Create a backend function that uses OpenAI to answer questions using embeddings #243

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Open

jackbravo opened this issue Jun 27, 2023 · 0 comments

Labels

backend

Milestone

jackbravo commented Jun 27, 2023

Create a backend API (or function since we are using remix) that based on a user provided question:

uses our vector storage and index to search for relevant questions (Choose a source of truth storage for embedding vectors for wize-q data #240, pgvector 1? opensearch? sqlite?)
sends them as context to OpenAPI in the prompt (example prompt)
requests OpenAPI to also provide sources for the answer
returns the response

Example video here: https://www.youtube.com/watch?v=Yhtjd7yGGGA

jackbravo added this to the Generative AI milestone

jackbravo added the backend label

jackbravo mentioned this issue

Create frontend for answering questions with LLM #245

Open

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment