Show HN: Unriddle – Create your own GPT-4 on top of any document

Re:Show HN: Unriddle – Create your own GPT-4 on top of any d... by shekhar101 on Monday April 03, 2023 @01:19PM (#35427679)

Can the vectorization of chunks and finding context close to query be done with any LLMs and then only relevant chunks be sent to OpenAI?

[ Parent | on HN ]

Re:Show HN: Unriddle – Create your own GPT-4 on top of any d... by naveedjanmo on Monday April 03, 2023 @01:26PM (#35427805)

Vectorisation is done via OpenAI's embedding API. And the chunking/querying is happens through the Langchain library. But there are a few different ways of doing it - another good library is LLamaIndex.

[ Parent | on HN ]

Re:Show HN: Unriddle – Create your own GPT-4 on top of any d... by shekhar101 on Monday April 03, 2023 @01:57PM (#35428436)

Thanks a lot! Do you _have_ to do vectorization and querying with the same LLM? Can someone do vectorization with 1 and do querying with reevant chunks with another?

[ Parent | on HN ]