Neum AI
AI
rag framework
SHOW HN2023
How HN took it
0 positive, 14 neutral or asking, 0 mixed, 5 critical, out of 19 comments about the project. Thread score -0.25.
Privacy: 0 for, 2 againstIdea: 0 for, 2 againstExecution: 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
Semantic chunking and metadata handling seen as useful ideas
From 2 comments
Yeah, we were playing around with doing some semantic chunking. Works okay for some use cases. We have some ideas to go further on that. Generally we have found that recursive…
ddematheu on HNLlamaIndex is pretty awesome. There are a couple areas where we think we are driving some differentiation. 1. The management of metadata as a first class citizen. This includes…
ddematheu on HN
Objections
Frameworks are thin ETL wrappers; direct engineering is as easy
From 2 comments
Very bearish on these frameworks and abstractions. Yes, obviously useful for prototyping and creating hype articles & tweets with fun examples. However any engineer is capable of…
ramoz on HNThe problem is that business people have been just rubbing together libraries for decades making money (though maybe not the MOST) and will see these frameworks as a "simple" way…
hobs on HN
Semantic chunking runs LLM-generated code without sanitizing
From 2 comments
Don't you find it dangerous to just run the code w/o any sanitizing? Why not capture a few strategies that the LLM returns as code that can be properly audited (and ran locally…
hrpnk on HNInteresting to see that the semantic chunking in the tools library is a wrapper around GPT-4. Asks GPT for the python code and executes it:…
hrpnk on HN
Little differentiation from LlamaIndex or Langchain
From 2 comments
How is this any different from LlamaIndex [1]? [1] https://www.llamaindex.ai
rmonvfer on HNThe problem is that business people have been just rubbing together libraries for decades making money (though maybe not the MOST) and will see these frameworks as a "simple" way…
hobs on HN
Requests
Expose more relevance and ranking control at application level
From 2 comments
Got it. I'd encourage you to expose more of that functionality at the level of your application if possible. I think there is a lot of potential in using more than just cosine…
eigenvalue on HNCool. Do you do any of the relevance calculations directly, or is that all handled by Weaviate? If so, is there any way to influence that part of it, or is it something of a…
eigenvalue on HN
Support for more data sources such as Redis
From 1 comment
Why MySQL and not PostgreSQL or Redis on the roadmap for sources?
imperio59 on HN
Questions
How does it improve retrieval compared to a plain vector DB
From 1 comment
How does the improve upon retrieval compared to just using any vector db and semantic search?
J_Shelby_J on HN
Why use this instead of Haystack
From 1 comment
If someone is about to start their project using Haystack would you suggest they instead look at Neumtry?
alchemist1e9 on HN
Alternatives named
LlamaIndex
From 1 comment
How is this any different from LlamaIndex [1]? [1] https://www.llamaindex.ai
rmonvfer on HN
Haystack
From 1 comment
If someone is about to start their project using Haystack would you suggest they instead look at Neumtry?
alchemist1e9 on HN
Langchain
From 1 comment
The problem is that business people have been just rubbing together libraries for decades making money (though maybe not the MOST) and will see these frameworks as a "simple" way…
hobs on HN
MemGPT
From 1 comment
Have you guys connected with MemGPT?
omarfarooq on HN