Week 5 community contribution (profe-ssor): Research/Learning RAG#2068
Open
profe-ssor wants to merge 1 commit intoed-donner:mainfrom
Open
Week 5 community contribution (profe-ssor): Research/Learning RAG#2068profe-ssor wants to merge 1 commit intoed-donner:mainfrom
profe-ssor wants to merge 1 commit intoed-donner:mainfrom
Conversation
…ebook Made-with: Cursor
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Week 5 Project: Research / Learning RAG Assistant
Summary
A RAG (Retrieval Augmented Generation) Q&A assistant for course notes and research-style documents. It answers questions using only the content you put in a knowledge base (no general knowledge), so it stays on-topic and avoidable.
What it does
Ingest: Loads markdown documents from a folder (default: week5 knowledge-base; can point to your own course or research notes).
Chunk & embed: Splits docs with RecursiveCharacterTextSplitter (500 chars, 100 overlap) and embeds with HuggingFace all-MiniLM-L6-v2 (no API key).
Store: Saves embeddings in Chroma (persistent vector DB).
Answer: For each question, retrieves the top‑k chunks, builds a context string, and calls an LLM with a system prompt: “Answer only from the context; if you don’t know, say so.”
UI: Gradio chat interface so you can ask questions in a browser.