GitHub - stanford-futuredata/ColBERT: Stanford ColBERT: stat...

GitHub - stanford-futuredata/ColBERT: Stanford ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22)

github.com

RelatedHighlights

In some applications, such as inline code suggestions, the best AI models are too expensive, so tools like Github Copilot use carefully tuned smaller models and various search heuristics to provide results. In other applications, even the largest models, like GPT-4, are too cheap!

Matei Zaharia, Omar Khattab, Lingjiao Chen, et al. • The Shift From Models to Compound AI Systems

Maximum Marginal Relevance (MMR): We can apply diversity-based re-ranking of documents during retrieval to get results that cover different perspectives or points of view from the documents retrieved so far.

Ben Auffarth • Generative AI with LangChain: Build large language model (LLM) apps with Python, ChatGPT, and other LLMs

Better RAG Results With Reciprocal Rank Fusion and Hybrid Search

John Wang assembled.com

Multiple indices. Splitting the document corpus up into multiple indices and then routing queries based on some criteria. This means that the search is over a much smaller set of documents rather than the entire dataset. Again, it is not always useful, but it can be helpful for certain datasets. The same approach works with the LLMs themselves.

Matei Zaharia, Omar Khattab, Lingjiao Chen, et al. • The Shift From Models to Compound AI Systems

Ben Auffarth • Generative AI with LangChain: Build large language model (LLM) apps with Python, ChatGPT, and other LLMs

Better RAG Results With Reciprocal Rank Fusion and Hybrid Search

Matt Rickard • Improving RAG: Strategies