V0.3.8 readme

TeamWiseFlow · Jan 24, 2025 · fdfe5c0 · fdfe5c0
1 parent b1ef7a2
commit fdfe5c0
Show file tree

Hide file tree

Showing 10 changed files with 10 additions and 228 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -35,11 +35,11 @@
 
   Provided a custom extractor interface to allow users to customize according to actual needs.
 
-- bug 修复以及其他改进（crawl4ai浏览器生命周期管理，异步 llm wrapper 等）（感谢 @tusik 贡献异步 llm wrapper）
+- bug 修复以及其他改进（crawl4ai浏览器生命周期管理，异步 llm wrapper 等）（感谢 @tusik 贡献）
 
   Bug fixes and other improvements (crawl4ai browser lifecycle management, asynchronous llm wrapper, etc.)
 
-  Thanks to @tusik for contributing the asynchronous LLM wrapper
+  Thanks to @tusik for contributing
 
 # V0.3.6
 - 改用 Crawl4ai 作为底层爬虫框架，其实Crawl4ai 和 Crawlee 的获取效果差别不大，二者也都是基于 Playwright ，但 Crawl4ai 的 html2markdown 功能很实用，而这对llm 信息提取作用很大，另外 Crawl4ai 的架构也更加符合我的思路；

diff --git a/README.md b/README.md
@@ -89,10 +89,6 @@ wiseflow 0.3.x版本使用 pocketbase 作为数据库，你当然也可以手动
 
 🌟 **这里与之前版本不同**，V0.3.5开始需要把 .env 放置在 [core](./core) 文件夹中。
 
-**windows 用户可以参考 core文件夹下的 windows.env windows_run.py 文件，执行 windows_run.py 脚本**
-
-感谢 @c469591 贡献的 windows 下原生启动脚本
-
 #### 3.1 大模型相关配置
 
 wiseflow 是 LLM 原生应用，请务必保证为程序提供稳定的 LLM 服务。

diff --git a/README_EN.md b/README_EN.md
@@ -88,10 +88,6 @@ For details, please refer to [pb/README.md](/pb/README.md)
 
 🌟 **This is different from previous versions** - starting from V0.3.5, the .env file needs to be placed in the [core](./core) folder.
 
-**Windows users can refer to the windows.env and windows_run.py files in the core folder and execute the windows_run.py script**
-
-Thanks to @c469591 for contributing the native Windows startup script
-
 #### 3.1 Large Language Model Configuration
 
 Wiseflow is a LLM native application, so please ensure you provide stable LLM service for the program.

diff --git a/README_JP.md b/README_JP.md
@@ -89,10 +89,6 @@ Wiseflow 0.3.xはデータベースとしてpocketbaseを使用しています
 
 🌟 **これは以前のバージョンとは異なります** - V0.3.5以降、.envファイルは[core](./core)フォルダに配置する必要があります。
 
-**Windowsユーザーはcoreフォルダ内のwindows.envとwindows_run.pyファイルを参照し、windows_run.pyスクリプトを実行してください**
-
-@c469591によるWindows用ネイティブ起動スクリプトの貢献に感謝いたします
-
 #### 3.1 大規模言語モデルの設定
 
 Wiseflowは LLMネイティブアプリケーションですので、プログラムに安定したLLMサービスを提供するようにしてください。

diff --git a/README_KR.md b/README_KR.md
@@ -88,10 +88,6 @@ Wiseflow 0.3.x는 데이터베이스로 pocketbase를 사용합니다. pocketbas
 
 🌟 **이전 버전과 다릅니다** - V0.3.5부터 .env 파일은 [core](./core) 폴더에 위치해야 합니다.
 
-**windows 사용자는 core 폴더의 windows.env와 windows_run.py 파일을 참조하여 windows_run.py 스크립트를 실행할 수 있습니다**
-
-@c469591님이 기여해 주신 windows용 네이티브 실행 스크립트에 감사드립니다
-
 #### 3.1 대규모 언어 모델 구성
 
 Wiseflow는 LLM 네이티브 애플리케이션이므로 프로그램에 안정적인 LLM 서비스를 제공하도록 해주세요.

diff --git a/core/windows.env b/core/windows.env
diff --git a/core/windows_general_process.py b/core/windows_general_process.py
diff --git a/core/windows_run.py b/core/windows_run.py
@@ -72,7 +72,6 @@ def main():
                 print(f"Error: run_task.py not found at: {process_script}")
         except subprocess.CalledProcessError as e:
             print(f"Error running run_task.py: {e}")
-
     else:
         print("Failed to start services")
 

diff --git a/test/get_info_test.py b/test/get_info_test.py
@@ -10,7 +10,6 @@
 sys.path.append(core_path)
 
 # 现在可以直接导入模块，因为core目录已经在Python路径中
-from scrapers import *
 from utils.general_utils import is_chinese
 from agents.get_info import get_author_and_publish_date, get_info, get_more_related_urls
 from agents.get_info_prompts import *
@@ -20,7 +19,7 @@
 # models = ['deepseek-reasoner']
 models = ['Qwen/Qwen2.5-7B-Instruct', 'Qwen/Qwen2.5-14B-Instruct',  'Qwen/Qwen2.5-32B-Instruct', 'deepseek-ai/DeepSeek-V2.5']
 
-async def main(sample: dict, include_ap: bool, prompts: list, focus_dict: dict, record_file: str):
+async def main(sample: dict, include_ap: bool, prompts: list, record_file: str):
     link_dict, links_parts, contents = sample['link_dict'], sample['links_part'], sample['contents']
     get_link_sys_prompt, get_link_suffix_prompt, get_info_sys_prompt, get_info_suffix_prompt = prompts
 
@@ -91,16 +90,16 @@ async def main(sample: dict, include_ap: bool, prompts: list, focus_dict: dict,
     focus_points = json.load(open(os.path.join(sample_dir, 'focus_point.json'), 'r'))
     focus_statement = ''
     for item in focus_points:
-        tag = item["focuspoint"]
-        expl = item["explanation"]
-        focus_statement = f"{focus_statement}//{tag}//\n"
+        tag = item["focuspoint"].strip()
+        expl = item["explanation"].strip()
+        focus_statement = f"{focus_statement}//{tag}//"
         if expl:
             if is_chinese(expl):
-                focus_statement = f"{focus_statement}解释：{expl}\n"
+                focus_statement = f"{focus_statement}\n解释：{expl}\n"
             else:
-                focus_statement = f"{focus_statement}Explanation: {expl}\n"
+                focus_statement = f"{focus_statement}\nExplanation: {expl}\n"
 
-    focus_dict = {item["focuspoint"]: item["focuspoint"] for item in focus_points}
+    #focus_dict = {item["focuspoint"]: item["focuspoint"] for item in focus_points}
     date_stamp = datetime.now().strftime('%Y-%m-%d')
     if is_chinese(focus_statement):
         get_link_sys_prompt = get_link_system.replace('{focus_statement}', focus_statement)
@@ -134,4 +133,4 @@ async def main(sample: dict, include_ap: bool, prompts: list, focus_dict: dict,
         with open(record_file, 'a') as f:
             f.write(f"raw materials: {file}\n\n")
         print(f'start testing {file}')
-        asyncio.run(main(sample, include_ap, prompts, focus_dict, record_file))
+        asyncio.run(main(sample, include_ap, prompts, record_file))
diff --git a/weixin_mp/__init__.py b/weixin_mp/__init__.py
@@ -19,9 +19,7 @@
 
 from general_process import main_process, wiseflow_logger, pb
 from typing import Optional
-import logging
 
-logging.getLogger("httpx").setLevel(logging.WARNING)
 
 # 千万注意扫码登录时不要选择"同步历史消息"，否则会造成 bot 上来挨个回复历史消息
 # 先检查下 wx 的登录状态，同时获取已登录微信的 wxid