├── README.md ├── rag_from_scratch_10_and_11.ipynb ├── rag_from_scratch_12_to_14.ipynb ├── rag_from_scratch_15_to_18.ipynb ├── rag_from_scratch_1_to_4.ipynb └── rag_from_scratch_5_to_9.ipynb /README.md: -------------------------------------------------------------------------------- 1 | # RAG From Scratch 2 | 3 | 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](https://www.anyscale.com/blog/fine-tuning-is-for-form-not-facts) and [can be costly](https://www.glean.com/blog/how-to-build-an-ai-assistant-for-the-enterprise). 4 | 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. 5 | These notebooks accompany a [video playlist](https://youtube.com/playlist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0x&feature=shared) that builds up an understanding of RAG from scratch, starting with the basics of indexing, retrieval, and generation. 6 | ![rag_detail_v2](https://github.com/langchain-ai/rag-from-scratch/assets/122662504/54a2d76c-b07e-49e7-b4ce-fc45667360a1) 7 | 8 | [Video playlist](https://www.youtube.com/playlist?list=PLfaIDFEXuae2LXbO1_PKyVJiQ23ZztA0x) --------------------------------------------------------------------------------