Hacker News Reader

nkaretnikovon Unveiling Ragna: An Open Source RAG-Based AI Orchestration Framework

Could you start a new discussion here? https://github.com/Quansight/ragna/discussions

nkaretnikovon Unveiling Ragna: An Open Source RAG-Based AI Orchestration Framework

There'll be a talk at PyData NYC 2023 on Ragna as well: https://nyc2023.pydata.org/cfp/talk/7DPRGM/

nkaretnikovon Unveiling Ragna: An Open Source RAG-Based AI Orchestration Framework

Are you asking about the query/tokenization or the overall architecture?

I assume it's the former. It's explained in the post after the diagram, see "The diagram illustrates a series of steps [...]".

We get a user query. Based on that query, we pull relevant parts from the doc. Then, we submit both the query and the doc parts to an LLM. This limits the amount of data we need to send and allows the user to know which parts of the doc are relevant.

nkaretnikovon Unveiling Ragna: An Open Source RAG-Based AI Orchestration Framework

My colleagues at Quansight released Ragna. It's pretty cool!

In the blogpost, there's a demo: you upload a pdf, ask ML model a question, it answers and shows which pages it looked at in the document. If you don't trust the output, you can double-check the doc since you have the page numbers.

Ragna currently ships with pre-built extensions for OpenAI, MosaicML, Anthropic, and local LLMs as well as the Chroma and LanceDB vector databases. And it's open source, too!

nkaretnikovon PyTorch: The Most Complex Software Project in the World Keeps Getting Better

I've written an article about PyTorch! It's meant for non-PyTorch devs and focuses on software architecture. Enjoy!