-
Notifications
You must be signed in to change notification settings - Fork 5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[FEATURE] 什么时候支持qwen-vl-chat?openai api或者chatchat api支持都可以,哪位提示一下在哪里更改代码来支持 #2969
Comments
🤖 嗨,@Liam-Ji!很高兴再次看到你提出的问题。希望你最近一切顺利! 您可以在Langchain-Chatchat的配置文件中添加对qwen-vl-chat的支持。具体来说,您需要在LLM_MODELS列表中添加"qwen-vl-chat",并在"llm_model"字典中添加相应的模型路径。例如: LLM_MODELS = ["chatglm3-6b", "zhipu-api", "openai-api", "qwen-vl-chat"]
"llm_model": {
...
"qwen-vl-chat": "Qwen/qwen-vl-chat",
...
} 同时,如果您希望支持OpenAI API或ChatChat API,您需要在ONLINE_LLM_MODEL字典中添加相应的API配置。例如: ONLINE_LLM_MODEL = {
...
"openai-api": {
"model_name": "gpt-4",
"api_base_url": "https://api.openai.com/v1",
"api_key": "your_openai_api_key",
"openai_proxy": "",
},
"chatchat-api": {
"model_name": "chatchat",
"api_base_url": "https://api.chatchat.com/v1",
"api_key": "your_chatchat_api_key",
"chatchat_proxy": "",
},
...
} 请注意,您需要将"your_openai_api_key"和"your_chatchat_api_key"替换为您的实际API密钥。 以上信息可以在configs/model_config.py.example中找到。 如果您在实施过程中遇到任何问题,欢迎随时提问。 SourcesThis response is meant to be useful and save you time. It is not meant to be a precise solution, but rather a starting point for your own research. Help me be more useful! Please leave a 👍 if this is helpful and 👎 if it is irrelevant. If you want to continue the conversation, start your reply with @dosu-bot. |
可是没有多模态知识库啊,加入了多模态模型的意义是 |
是这样的,我有个场景:识别图像场景的内容作为标签,qwen-vl-chat不能直接给出标签,但是他可以描述图像的内容,可以根据这个内容与知识库匹配得到标签。这个过程第一步用qwen-vl-chat得到描述,第二步用qwen-vl-chat+知识库得到标签。所以想看看LangChain-Chatchat能不能支持qwen-vl-chat |
不需要多模态知识库,现有的文字知识库就能用。 |
这个发送“你是谁”,后台出来的错误信息,只拿到了返回的两个字“我是” During handling of the above exception, another exception occurred:
The above exception was the direct cause of the following exception: Traceback (most recent call last): The above exception was the direct cause of the following exception: Traceback (most recent call last): |
请问您的问题解决了吗?我也遇到同样的问题了 |
还没有 |
同样的问题,有没有解决? |
引入多模态的场景中,对应解决方案的设计思路这里面提到的应该可以满足 如何借助LLMs构建支持文本、表格、图片的知识库 - 知乎 |
功能描述 / Feature Description
支持qwen-vl-chat
The text was updated successfully, but these errors were encountered: