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: What are you building LLM/RAG chatbots with

7 pointsby petervandijckabout 1 year ago
LangChain? Cohere? LLamaIndex? DIY?<p>Are you finding specific pros&#x2F;cons for some of the ones that try to be a platform. As an example, we&#x27;ve found LangSmith&#x27;s integration with LangChain super useful, even though LangChain itself has its pros and its cons.

3 comments

simonwabout 1 year ago
I&#x27;m mainly hacking around with my LLM CLI tool, experimenting with different combinations of embedding models and LLMs: <a href="https:&#x2F;&#x2F;til.simonwillison.net&#x2F;llms&#x2F;embed-paragraphs#user-content-answering-a-question" rel="nofollow">https:&#x2F;&#x2F;til.simonwillison.net&#x2F;llms&#x2F;embed-paragraphs#user-con...</a><p>I really need to add a web interface to that so it&#x27;s a bit more accessible to people who don&#x27;t live in the terminal!
评论 #39759828 未加载
LorenDBabout 1 year ago
I&#x27;m taking a DIY approach to RAG&#x2F;function calling for a work tool. We&#x27;re looking for data sovereignty, so we&#x27;re probably going to self-host. To that end, I&#x27;m using Ollama to serve some models. If you want to do DIY I would highly recommend using NexusRaven for your function calling model.<p>No promises but I&#x27;m hopeful we can opensource our work eventually.
评论 #39760535 未加载
评论 #39759529 未加载
bovemabout 1 year ago
I used LangChain and models hosted on Ollama for my latest project [1]. Since I have a GPU now and Ollama is now available for Windows I can build LLM based applications quickly with local debugging.<p>[1] <a href="https:&#x2F;&#x2F;github.com&#x2F;bovem&#x2F;chat-with-doc">https:&#x2F;&#x2F;github.com&#x2F;bovem&#x2F;chat-with-doc</a>