rlama
AI
retrieval augmented generation
SHOW HN2025
How HN took it
2 positive, 12 neutral or asking, 0 mixed, 6 critical, out of 20 comments about the project. Thread score -0.14.
Idea: 2 for, 2 againstExecution: 0 for, 2 againstPerformance: 0 for, 2 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
Single binary distribution and Go implementation appreciated
From 2 comments
What is the architecture/tech-stack used in building this? I didn't find this info neither on github readme, nor on website. I like the fact that it is written in Go and small…
foundzen on HNReally nice project, congrats & great work! Quick notes: - as an end user, some primary concerns re apps using the file system: ``` - who will be able to read it? does the app…
mentalgear on HN
Useful idea of local document AI
From 2 comments
This is cool and pretty much what I was wondering about, I mean obvious it was possible, cool to see it implemented. Looking forward to having a play. I am building a tool purely…
TheNicholasNick on HNThis is great! It would be great if there were an API interface for integration into other systems.
ding444 on HN
Objections
No chunking; whole documents embedded and truncated, so retrieval fails on long books
From 1 comment
This appears to do no chunking. It just shoves the entire document (entire book, in my case) into the embedding request to Ollama. So it's only helpful if all your documents are…
andai on HN
Hallucination risk and lack of source citation
From 1 comment
I feel very doubtful on usefulness of these tools because of hallucinations. How reliable is this one in comparison with others like these? How well does it cite the source? To…
smusamashah on HN
Requires Python dependencies for text extraction, undermining single binary
From 2 comments
rlama requires a python install (and several dependencies via pip) to extract text. https://github.com/DonTizi/rlama/blob/main/internal/service/document_loader.go#L448
andai on HNDefeats the point of the single binary installation if you have to set up dependencies.
Xiol32 on HN
Custom vector store less performant than established options
From 1 comment
Why not use an established open source vector db like pg_vector etc? I imagine your implementation is not going to be as performant
dcreater on HN
Requests
Add chunking with overlap
From 2 comments
This appears to do no chunking. It just shoves the entire document (entire book, in my case) into the embedding request to Ollama. So it's only helpful if all your documents are…
andai on HNI have just implemented chunking with overlap for larger documents to split texts into smaller chunks and ensure access to all documentation in your RAG. It's currently in the…
Dontizi on HN
Support llama.cpp backend
Add an API interface
From 2 comments
This is great! It would be great if there were an API interface for integration into other systems.
ding444 on HNI thought about adding an API interface for it. It is on my to-do list of things that could be good to add. For now, I'm gathering feedback to see what people like about it or not.
Dontizi on HN
Show search results and cite sources
From 2 comments
This appears to do no chunking. It just shoves the entire document (entire book, in my case) into the embedding request to Ollama. So it's only helpful if all your documents are…
andai on HNI feel very doubtful on usefulness of these tools because of hallucinations. How reliable is this one in comparison with others like these? How well does it cite the source? To…
smusamashah on HN
Support TypeScript files and privacy/file access guarantees
From 1 comment
Really nice project, congrats & great work! Quick notes: - as an end user, some primary concerns re apps using the file system: ``` - who will be able to read it? does the app…
mentalgear on HN
Questions
What is the architecture and tech stack
From 1 comment
What is the architecture/tech-stack used in building this? I didn't find this info neither on github readme, nor on website. I like the fact that it is written in Go and small…
foundzen on HN
What license is it released under
From 1 comment
Cool project. What license is this released under? Not seeing it documented.
mattnewton on HN
How good and reliable is the RAG answer quality
From 2 comments
How good is the RAG though? Just throwing a vector db at it doesn't make it useful...
KaoruAoiShiho on HNI feel very doubtful on usefulness of these tools because of hallucinations. How reliable is this one in comparison with others like these? How well does it cite the source? To…
smusamashah on HN
Alternatives named
Open WebUI document database
From 1 comment
> How well does it cite the source? I don't know about the OP tool, but open webui has its own document database which you can integrate with LLMs, and when answering questions…
tarruda on HN
AWS Bedrock knowledge bases
From 1 comment
Not a paid solution, but great for testing models yourself: AWS bedrock. Wonky documentation (definitely released too early), but imo the best model agnostic diy solution out…
danihh on HN
Orama hybrid search
From 1 comment
I recommend using this hybrid vector/full text search engine that works across many runtimes: https://github.com/oramasearch/orama
mentalgear on HN
chromem-go embedded vector store
From 1 comment
Hi, if you want to keep using a Go embedded/in-process vector store, but with some additional features, you can check out my project https://github.com/philippgille/chromem-go
PhilippGille on HN
Building your own RAG with Ollama tutorial
From 1 comment
Just do your own RAG. It's very easy and Ollama actually have a quick start tutorial on their page. Then you can also fine-tune the process to your needs.
magic_hamster on HN