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.

Show HN: RAG on HN comments in 34 LOC

6 pointsby benzguo10 months ago

3 comments

benzguo10 months ago
Little demo that searches Hacker News comments for a topic (using <a href="https:&#x2F;&#x2F;hn.algolia.com&#x2F;api" rel="nofollow">https:&#x2F;&#x2F;hn.algolia.com&#x2F;api</a>), extracts sentiment and other metadata, then generates a research summary. Really proud of the API we&#x27;ve built at <a href="https:&#x2F;&#x2F;substrate.run" rel="nofollow">https:&#x2F;&#x2F;substrate.run</a> – you don&#x27;t have to think about graphs, but you implicitly create a DAG by relating tasks to each other. Because you submit the entire workflow to our inference service, you get automatic parallelization of dozens of LLM calls for free, zero roundtrips, and much faster execution of multi-step workflows (often running on the same machine).
bosch_mind10 months ago
I’m new to RAG, but have been learning about it lately for fun and it’s pretty incredible as a concept.<p>What are your thoughts around these frameworks like llama index and langchain? Being a seasoned engineer, it seems like a ridiculous amount of fluff around an already simple process.
Something123410 months ago
How do I run it?
评论 #40971985 未加载