[POC] Build a chat interface to the weave-gitops / flux docs #114
Open
Description
Notes
Prior art:
- https://supabase.com/docs (https://github.com/supabase/supabase/pull/12056/files) - supabase
- https://astro-labs.app/docs (https://github.com/gannonh/gpt3.5-turbo-pgvector) - supabase
- ?
Projects of interest:
- https://github.com/hwchase17/langchain/
- https://github.com/jerryjliu/llama_index
- https://github.com/openai/chatgpt-retrieval-plugin
- https://github.com/mpaepper/content-chatbot
- https://github.com/whitead/paper-qa
- ui: https://github.com/ddiu8081/chatgpt-demo/
- ?
Guides / tutorials:
- https://github.com/openai/openai-cookbook/blob/main/examples/Question_answering_using_embeddings.ipynb
- https://simonwillison.net/2023/Jan/13/semantic-search-answers/
- https://betterprogramming.pub/how-to-build-your-own-custom-chatgpt-with-custom-knowledge-base-4e61ad82427e
- ?
Various links
- https://news.ycombinator.com/item?id=35327204 ways to improve the query-to-vector encoding
Approaches
Supabase
??
Build a static docker image with vectors pre-computed with a simple http api
??
Try and use openai's chatgpt-retrieval-plugin
Pros:
- Would be future proof and compatible with a future chatgpt plugin
- Has upsert etc for adding more docs in the future, e.g. via github-actions in weave-gitops/flux
Cons:
- Untested as an approach
- The vector stores that it uses are unfamiliar
Metadata
Assignees
Labels
No labels