Birbla

What is a good format for a tool to report data to a LLM?

What is a good format for a tool to report data to a LLM?

4 pointsby michaelmure6 comments

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • provide a summary,Provide metadata again;Expand the complete content when needed
    by welcomezhangjun
  • In my experience, LLMs are really good with SQL. If you can structure your data into easily queryable SQL data, your LLM will be able to generate queries to get what it needs really effectively
    by vivekyyy
  • Standard disclosure of "I'm no LLM expert".

    Could tokens be pre-embedded and saved? Suppose you're transferring a context to another agent. Currently I just copy/paste, tell the other agent to reference a .md file.

    What is I could get a "compressed" binary file containing the context in the embedding space. Then the other agent can consume that and continue on it's merry way.

    by kooi
  • I'm asking this because as I wrote a new CLI tool I picked json as the recommended output format for LLMs. I noticed though that they easily get lost and generally consume a lot of tokens to analyse the output. I'm sure it would work well when the LLM is trained for and already know what to expect, but that doesn't work for a new tool.

    So, what's the natural language for them?

    by michaelmure
  • I settled on JSONL for an LLM-optimized output format. Rationale: https://github.com/Leftium/gg/blob/main/specs/completed/gg-a...

    Combine that with context mode: https://hw.leftium.com/i/47193064

    by Leftium

Explore Birbla archives