rag-from-scratch

by langchain-ai · Developer Tools

RAG From Scratch LLMs are trained on a large but fixed corpus of data, limiting their ability to reason about private o

New0 ratings9,267 starsActive
Developer ToolsDeveloper ToolJupyter Notebook
GitHub⚑ Report
rag-from-scratch — image 1

About this project

RAG From Scratch LLMs are trained on a large but fixed corpus of data, limiting their ability to reason about private or recent information. Fine-tuning is one way to mitigate this, but is often not well-suited for factual recall and can be costly. Retrieval augmented generation (RAG) has emerged as a popular and powerful mechanism to expand an LLM's knowledge base, using documents retrieved from an external data source to ground the LLM generation via in-context learning. These notebooks accompany a video playlist that builds up an understanding of RAG from scratch, starting with the basics of indexing, retrieval, and generation. Video playlist

Technologies

Jupyter Notebook

Project health

Inactive for over a year
Last updatelast year
Contributors4
Latest release
Open issues & PRs39
License
On GitHubsince 2024

GitHub

9,267
stars
2,193
forks
4
contributors
39
open issues & PRs
Jupyter Notebook
language
last year
last commit
View on GitHub ↗

Reviews

out of 5 · 0 ratings
★★★★★
0%
★★★★
0%
★★★
0%
★★
0%
0%
Sign in to write a review
No reviews yet
Be the first to review rag-from-scratch.

Built by

langchain-ai
Imported from GitHub · not yet claimed on GitPalace
View developer pageSign in with GitHub to claim

Maintain langchain-ai/rag-from-scratch? Claiming verifies admin access through your GitHub account and gives you control of this listing.

You might also like