A sample app for the Retrieval-Augmented Generation pattern running in Azure, using Azure Cognitive Search for retrieval and Azure OpenAI large language models to power ChatGPT-style and Q&A experiences.
[ ] bug report -> please search issues before submitting
[x] feature request
[ ] documentation issue or request
[ ] regression (a behavior that used to work and stopped in a new release)
Description
As a user, I want to preserve long context so that my conversation is relevant and delivers the best quality results.
Because of the token limit, conversations are constrained. To preserve context over longer conversations, a mechanism like summarization needs to be used so that the conversation provides high value.
Expected/desired behavior
[ ] Determine design for how to preserve long-context in the chat (e.g. LangChain, )
[ ] Document design & create another issue (feature request) for build
This issue is for a: (mark with an
x
)Description
Because of the token limit, conversations are constrained. To preserve context over longer conversations, a mechanism like summarization needs to be used so that the conversation provides high value.
Expected/desired behavior
Mention any other details that might be useful