latorc / wechat-ai-assistant Goto Github PK
View Code? Open in Web Editor NEW微信AI助理 (Wechat AI Assistant): 在微信中与 AI 助理进行多模态交互, 处理问答、扮演角色、响应语音消息、分析图片和视频、总结文章和网页链接、搜索互联网等等。现支持 OpenAI Assistant API 和 GPT-4o模型。
License: MIT License
微信AI助理 (Wechat AI Assistant): 在微信中与 AI 助理进行多模态交互, 处理问答、扮演角色、响应语音消息、分析图片和视频、总结文章和网页链接、搜索互联网等等。现支持 OpenAI Assistant API 和 GPT-4o模型。
License: MIT License
如题,我已再三确认模型是存在的。
配置如下:
openai:
#api_key:
#base_url: # API的网址。原版API使用默认值: https://api.openai.com/v1
api_key: sk-zytscKkrg06aExzG41F898Ef82F046Ea8bAd51Bb82D5280f
base_url: http://localhost:3002/v1
proxy: # 代理服务器地址。格式为"http://地址:端口号"
chat_model: gpt-3.5-turbo # 聊天使用模型名称,例如:gpt-3.5-turbo-0125, gpt-4-turbo-preview. 可用模型参见(https://platform.openai.com/docs/models/overview)
image_model: dall-e-3 # (可选, 默认值: dall-e-3) 作图模型, 选项: dall-e-3, dall-e-2
image_quality: hd # 现在作图质量由模型决定, 该参数暂时无效。(可选, 默认值: standard) 作图质量。选项: standard(标准), hd(高清)。
image_size: 1024x1024 # (可选, 默认值: 1024x1024) 作图大小, dall-e-3 支持尺寸 1024x1024, 1792x1024, 1024x1792。
voice: alloy # 虚拟配音演员 alloy, echo, fable, onyx, nova, and shimmer. 试听: https://platform.openai.com/docs/guides/text-to-speech/voice-options
voice_speed: 1.1 # 语音速度, 可选 0.25-4.0 (默认1.0)
transcript_prompt: "请转录用户的语音消息,可能使用的语言是:简体中文和English" # 为语音转录提供一段提示词,以提高识别正确率
错误如下:
2024-05-05 23:52:18 初始化OpenAI API...
2024-05-05 23:52:18 启用工具 image_to_text (获取图像的文字描述)
2024-05-05 23:52:18 启用工具 text_to_image (用文字描述生成图像)
2024-05-05 23:52:18 启用工具 text_to_speech (用文字生成语音)
2024-05-05 23:52:18 启用工具 browse_link (访问链接获取内容)
2024-05-05 23:52:18 启用工具 bing_search (用必应搜索网络内容)
2024-05-05 23:52:18 启用工具 audio_transcript (语音转录成文字)
2024-05-05 23:52:18 启用工具 video_analysis (分析视频内容)
主程序发生错误: Traceback (most recent call last):
File "main.py", line 42, in
File "main.py", line 16, in main
File "openai_wrapper.py", line 42, in init
File "openai_wrapper.py", line 65, in load_config
File "openai_wrapper.py", line 132, in get_assistant
File "openai\resources\beta\assistants\assistants.py", line 287, in list
File "openai_base_client.py", line 1249, in get_api_list
File "openai_base_client.py", line 1094, in _request_api_list
File "openai_base_client.py", line 889, in request
File "openai_base_client.py", line 965, in _request
File "openai_base_client.py", line 1013, in _retry_request
File "openai_base_client.py", line 965, in _request
File "openai_base_client.py", line 1013, in _retry_request
File "openai_base_client.py", line 980, in _request
openai.InternalServerError: Error code: 503 - {'error': {'message': '当前分组 default 下对于模型 无可用渠道 (request id: 2024050523522150057096679513566)', 'type': 'one_api_error'}}
2024-05-05 23:52:21 主程序发生错误, 即将退出: Traceback (most recent call last):
File "main.py", line 42, in
File "main.py", line 16, in main
File "openai_wrapper.py", line 42, in init
File "openai_wrapper.py", line 65, in load_config
File "openai_wrapper.py", line 132, in get_assistant
File "openai\resources\beta\assistants\assistants.py", line 287, in list
File "openai_base_client.py", line 1249, in get_api_list
File "openai_base_client.py", line 1094, in _request_api_list
File "openai_base_client.py", line 889, in request
File "openai_base_client.py", line 965, in _request
File "openai_base_client.py", line 1013, in _retry_request
File "openai_base_client.py", line 965, in _request
File "openai_base_client.py", line 1013, in _retry_request
File "openai_base_client.py", line 980, in _request
openai.InternalServerError: Error code: 503 - {'error': {'message': '当前分组 default 下对于模型 无可用渠道 (request id: 2024050523522150057096679513566)', 'type': 'one_api_error'}}
Installing collected packages: sortedcontainers, soupsieve, PySocks, pydantic_core, pycparser, protobuf, packaging, outcome, h11, grpcio, distro, anyio, annotated-types, wsproto, webdriver-manager, pydantic, httpcore, grpcio-tools, cffi, beautifulsoup4, trio, pynng, httpx, wcferry, trio-websocket, openai, selenium
WARNING: Failed to write executable - trying to use .deleteme logic
ERROR: Could not install packages due to an OSError: [WinError 2] 系统找不到指定的文件。: 'C:\Python312\Scripts\distro.exe' -> 'C:\Python312\Scripts\distro.exe.deleteme'——这个文件搜百度都搜不到,咋整?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.