HN Explorer

jxnlco

↗ HN profile [ 96.1 ms ] full profile
Karma
83
Created
February 16, 2023 (3y ago)
Submissions
0
  1. Why RAG is more than just vector search (timescale.com)
    5 points 0
  2. Best Tools for Indie Tech Consultants (jxnl.co)
    2 points 0
  3. 1 points 0
  4. 1 points 0
  5. 1 points 0
  6. Systematically Improving Your RAG (jxnl.co)
    176 points 53
  7. Show HN: Instructor v1, for LLM structured output and streaming (python.useinstructor.com)
    5 points 0
  8. Structured Data for Open-Source LLMs (jxnl.github.io)
    2 points 0
  9. Stop Using LGTM Few for RAG (jxnl.github.io)
    1 points 0
  10. How to Ship an AI Application MVP (jxnl.github.io)
    1 points 0
  11. Embedding (RAG) all of Wikipedia in less than 15 minutes (modal.com)
    7 points 0
  12. 1 points 0
  13. Steering Large Language Models with Pydantic (blog.pydantic.dev)
    5 points 0
  14. 1 points 0
  15. 1 points 0
  16. Python caching decorators in three levels (jxnl.github.io)
    10 points 0
  17. Validating LLM Citations with Pydantic (jxnl.github.io)
    1 points 0
  18. Introduction to async batching using `asyncio` and `OpenAI` (jxnl.github.io)
    6 points 0
  19. At the Intersection of LLMs and Kernels – Research Roundup (charlesfrye.github.io)
    6 points 0
  20. Good LLM Validation Is Just Good Validation (jxnl.github.io)
    2 points 0
  21. Distilling Python Functions into an LLM Finetune (jxnl.github.io)
    3 points 0
  22. RAG is more than just embedding search (jxnl.github.io)
    151 points 58
  23. Improving OpenAI Function Calling Usability in Python (medium.com)
    8 points 0
  24. Show HN: Automatic YouTube Chapters and Summaries (youtubechapters.app)
    1 points 0
  25. 1 points 0