Open leochen12-rgb opened 9 months ago
Bot detected the issue body's language is not English, translate it automatically.
Title: [Bug] Gemini Pro model does not support stream output
v2.10.1 deployed using docker-compose: Support Google Gemini mode does not support streaming text output and can only output all results. There is no typewriter effect~
使用docker-compose部署的v2.10.1: Support Google Gemini mode不支持流式文本输出,只能全部输出结果。没有打字机效果哦~
not ready, google currently doesn't have streaming mode in their RESTful API I think
Bot detected the issue body's language is not English, translate it automatically.
not ready, google currently doesn't have streaming mode in their RESTful API I think
Streaming response is ready. But i haven't check it further. https://ai.google.dev/api/rest/v1beta/models/streamGenerateContent
not ready, google currently doesn't have streaming mode in their RESTful API I think
Streaming response is ready. But i haven't check it further. https://ai.google.dev/api/rest/v1beta/models/streamGenerateContent
it's still json
use a longer prompt like "write a story about time travelling.", it'll tell the difference.
Streaming support is available in PR https://github.com/ChatGPTNextWeb/ChatGPT-Next-Web/pull/3688. Please create an individual issue if you encounter any problems.
https://github.com/google-gemini/cookbook/blob/main/quickstarts/rest/Streaming_REST.ipynb
add alt=sse
in query_string, will get response with content type: text/event-stream
使用docker-compose部署的v2.10.1: Support Google Gemini mode不支持流式文本输出,只能全部输出结果。没有打字机效果哦~