Viewing profile — ArnavAgrawal03

you can do that with Morphik already :) We use an embedding model that processes videos and allows you to perform RAG on them.

Came here to say I love Ocaml too

We use a BSL for our product ( https://morphik.ai ) and usually stay away from calling it anything. We'd just say "repo is public at: https://github.com/morphik-org/morphik-core ".…

we used multi-vector models at Morphik, and I can confirm the real-world effectiveness, especially when compared with dense-vector retrieval.

> They had known him for only 15 seconds, yet they still perceived the act of snapping him in half as violent. This is right out of Community

Our argument in general is that even in the non-flattened cases, we see complex diagrams pop up in documents that won't work with a text-based approach. In the context of RAG, the …

Would love to try our hand at it! We have a couple magazine use cases, but the harder it is, the more fun it is :)

Would love feedback :)

Yes! We have a use case in production with over a million pages. MUVERA is good for this, since it is basically akin to regular vector search + re-ranking. In our current setup, we…

For HTML, in a lot of cases, using the tags to chunk things better works. However, I've found that when I'm trying to design a page, showing models the actual image of the page lea…

Completely agree with this. This is what we've observed in production too. Embedding images makes the RAG a lot more robust to the "inner workings" of a document.

You can add OCR with Gemini, and presumably that would lead to better results than the OCR model we compared against. However, it's important to note that then you're guaranteeing …

Multimodal RAG is exactly what we argue for. In their original state, though, multivectors (that form the basis for multi-modal RAG) are very unwieldy - computing the similarity sc…

This would depend on the exact use case. Feeding in the invoice directly to the model is - in my opinion - the best way to approach this. If you need to search over them, then dire…

That's an interesting point. We've found that for most use cases, over 5 pages of context is overkill. Having a small LLM conversion layer on top of images also ends up working pre…

I've used your product and particularly like that you show bugs in a table instead of littering my entire PR. Does Jazzberry run on the entire codebase, or does it look at the spec…

While we don't use this yet, it seems very promising - thanks! We did something similar (with libreoffice, for example) to have support for non PDF datatypes, but this seems like i…

totally agree that air-gapped provides unparalleled peace of mind. That's a major reason why we have strong support for local deployment. Nice to know that our hypothesis is somewh…

No, you can bring your own LLM. In the cloud, we're querying gpt-4o. We're looking to expand to have some fine-tuned VLMs for document parsing and extraction further in the roadmap…

Yes! If you're running the local version and it's taking long, that an indication that your GPU isn't being used properly. This can be traced back to the `colpali_embedding_model.p…

Hey! what format of files are you uploading? seems to work ok on my end...

Thanks for the feedback :) We're using the MCP daily as we develop Morphik further. Thought it would be a nice thing to share. "I used the stones to [make] the stones" haha

Thank you!! It works particularly well with those. We use ColPali-style embeddings for our visual doc search. As a result, we're not limited by parsing quality the same way typical…

Just adding some of our roadmap here as well: - AST parsing and conversion to visual graphs for easier understanding of large codebases - Integrate custom knowledge graph editing, …