path.join(tempfile.gettempdir(), uuid.uuid4().hex + ".md") - with open(temp_md, "w", encoding="utf-8") as f: - f.write(markdown_content) - - # 使用pandoc转换 - output_file = os.path.join(tempfile.gettempdir(), "【理想大模型】问答.docx") - subprocess.run(['pandoc', temp_md, '-o', output_file, '--resource-path=static'], check=True) - - # 读取生成的Word文件 - with open(output_file, "rb") as f: - stream = BytesIO(f.read()) - - # 返回响应 - encoded_filename = urllib.parse.quote("【理想大模型】问答.docx") - return StreamingResponse( - stream, - media_type="application/vnd.openxmlformats-officedocument.wordprocessingml.document", - headers={"Content-Disposition": f"attachment; filename*=UTF-8''{encoded_filename}"}) - - except HTTPException: - raise - except Exception as e: - logger.error(f"Unexpected error: {str(e)}") - raise HTTPException(status_code=500, detail="Internal server error") - finally: - # 清理临时文件 - try: - if temp_md and os.path.exists(temp_md): - os.remove(temp_md) - if output_file and os.path.exists(output_file): - os.remove(output_file) - except Exception as e: - logger.warning(f"Failed to clean up temp files: {str(e)}") - - -@app.get("/api/tree-data") -async def get_tree_data(): - try: - pg_pool = await init_postgres_pool() - async with pg_pool.acquire() as conn: - # 执行查询 - rows = await conn.fetch(""" - SELECT id, - title, - parent_id, - is_leaf, - prerequisite, - related - FROM knowledge_points - ORDER BY parent_id, id - """) - # 构建节点映射 - nodes = {} - for row in rows: - prerequisite_data = json.loads(row[4]) if row[4] else [] - # 转换先修知识格式 - if isinstance(prerequisite_data, list) and len(prerequisite_data) > 0 and isinstance(prerequisite_data[0], - dict): - # 已经是新格式 - prerequisites = prerequisite_data - else: - # 转换为新格式 - prerequisites = [{"id": str(id), "title": title} for id, title in - (prerequisite_data or [])] if prerequisite_data else None - - nodes[row[0]] = { - "id": row[0], - "title": row[1], - "parent_id": row[2] if row[2] is not None else 0, - "isParent": not row[3], - "prerequisite": prerequisites if prerequisites and len(prerequisites) > 0 else None, - "related": json.loads(row[5]) if row[5] and len(json.loads(row[5])) > 0 else None, - "open": True - } - - # 构建树形结构 - tree_data = [] - for node_id, node in nodes.items(): - parent_id = node["parent_id"] - if parent_id == 0: - tree_data.append(node) - else: - if parent_id in nodes: - if "children" not in nodes[parent_id]: - nodes[parent_id]["children"] = [] - nodes[parent_id]["children"].append(node) - - return {"code": 0, "data": tree_data} - except Exception as e: - return {"code": 1, "msg": str(e)} - - -@app.post("/api/update-knowledge") -async def update_knowledge(request: fastapi.Request): - try: - data = await request.json() - node_id = data.get('node_id') - knowledge = data.get('knowledge', []) - update_type = data.get('update_type', 'prerequisite') # 默认为先修知识 - - if not node_id: - raise ValueError("Missing node_id") - - pg_pool = await init_postgres_pool() - async with pg_pool.acquire() as conn: - if update_type == 'prerequisite': - await conn.execute(""" - UPDATE knowledge_points - SET prerequisite = $1 - WHERE id = $2 - """, - json.dumps( - [{"id": p["id"], "title": p["title"]} for p in knowledge], - ensure_ascii=False - ), - node_id) - else: # related knowledge - await conn.execute(""" - UPDATE knowledge_points - SET related = $1 - WHERE id = $2 - """, - json.dumps( - [{"id": p["id"], "title": p["title"]} for p in knowledge], - ensure_ascii=False - ), - node_id) - - return {"code": 0, "msg": "更新成功"} - except Exception as e: - logger.error(f"更新知识失败: {str(e)}") - return {"code": 1, "msg": str(e)} - - -@app.post("/api/render_html") -async def render_html(request: fastapi.Request): - data = await request.json() - html_content = data.get('html_content') - html_content = html_content.replace("```html", "") - html_content = html_content.replace("```", "") - # 创建临时文件 - filename = f"relation_{uuid.uuid4().hex}.html" - filepath = os.path.join('../static/temp', filename) - - # 确保temp目录存在 - os.makedirs('../static/temp', exist_ok=True) - - # 写入文件 - with open(filepath, 'w', encoding='utf-8') as f: - f.write(html_content) - - return { - 'success': True, - 'url': f'/static/temp/{filename}' - } - - -@app.get("/api/sources") -async def get_sources(page: int = 1, limit: int = 10): - try: - pg_pool = await init_postgres_pool() - async with pg_pool.acquire() as conn: - # 获取总数 - total = await conn.fetchval("SELECT COUNT(*) FROM t_wechat_source") - # 获取分页数据 - offset = (page - 1) * limit - rows = await conn.fetch( - """ - SELECT id, account_id, account_name, created_at - FROM t_wechat_source - ORDER BY created_at DESC - LIMIT $1 - OFFSET $2 - """, - limit, offset - ) - - sources = [ - { - "id": row[0], - "name": row[1], - "type": row[2], - "update_time": row[3].strftime("%Y-%m-%d %H:%M:%S") if row[3] else None - } - for row in rows - ] - - return { - "code": 0, - "data": { - "list": sources, - "total": total, - "page": page, - "limit": limit - } - } - except Exception as e: - return {"code": 1, "msg": str(e)} - - -@app.get("/api/articles") -async def get_articles(page: int = 1, limit: int = 10): - try: - pg_pool = await init_postgres_pool() - async with pg_pool.acquire() as conn: - # 获取总数 - total = await conn.fetchval("SELECT COUNT(*) FROM t_wechat_articles") - # 获取分页数据 - offset = (page - 1) * limit - rows = await conn.fetch( - """ - SELECT a.id, - a.title, - a.source as name, - a.publish_time, - a.collection_time, - a.url - FROM t_wechat_articles a - ORDER BY a.collection_time DESC - LIMIT $1 - OFFSET $2 - """, - limit, offset - ) - - articles = [ - { - "id": row[0], - "title": row[1], - "source": row[2], - "publish_date": row[3].strftime("%Y-%m-%d") if row[3] else None, - "collect_time": row[4].strftime("%Y-%m-%d %H:%M:%S") if row[4] else None, - "url": row[5], - } - for row in rows - ] - - return { - "code": 0, - "data": { - "list": articles, - "total": total, - "page": page, - "limit": limit - } - } - except Exception as e: - return {"code": 1, "msg": str(e)} - - -if __name__ == "__main__": - uvicorn.run(app, host="0.0.0.0", port=8000) diff --git a/dsLightRag/Topic/JiHe/kv_store_llm_response_cache.json b/dsLightRag/Topic/JiHe/kv_store_llm_response_cache.json index aaa8518c..d4b77ba4 100644 --- a/dsLightRag/Topic/JiHe/kv_store_llm_response_cache.json +++ b/dsLightRag/Topic/JiHe/kv_store_llm_response_cache.json @@ -537,5 +537,18 @@ "create_time": 1752818371, "update_time": 1752818371, "_id": "hybrid:keywords:37a1721ae1b1e0a8858a85a94a139d9a" + }, + "hybrid:keywords:6d5e4e5a7a264a947d2e6e9cb8befec7": { + "return": "{\"high_level_keywords\": [\"\\u51e0\\u4f55\\u8bc1\\u660e\", \"\\u4e09\\u89d2\\u5f62\", \"\\u5185\\u90e8\\u70b9\", \"\\u89d2\\u5ea6\\u5173\\u7cfb\"], \"low_level_keywords\": [\"\\u4e09\\u89d2\\u5f62ABC\", \"\\u70b9P\", \"\\u2220BPC\", \"\\u2220A\"]}", + "cache_type": "keywords", + "chunk_id": null, + "embedding": null, + "embedding_shape": null, + "embedding_min": null, + "embedding_max": null, + "original_prompt": "求证：在三角形ABC中，P为其内部任意一点。请证明：∠BPC > ∠A。", + "create_time": 1752821457, + "update_time": 1752821457, + "_id": "hybrid:keywords:6d5e4e5a7a264a947d2e6e9cb8befec7" } } \ No newline at end of file diff --git a/dsLightRag/WxGzh/T1_LoginGetCookie.py b/dsLightRag/WxGzh/T1_LoginGetCookie.py deleted file mode 100644 index 83eb3e0d..00000000 --- a/dsLightRag/WxGzh/T1_LoginGetCookie.py +++ /dev/null @@ -1,78 +0,0 @@ -# 详解（一）Python + Selenium 批量采集微信公众号，搭建自己的微信公众号每日AI简报，告别信息焦虑 -# https://blog.csdn.net/k352733625/article/details/149222945 - -# 微信爬爬猫---公众号文章抓取代码分析 -# https://blog.csdn.net/yajuanpi4899/article/details/121584268 - -import json -import logging - -from torch.distributed.elastic.timer import expires - -""" -# 查看selenium版本 -pip show selenium -4.34.2 - -# 查看Chrome浏览器版本 -chrome://version/ -138.0.7204.101 (正式版本) （64 位） - -# 下载驱动包 -https://googlechromelabs.github.io/chrome-for-testing/ -https://storage.googleapis.com/chrome-for-testing-public/138.0.7204.94/win64/chromedriver-win64.zip -""" -import time -from selenium import webdriver -from selenium.webdriver.chrome.options import Options -from selenium.webdriver.chrome.service import Service as ChromeService - -if __name__ == '__main__': - # 定义一个空的字典，存放cookies内容 - cookies = {} - # 设置headers - 使用微信内置浏览器的User-Agent - header = { - "HOST": "mp.weixin.qq.com", - "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36 QBCore/4.0.1301.400 QQBrowser/9.0.2524.400 Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2875.116 Safari/537.36 NetType/WIFI MicroMessenger/7.0.20.1781(0x6700143B) WindowsWechat(0x63010200)", - "Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8", - "Accept-Encoding": "gzip, deflate, br", - "Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.6,en;q=0.5;q=0.4", - "Connection": "keep-alive" - } - # 用webdriver启动谷歌浏览器 - logging.info("启动浏览器，打开微信公众号登录界面") - options = Options() - - service = ChromeService(executable_path=r"C:\Windows\System32\chromedriver.exe") - driver = webdriver.Chrome(service=service, options=options) - # 打开微信公众号登录页面 - driver.get('https://mp.weixin.qq.com/') - # 等待5秒钟 - time.sleep(2) - # # 拿手机扫二维码！ - logging.info("请拿手机扫码二维码登录公众号") - time.sleep(20) - - # 重新载入公众号登录页，登录之后会显示公众号后台首页，从这个返回内容中获取cookies信息 - driver.get('https://mp.weixin.qq.com/') - # 获取cookies - cookie_items = driver.get_cookies() - expiry=-1 - # 获取到的cookies是列表形式，将cookies转成json形式并存入本地名为cookie的文本中 - for cookie_item in cookie_items: - cookies[cookie_item['name']] = cookie_item['value'] - if('expiry' in cookie_item and cookie_item['expiry'] > expiry): - expiry = cookie_item['expiry'] - - if "slave_sid" not in cookies: - logging.info("登录公众号失败，获取cookie失败") - exit() - - # 将cookies写入文件 - cookies["expiry"] = expiry - with open('cookies.txt', mode='w', encoding="utf-8") as f: - f.write(json.dumps(cookies, indent=4, ensure_ascii=False)) - # 关闭浏览器 - driver.quit() - # 输出提示 - print("成功获取了cookies内容！") diff --git a/dsLightRag/WxGzh/T2_CollectArticle.py b/dsLightRag/WxGzh/T2_CollectArticle.py deleted file mode 100644 index 6ea92942..00000000 --- a/dsLightRag/WxGzh/T2_CollectArticle.py +++ /dev/null @@ -1,251 +0,0 @@ -# 详解（一）Python + Selenium 批量采集微信公众号，搭建自己的微信公众号每日AI简报，告别信息焦虑 -# https://blog.csdn.net/k352733625/article/details/149222945 - -# 微信爬爬猫---公众号文章抓取代码分析 -# https://blog.csdn.net/yajuanpi4899/article/details/121584268 - -""" -# 查看selenium版本 -pip show selenium -4.34.2 - -# 查看Chrome浏览器版本 -chrome://version/ -138.0.7204.101 (正式版本) （64 位） - -# 下载驱动包 -https://googlechromelabs.github.io/chrome-for-testing/ -https://storage.googleapis.com/chrome-for-testing-public/138.0.7204.94/win64/chromedriver-win64.zip -""" -import asyncio -import datetime -import json -import logging -import random -import re -import time - -import requests -from selenium.webdriver.chrome.options import Options - -from Util.LightRagUtil import initialize_pg_rag, initialize_rag -from Util.PostgreSQLUtil import init_postgres_pool -from Util.WxGzhUtil import init_wechat_browser, get_article_content - -# 删除重复的日志配置，只保留以下内容 -logger = logging.getLogger('WxGzh') -logger.setLevel(logging.INFO) - -# 确保只添加一个handler -if not logger.handlers: - handler = logging.StreamHandler() - handler.setFormatter(logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')) - logger.addHandler(handler) - -# 添加微信请求头 -header = { - 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36', - 'Referer': 'https://mp.weixin.qq.com/' -} - -async def get_wechat_sources(): - """从t_wechat_source表获取微信公众号列表""" - try: - pool = await init_postgres_pool() - async with pool.acquire() as conn: - rows = await conn.fetch('SELECT * FROM t_wechat_source') - return [dict(row) for row in rows] - finally: - await pool.close() - - -async def is_article_exist(pool, article_url): - """检查文章URL是否已存在数据库中""" - try: - async with pool.acquire() as conn: - row = await conn.fetchrow(''' - SELECT 1 - FROM t_wechat_articles - WHERE url = $1 LIMIT 1 - ''', article_url) - return row is not None - except Exception as e: - logging.error(f"检查文章存在性失败: {e}") - return False # 出错时默认返回False，避免影响正常流程 - - -async def save_article_to_db(pool, article_title, account_name, article_url, publish_time, content, source_id): - # 在这里调用 lightrag进行知识库构建 - WORKING_DIR = f"../Topic/ChangChun" - docx_name = f"{account_name}_{article_title}" # 组合来源和标题作为文档名 - logger.info(f"开始处理文档: {docx_name}") - try: - # 注意：默认设置使用NetworkX - rag = await initialize_rag(WORKING_DIR) - await rag.ainsert(content) - logger.info(f"索引完成: {docx_name}") - except Exception as e: - print(f"An error occurred: {e}") - finally: - await rag.finalize_storages() - - try: - async with pool.acquire() as conn: - await conn.execute(''' - INSERT INTO t_wechat_articles - (title, source, url, publish_time, content, source_id) - VALUES ($1, $2, $3, $4, $5, $6) - ''', article_title, account_name, article_url, - publish_time, content, source_id) - logger.info(f"保存文档到知识库成功: {docx_name}") - except Exception as e: - logging.error(f"保存文章失败: {e}") - - -async def initialize_wechat_session(): - """初始化微信会话，获取cookies和token""" - with open('cookies.txt', 'r', encoding='utf-8') as f: - content = f.read() - cookies = json.loads(content) - global driver # 添加这行 - expiry = cookies["expiry"] - if expiry: - current_timestamp = time.time() - if current_timestamp > expiry: - logger.error("Cookie已过期") - exit() - - del cookies["expiry"] - - options = Options() - options.add_argument('-headless') - driver = init_wechat_browser() - - url = 'https://mp.weixin.qq.com' - response = requests.get(url=url, allow_redirects=False, cookies=cookies) - - if 'Location' in response.headers: - redirect_url = response.headers.get("Location") - token_match = re.findall(r'token=(\d+)', redirect_url) - if token_match: - token = token_match[0] - return cookies, token - - return None, None - - -async def get_wechat_account_list(cookies, token, account_name): - """获取指定公众号的fakeid""" - search_url = 'https://mp.weixin.qq.com/cgi-bin/searchbiz?' - query_id = { - 'action': 'search_biz', - 'token': token, - 'lang': 'zh_CN', - 'f': 'json', - 'ajax': '1', - 'random': random.random(), - 'query': account_name, - 'begin': '0', - 'count': '5' - } - - search_response = requests.get(search_url, cookies=cookies, headers=header, params=query_id) - lists = search_response.json().get('list')[0] - return lists.get('fakeid') - - -async def get_article_list(cookies, token, fakeid): - """获取公众号文章列表""" - appmsg_url = 'https://mp.weixin.qq.com/cgi-bin/appmsg?' - query_id_data = { - 'token': token, - 'lang': 'zh_CN', - 'f': 'json', - 'ajax': '1', - 'random': random.random(), - 'action': 'list_ex', - 'begin': '0', - 'count': '5', - 'query': '', - 'fakeid': fakeid, - 'type': '9' - } - - query_fakeid_response = requests.get(appmsg_url, cookies=cookies, headers=header, params=query_id_data) - return query_fakeid_response.json().get('app_msg_list') - - -async def process_single_article(article_info, account_info, cookies, token): - """处理单篇文章""" - article_url = article_info.get('link') - article_title = article_info.get('title') - publish_time = datetime.datetime.fromtimestamp(int(article_info.get("update_time"))) - - if '试卷' in article_title: - return False - - try: - pool = await init_postgres_pool() - # 先检查文章是否已存在 - if await is_article_exist(pool, article_url): - logger.info(f'文章已存在，跳过保存: {account_info["account_name"]}-{article_title}') - return False - content = get_article_content(article_url) - await save_article_to_db(pool, article_title, account_info["account_name"], - article_url, publish_time, content, account_info["id"]) - return True - except Exception as e: - logger.error(f"处理文章时出错: {e}") - return False - finally: - if 'pool' in locals(): - await pool.close() - - -async def process_wechat_account(account_info, cookies, token): - """处理单个公众号的所有文章""" - cnt = 0 - fakeid = await get_wechat_account_list(cookies, token, account_info["account_name"]) - articles = await get_article_list(cookies, token, fakeid) - - for article in articles: - success = await process_single_article(article, account_info, cookies, token) - if success: - cnt += 1 - time.sleep(1) - - logger.info(f"成功获取公众号: {account_info['account_name']} {cnt}篇文章。") - return cnt - - -async def main(): - """主函数""" - while True: - try: - logger.info("开始执行微信公众号文章采集任务") - cookies, token = await initialize_wechat_session() - if not cookies or not token: - logger.error("初始化微信会话失败") - continue - - account_list = await get_wechat_sources() - for account in account_list: - await process_wechat_account(account, cookies, token) - - logger.info("本次采集任务完成，等待30分钟后再次执行") - await asyncio.sleep(30 * 60) # 30分钟 - except Exception as e: - logger.error(f"主循环发生错误: {e}") - await asyncio.sleep(30 * 60) # 出错后也等待30分钟 - finally: - if 'driver' in globals(): - driver.quit() - - -if __name__ == '__main__': - loop = asyncio.new_event_loop() - asyncio.set_event_loop(loop) - try: - loop.run_until_complete(main()) - finally: - loop.close() diff --git a/dsLightRag/WxGzh/__init__.py b/dsLightRag/WxGzh/__init__.py deleted file mode 100644 index e69de29b..00000000 diff --git a/dsLightRag/WxGzh/cookies.txt b/dsLightRag/WxGzh/cookies.txt deleted file mode 100644 index 7183301e..00000000 --- a/dsLightRag/WxGzh/cookies.txt +++ /dev/null @@ -1,17 +0,0 @@ -{ - "_clsk": "2gtve8|1752546228205|1|1|mp.weixin.qq.com/weheat-agent/payload/record", - "xid": "16332bed01be1055e236ad45b33af8df", - "data_bizuin": "3514353238", - "slave_user": "gh_4f88a4e194da", - "slave_sid": "QzBRX1FWTXNMaEdJYnc4ODBaM3FJU3RRbjVJNFE2N2IzMXFyVGlRQ0V5YklvNGFOc3NBWHdjV2J5OVg5U0JBVXdfdGhSU3lObXRheG1TdFUyXzVFcTFYS3E1NTh2aTlnSlBOOUluMUljUnBkYktjeUJDM216WVJNYzJKQkx2eW9Ib1duUk1yWXI3RndTa2dK", - "rand_info": "CAESIFwUSYus3XR5tFa1+b5ytJeuGAQS02d07zNBJNfi+Ftk", - "data_ticket": "9gQ088/vC7+jqxfFxBKS2aRx/JjmzJt+8HyuDLJtQBgpVej1hfSG1A0FQKWBbHQh", - "bizuin": "3514353238", - "mm_lang": "zh_CN", - "slave_bizuin": "3514353238", - "uuid": "8c5dc8e06af66d00a4b8e8596c8662eb", - "ua_id": "y1HZNMSzYCWuaUJDAAAAAApPVJ0a_arX_A5zqoUh6P8=", - "wxuin": "52546211515015", - "_clck": "msq32d|1|fxm|0", - "expiry": 1787106233 -} \ No newline at end of file From 67b86ab007eec5051e506d632b13413d892fc572 Mon Sep 17 00:00:00 2001 From: HuangHai <10402852@qq.com> Date: Fri, 18 Jul 2025 15:51:37 +0800 Subject: [PATCH 2/2] 'commit' --- dsLightRag/.idea/dsLightRag.iml | 10 ++++------ dsLightRag/.idea/misc.xml | 2 +- dsLightRag/requirements.txt | Bin 0 -> 19904 bytes 3 files changed, 5 insertions(+), 7 deletions(-) create mode 100644 dsLightRag/requirements.txt diff --git a/dsLightRag/.idea/dsLightRag.iml b/dsLightRag/.idea/dsLightRag.iml index 9c386072..850c697c 100644 --- a/dsLightRag/.idea/dsLightRag.iml +++ b/dsLightRag/.idea/dsLightRag.iml @@ -1,12 +1,10 @@ - - - - - - + + + \ No newline at end of file diff --git a/dsLightRag/.idea/misc.xml b/dsLightRag/.idea/misc.xml index 2cad77d0..85f1c6fa 100644 --- a/dsLightRag/.idea/misc.xml +++ b/dsLightRag/.idea/misc.xml @@ -3,5 +3,5 @@ - + \ No newline at end of file diff --git a/dsLightRag/requirements.txt b/dsLightRag/requirements.txt new file mode 100644 index 0000000000000000000000000000000000000000..45675be946c12734e22988cba987a39ea4bc5e84 GIT binary patch literal 19904 zcmchfYj2!M5ryB+Nc@LL`vruY#J40~35nf>MXZPjEC?a3Wclui?HS`4=l0`)^YoeH z>UTVjykbF-9mic=U0rqR($zir_rDH?!(l#L4jaSu@NxLH{%j3Thi!dr4nH4$HXIB` z`g0=hSOovDCbK~J8k@_sLczSb8)$DtDR`Y6Rm%sIhT?m ztG`&`dahL$n!&gwL&i=0TwJfjYd-u_d?Fn*{kn6>b~a4gYS3(I9QnpHaF~pCxz#9( z>UucVKC=oM*j>tTslD7vTQg~@v;@VLR;oR# zjYqT&KBD_e*#(Qvmv;5O(QS{Rsdg|I|5uXzx%6p?*ePE@&{XTsmRdP!yI4rZYw60^ zfc9mZ<2|6kbLn~}nrH}`-9}Yh7t+g(G&bJpw*Gz7G=L4T2vUKFJ$+?=Q%Qh@`mtbv zu|>1B=azm#0nU##|7N*^U@q31OUo1e*>Bp$dZDylOz+*!g|9OO}N= zTr_N1W6;1U^2{aiRBLUB(t8Fki@V)Ho1KUDTI;fVkM-PG4|$&qztLBG|I6W7`}57f zPlx()jMCW$dcB-Js^>kh)>Qd+yz6R2A{O%kDA`krCD?|(+qnk7U0Wq`5RH)G>T+nRwH}F z&&kD5fQ`p%2Mo+)t4nESPyDX+eXN}^U+ZPJdE5)lMJqe{{&M7faOkDMXQJ81#)K_N zvMScb_GF1mSFJ6e!849`K6-Dvev(8(cYCCCq?a{0T4ZE{G?OAvZbr|Q2%tlv6IU_`BJgfYX@x7&1JPu!Gv&X{q zakC;QO$`kVIw&k2YbJI)5S1&g{q_^S5_yo+8Qs)l1X=giu6IMG1YRh>QJVelaL!5>W?ODhL=@@+Q$w#JDxMXi1&_EN`_L-RJI^K4 zbNQFE4regx(s7Ld7xZS!O_#BmU6)6kYR}YH zHMTK)qg9XunTeWc8BWxQ-XFS!4<|@y7TRa1%(v(k^1)ka@KlsJ-MR8+@A0=&t%*g) z)gh5`SF4t_z&>@zv_&gc&bk$CPMg$N$6W*Bq*o-H*{@DD^K=rWJ`a%o)JqA=Bi1|&REkG&zU%qeaUni((OdwJp-LNQoYky zFnz1vG0xtR&GEvBUgZU@tDC_L^q#X1J6=DdkLb)NJB+=KdbBXQ$^|W+HwlgL!rFSu ziU`g_mA{y8?T=@!(-69gRth)$JbOBI0Cv36ACPAs^$D&JPraYDe?Pn#{-!;VMT5Dj zRC4-GuLL}7H&jG&>_`NdDF&}<)855ejs-opec@`g;|8v5Ik?Un@?3YO4+OT5F6diF zM}1$|%AU}6kc1D|*K%HfFBHKo{y0-6tE$8?C(>POuh9u3^fY>@GEU#k{lHYIrY>$| zu+2xGhtbfEe1~4k%a(C2S8|^DIlFPT<1~fmlH>NI0Zxd0pXFSm=m@PABFO~yQL1hJ z#Yy*4vBfcheSVxvX`jKU7y|(johIt#CW4 zOpQV?#thD#oUCq|E$9MWF7ZfqDV>GVC)wE2=LzGPbI);$xZ{Y4zWO!Ym8B1cU!`~I zC|v77MNa7V>1Z&~D*P6{K4GyJe(MNJC!lU4%-0?d4PMJ^dr~-}1tMa+&0bnrk<3#R z8(P8j#))P{!iwfaP0k|YM&61l(4;qL?CdvP;Kw;hF$)=x#x`Cz%T zc20eOuepl>LM)YWA50sIXaWC84gv>I81WO0jn6CKbh}9!ebQ587hcCTx8-6l2nk-t)FumQ1s%)1GD~FEtY25p>(`Id$(#TRu0_&CgmpP4|(+ z=X0-xwZkp-!V2zd*L%{JFng0IlbJb<2Hh`2!6tf)@*OP`*g%ISDNlf67Q)I zuxrqg>eJHU>2H-;IDe(@lKp{p>wq)TM^QKuGVY44JoG|i@AZXDm&(9+M)+Q~!vAeu2Zt7nGMvTk*3?b9a+#Vg6+AYr`b!@7Il@K;`wHOGjVORw;@ zmqLTzb8;@!+$_(WjG#BiBc%Q$%kN9NnSLI30F0e4RPp_;>5!~KbUD#)z^Cg)I$BSf zA0WXK{eGtJ_69N+e)vSb<~U0fhyEA(&TTj~39h1y&6YjyZ@q8ug`z?lX?ol+21<-Rv7vr6=FNC1~1&&`gY3Wq{cKEtU z>pWo#qu=`&hB_ykA0##V<#*u6`{;iI`sq}1e}Gog#kTeE^ysCZwJ(0WCE@fs?vPtw ze2-O`M_e*KUCRU+oX^jNE$je3(Wo)wn+LrO|Cw#~# zMksQO>nooj;8*Js*QsHQWy@5Ux^DPPL}b)xw{E%7rb6hufn;^Q?329Zf%m@FAc7NL z63ZOB;ptV)GjD% z*XMQ0V{~zcE}sP1J@akv>76}|0e+tmG~-)8=2%X4h(Ct*#y8oiaa=2PxFRPiH@x2iz zXZj=ABlaXqaW`|{mgqI7T;gx`)bn8Hz5PAM2w;x=AaZ%#eol4h$-e0bf1V5TKM3jA z!5Sj7ar;Q{@LedxyA$Qu2nXqW1>FycXYAs`_^UpeZkOAy#}2- zdRjl0KQWMs2K=BAs_HsP1l7B;)!`lDY~yu${5&`G?AKI3HQ(HmlpXQK$4Xtc`mx&c zo4p@D%V#}wO?a3}Ia{&~``a^`^&dX=pL=x+!r|Ex2+YeJ#PI8PPCNrBF2)|&q z&nU@w9wh^NjPraS{lX!=Kt~~W&FW5w`s#JS9O3G@!?<_t7NGHx1N5n{uq;=-G<+Ba{a_;SuLH}*@N5?QK};q7E! zRfGcTgo9rtq>^_oL%WfPULAEh(Gi)#qt_=VN$&H=0aW4j;uKD-=57cl0^T6_Wb5-E z{LnG?*|n;(301FeT(dGXmCJMEM{Q*cvv;^z`ZvR$hQE#^_G#O9tA6!LMv66%w&zY= z%HGjYFF`WCkp~rLd$N4a$m|MP{aQM@Bo}ha7-=0xpo-T);fzctjJufow^hud=bBwQ zZc}0L?jhB4Va$3(!@(e{kR_?8SSL2McC)MG?f&f&y6sPTl{0+H3@6v5;3L|u_edFM zG?>6se1fnIV`KM6)8r zitKbPi?BLKhsr)scK9gWxISmJ`r>d({GdaTei0G6Uo9y3sQu;T)7BD4@QB2W6XDBi z?@NNmPPNPMw`bV4%=aia2GsVPijpfpmOUZVzAxoAC0+myf~$C8B8shrMT5nP>PCF+ z1D)3Sbba>ZuI*Y`uHL#n6Ly{}D(^~8x)t0NVxuuPawe}w$&tL*q}IeHyxAP*OwX-; zFntxg5ZxJ#-fQ&XdkI%9wzN-6Wxt++9J-Ix2hR6~wV>9t~gBcX5v zH8I(UjAhX9sUH|fceRHZ~59kMk1!ZqEcGk2&E!N8n*1S__z8n6&jIqeLx+Bm< zePMqARpeURpV_a4yf^Bde7lqZ&W<1G+7utvllt@U$2$tJS32X|=Q@X*D`XAg-LEJQ z{!_#6RNTH_a*Hk^(X}KB9&M{aKpzY0MF4B`brti;;S=raN_%0xb6{!Kt6;DAmGy57 zm2TdM%Y|&5{cuZOagLRU0PX`|JLD+6WYj%{eZ_fR3S2BL={Vl+8>CV5QTY(Vw%fY! zWsikA`hV`fVQ zs(Hm{Ur6nb&X6y0F)^wlPd}GPHSTSopLMivC28)?qnmYfS1qCvA&jR&r6XW+A2kED z4tdzO71Y~~gWSU}hF@vKcmMPDiI!*bCVtP&`=O-t$>W(YM>gm4Y_>D@L{g$F+^y+# zt36$E{EamBN_BL3x3!;Xml1L8}_%vAlLE4pV#!sj{6eMrg?>9Z5!oY7gUFq>YhyC8wmEX zN=a1`q_~@5Ejx#hRWjSM6!7PECtWnGNS)o&AZ_*f+@;FBN-*g9u~vrO9?A_- zuW#hR_R$pkL9+2&_qD4(Y5N+{){;LD&JMhPQ()(eGv=y@js+-+o>ydfObS(6v98mTDpI&maE$>$XzH#-b zyOgJY1GcQJl#$tjRsazE|UVDZDs@o;FUg;Ud3{STsgs#Q*`xg*<@&%uja z<1;=ut~!XwSm?#GoC81UZ}9GQk<8J+y&QTmoW}cDQQpLQO~|uez3Ay*vX7pJd`==(9L`jB1IR&;14?=026r7Ji)+J-AaFe*Y8~YXWq?kcH5s ztwYWSz4qg(F6~kF(9dNmIJ(=N)$l!HC1-2ofuiz*ee>~g{#cmWl_sas&IfVc(NE(z zAC8XjoZP6EINQC{Tq5J@tx{(2=_}5dcpXuSNVYy&-~ay?IK@+Ib2`M%7ph&>%e8Km z$O@i0YjA%?MxskF&PKd{a4tcY_zFmgztA_~^ZDe5#+5wNV6rM_ej7YDnZ-{d`(4^?K?tia}0rS}Q#KlEw6RS@!)&$R~O`{zvwH z+;=j>Jv2v*am-|2x1-zA#Gh#2Z*TA)sx9|V?LXA&=JH}G$$DC9Kss5~fpVO16-M>R zd2^%rX4SjUAPc!8ognX*-ao!fwc;qx&+);kSp2Tcw}RV`Mm(OhEtG?JcUo5~t}$O@ zoL(2z2z3|#;|RH7wc@&M-6AqqUzPW-DTr~@l$?89o%@rzSQK4X^n5Q0bU@C@>k@2X zf556x@PF9kvq6lYOJkYQg^+uGmxU@f`2D+4%$sXG^H|jNTGcT+oK|BCJsh-7P5k&s zLqFqc7Gq~dS4oY}vr5L?NwW|3@0_Ws`2U}v0~z)} za=WA2`xYlTu^{p1_T2x^KiG}`JK;hya7V`)-P}LBD-gabZScO@V>|IbzU6VZ$cdLQgB^U%I)N#7JY hQrjl*wJxdjxzh_j-!GY?JD;4_$p)#w9T7_U{{Wn0q*MR^ literal 0 HcmV?d00001