Add LLM RAG exploration notebook (experimental)#282
Open
kevke-edu wants to merge 1 commit into
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This PR is completely isolated to the new experimental/ folder. It strictly contains additive changes and does not modify any existing frontend or backend code, so it should merge cleanly
Note: The complete end-to-end feature is already deployed across the stack (frontend .tsx files, Node/Express gateway, and Flask backend). Please refer to PR #274 for the production implementation. This PR strictly contains the original exploratory Jupyter notebook.
This notebook documents the initial prototyping of the LLM RAG architecture. The notebook starts by evaluating the Gemini API for both embeddings and text generation. However, strict rate limits during testing made it unviable for sustained development. Following this, a second round of experiments transitioned to using local sentence-transformers to embed the recipe data and explored free Nvidia models via OpenRouter for the generation step. HuggingFace models are also explored as a potential fall back in case rate limits were observed for the OpenRouter provider.