TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Ask HN: Best tools to create LLM prodcuts?

4 pointsby funerralmost 2 years ago
I'd like to maximize DX. I'm looking for reasonable pricing for embedding databases, fine-tuning models and chatbot interfaces. What's the best game in town for those?

2 comments

tikkunalmost 2 years ago
1. Embedding databases: pgvector, storing embeddings in plain json (if you don&#x27;t have too many), chroma, weaviate, pinecone<p>2. Fine-tuning: The better a model is, the more it&#x27;s worth fine tuning it. GPT-4 is the best model by far. To fine tune it you need to be an OpenAI foundry customer, 6 figures plus spend. Otherwise, any GPU compute provider can allow you to fine tune an open model<p>3. Interfaces: Not quite sure what you mean here, but Vercel has some templates&#x2F;open source examples
kacperlukawskialmost 2 years ago
Definitely Qdrant is a great option. It&#x27;s an open source vector DB, so you can experiment locally without any cost, but if you prefer managed solution Qdrant Cloud is an option: <a href="https:&#x2F;&#x2F;cloud.qdrant.io&#x2F;" rel="nofollow">https:&#x2F;&#x2F;cloud.qdrant.io&#x2F;</a>