FastGraphRAG

AI

retrieval augmented generation

SHOW HN2024

457points
119comments
#82of 3,515 in 2024
Top 3%of 2024 by points

How HN took it

CuriousMostly questions and neutral comments

7 positive, 31 neutral or asking, 1 mixed, 6 critical, out of 45 comments about the project. Thread score -0.11.

Idea: 4 for, 2 againstDocs: 0 for, 2 againstPerformance: 1 for, 0 againstPricing: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Useful idea applying PageRank to graph retrieval

    From 2 comments
    • Super interesting, thanks for sharing. How large a corpus of domain specific text do you need to obtain a useful knowledge graph? Aider has been doing PageRank on the call graph…
      anotherpaulg on HN
    • Cool idea. IMHO traditional information retrieval is the way to go with RAG. Vector search is nice but also slow and expensive and people seem to use it as magic pixie dust. It…
      jillesvangurp on HN

Objections

  • Documentation in README is thin on how it works

    From 2 comments
    • Wonder why this all - here on HN - is not part of the readme .md which says absolutely nothing about how and why this all would work. The whole approach to representing the work,…
      larodi on HN
    • I might be the wrong target audience (I do have a great interest in this, but I am not doing it at a professional level) but I feel the GitHub could explain things a bit better —…
      andai on HN
  • Very similar to existing projects like nano graphrag and HippoRAG without credit

    From 2 comments
    • It looks awfully similar to nano graphrag, but I fail to see any credits to it.
      dantodor on HN
    • What is the difference to HippoRAG, which seems to be the same approach but came our earlier?
      zwaps on HN
  • Pricing is unclear between free tier and self-hosting

    From 1 comment
    • Cool! But I'm confused on your pricing. The github page says first 100 requests are free but the landing page says to self host if you want to use for free. I signed up and used…
      davidsainez on HN

Requests

  • Add Neo4j and other graph database connectors

    From 1 comment
  • Benchmark results on multi-hop retrieval datasets

    From 2 comments
    • Do you have any retrieval and generation metric scores (eg, KILT or NQ datasets)? I know benchmark datasets are not the be-all-end-all, but a halfway decent score and…
      gillesjacobs on HN
    • Thanks for releasing this! Have you gotten a chance to run any multi-hop retrieval benchmarks? It would be very useful to be able to compare this method to other establishes RAG…
      lordofgibbons on HN

Questions

  • How does it compare to HippoRAG and LightRAG

    From 2 comments
    • What is the difference to HippoRAG, which seems to be the same approach but came our earlier?
      zwaps on HN
    • I'm curious how the implementation compares with LightRAG (https://github.com/HKUDS/LightRAG) ?
      redwood on HN
  • How well does it answer broad questions

    From 1 comment
    • How is it at answering broad questions? Communities and clustering were specifically for that purpose of agglomerating, right?
      fudged71 on HN
  • Can it be used with LLMs other than OpenAI

    From 1 comment

Alternatives named

  • Microsoft GraphRAG

    From 1 comment
  • HippoRAG

    From 1 comment
    • LLMs are only used to construct the graph, to navigate it we use an algorithmic approach. As of now, what we do is very similar to HippoRAG…
      liukidar on HN
  • LightRAG

    From 1 comment
    • I'm curious how the implementation compares with LightRAG (https://github.com/HKUDS/LightRAG) ?
      redwood on HN
  • nano graphrag

    From 1 comment
    • It looks awfully similar to nano graphrag, but I fail to see any credits to it.
      dantodor on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/42174829)