Streaming of response didn't work
stevenzhang114 opened this issue · comments
Describe the bug
The result will not be showed as "streaming" type of response when generating the answers, instead will just show "Generating answer..." , and then will show whole response at the end.
To Reproduce
Steps to reproduce the behavior:
- Go to "Azure OpenAI studio" -> Chat playground
- Add data source
- Use "Deploy to" button to deploy a new web app
- Configure "AZURE_OPENAI_STREAM" variable to True
- Ask any questions
Expected behavior
The answer should be showing as Streaming style like when testing in Chat playground in OpenAI studio
Screenshots
If applicable, add screenshots to help explain your problem.
Configuration: Please provide the following
- Azure OpenAI model name and version (e.g. 'gpt-35-turbo-16k, version 0613')
gpt-4 & gpt-35-turbo-16k, version 0613 - Is chat history enabled?
No - Are you using data? If so, what data source? (e.g. Azure AI Search, Azure CosmosDB Mongo vCore, etc)
- CosmosDB Mongo vCore
Additional context
Add any other context about the problem here.