Yasyf Mohamedali and I built Summ, an open-source tool that provides intelligent search and question-answering across large sets of transcripts. ⚡️ We turn your unstructured transcripts into queryable SQL and JSON! Try it out and read how we did it here:

To answer a query, we pick the best of three methods. The first two methods use LLMs to create and populate a "database" with relevant metrics to answer a question. The last method uses recursive summarization, summarizing sets of facts to eventually answer the query.

Check out the repo here: And the docs here:

@yasyf I'm extremely interested in this. Have a couple of creators of video channels with large archives which have immense knowledge trapped inside MP4 files, and that knowledge needs to be indexed and summarized and interacted with.

@yasyf This is incredible!

@yasyf @_StevenFan

@yasyf Added to list of OP stack (OpenAI + Pinecone) projects:

@yasyf This is amazing. Also super smart way to display the results and showing potential other queries at the same time

@yasyf This may be even easier to develop using the integration with @gpt_index

@yasyf Super cool!

@yasyf This is incredible! Building out something similar for google docs and going to use this PS : Adding to my AI newsletter