sukidesuka
sukidesuka
This change definitely has bugs. I updated to the latest version of traceloop-sdk today, 0.16.6, but even though gpt4's responses are normally output to the console without any filtering issues,...
According to the Azure official documentation https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new ``` data: {"id":"","object":"","created":0,"model":"","prompt_annotations":[{"prompt_index":0,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}}}],"choices":[],"usage":null} data: {"id":"chatcmpl-7rCNsVeZy0PGnX3H6jK8STps5nZUY","object":"chat.completion.chunk","created":1692913344,"model":"gpt-35-turbo","choices":[{"index":0,"finish_reason":null,"delta":{"role":"assistant"}}],"usage":null} data: {"id":"chatcmpl-7rCNsVeZy0PGnX3H6jK8STps5nZUY","object":"chat.completion.chunk","created":1692913344,"model":"gpt-35-turbo","choices":[{"index":0,"finish_reason":null,"delta":{"content":"Color"}}],"usage":null} data: {"id":"chatcmpl-7rCNsVeZy0PGnX3H6jK8STps5nZUY","object":"chat.completion.chunk","created":1692913344,"model":"gpt-35-turbo","choices":[{"index":0,"finish_reason":null,"delta":{"content":" is"}}],"usage":null} data: {"id":"chatcmpl-7rCNsVeZy0PGnX3H6jK8STps5nZUY","object":"chat.completion.chunk","created":1692913344,"model":"gpt-35-turbo","choices":[{"index":0,"finish_reason":null,"delta":{"content":" a"}}],"usage":null} ... data: {"id":"","object":"","created":0,"model":"","choices":[{"index":0,"finish_reason":null,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"content_filter_offsets":{"check_offset":44,"start_offset":44,"end_offset":198}}],"usage":null} ... data: {"id":"chatcmpl-7rCNsVeZy0PGnX3H6jK8STps5nZUY","object":"chat.completion.chunk","created":1692913344,"model":"gpt-35-turbo","choices":[{"index":0,"finish_reason":"stop","delta":{}}],"usage":null} data: {"id":"","object":"","created":0,"model":"","choices":[{"index":0,"finish_reason":null,"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"content_filter_offsets":{"check_offset":506,"start_offset":44,"end_offset":571}}],"usage":null} data: [DONE]...
我算是搞明白了，如果你要改port，你先要进入qbit的设置面板里把port改掉。然后把docker的-e WEBUIPORT=8080和-p 8080:8080改掉
> @jefffortune > > Thank you for attaching the screenshots!谢谢您附上的截图！ > > Could you test this out:你能测试一下这个吗？ > > ```python > for chunk in qa_chain.stream({"question": "Please explain AI"}): > print(chunk)...
I think a callback or something else is needed to allow functions like chain.invoke or chain.astream to capture console output, or to use TextIteratorStreamer to capture the output by themselves,...