[HN Gopher] Unveiling Ragna: An Open Source RAG-Based AI Orchest...
___________________________________________________________________
Unveiling Ragna: An Open Source RAG-Based AI Orchestration
Framework
Author : nkaretnikov
Score : 39 points
Date : 2023-11-01 13:40 UTC (9 hours ago)
(HTM) web link (quansight.com)
(TXT) w3m dump (quansight.com)
| nkaretnikov wrote:
| 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!
| abss wrote:
| How it works?
| nkaretnikov wrote:
| 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.
| nkaretnikov wrote:
| There'll be a talk at PyData NYC 2023 on Ragna as well:
| https://nyc2023.pydata.org/cfp/talk/7DPRGM/
| esafak wrote:
| https://ragna.chat/
|
| https://github.com/Quansight/ragna
| yding wrote:
| Congrats on the launch!
| jeffchuber wrote:
| cool :) (jeff from chroma)
| raylad wrote:
| What are Ragna's competitors? Or just other options for something
| similar.
| Dnguyen wrote:
| I'm trying out the demo and it's taking forever for just one
| small file. What do you recommend for a minimum system to try
| this out?
___________________________________________________________________
(page generated 2023-11-01 23:01 UTC)