Knowledge retrieval architectures for LLMs (2023)

Re:Knowledge retrieval architectures for LLMs (2023) by triyambakam on Thursday April 27, 2023 @05:59PM (#35735121)

This is super helpful. I'm building a document question-answering service over a custom data corpus (related to Saivism, a sect of Hinduism). So far the first pass has been to manually chunk the text (based on headings, chapters etc.) and then I've used OpenAI's embedding service and storing the embeddings in Pinecone. All stiched together using LangChain. To ask a question, the question is again embedded, then searched against the vector store, then the related documents are provided as context to the LLM along with the question.

So far it was really easy to set up the prototype, but the results weren't as great as I had hoped, so I'm excited to see how I could improve it.

Edit: wow, I didn't see this before. LangChain implements one of the featured article's suggestions (HyDE) - https://python.langchain.com/en/latest/modules/chains/index_...

[ Parent | on HN ]

Re:Knowledge retrieval architectures for LLMs (2023) by kaycebasques on Thursday April 27, 2023 @08:35PM (#35736227)

This is the same approach that Supabase Clippy took: https://supabase.com/blog/chatgpt-supabase-docs

They called it "context injection" but the OpenAI community appears to call it "retrieval-augmented generation".

Edit: I see now that Matt's post is talking all about these ideas. I'm happy that the terminology around this space is solidifying.

(Tangent) I will go to the grave continuing to call it Supabase Clippy even though presumably this prediction from the Supabase blog post became true:

> Today, we're doing our part to support the momentum by releasing “Supabase Clippy” for our docs (and we don't expect this name to last long before the lawyers catch on).

[ Parent | on HN ]

Re:Knowledge retrieval architectures for LLMs (2023) by kiwicopple on Thursday April 27, 2023 @09:10PM (#35736435)

The lawyers haven’t reached out yet! Too distracted with all the LLM-generated emails they are getting sent no doubt

[ Parent | on HN ]

Re:Knowledge retrieval architectures for LLMs (2023) by triyambakam on Thursday April 27, 2023 @11:29PM (#35737171)

Why call it Clippy at all if you anticipate a conflict? It feels immature.

[ Parent | on HN ]

Re:Knowledge retrieval architectures for LLMs (2023) by kiwicopple on Friday April 28, 2023 @12:26AM (#35737468)

yes, it's immature, however in January not many companies had created something like this and it was the most analogous way of explaining the functionality. it's also memorable

[ Parent | on HN ]

Re:Knowledge retrieval architectures for LLMs (2023) by freezed88 on Thursday April 27, 2023 @08:44PM (#35736291)

depending on what questions you're asking, you could check out LlamaIndex query capabilities - can define different index structures for different queries + can plugin to your langchain workflow: https://gpt-index.readthedocs.io/en/latest/use_cases/queries...

[ Parent | on HN ]