[HN Gopher] Retrieval powered by object storage: AMA
___________________________________________________________________
Retrieval powered by object storage: AMA
Hey everyone - I'm Jeff from the Chroma team. Chroma is the most
popular open-source vector database. Chroma now has a fully-
distributed and serverless version backed by object-storage (also
Apache 2.0). More on why and how we built this here:
https://www.trychroma.com/engineering/serverless AMA about AI,
retrieval, systems, Rust, and more.
Author : jeffchuber
Score : 10 points
Date : 2024-10-10 20:22 UTC (2 hours ago)
| SunlitCat wrote:
| Okay! I have a question, more like an observation! (Sorry I am
| maybe not your target audience, but to get things started)
|
| Many buzzwords used and after reading your project page, I
| requested the help of ChatGPT to make any sense out of it!
|
| Is what Chatgpt tells me about your interesting project right?
|
| This is what it has to say:
|
| Chroma's serverless system is designed to help developers build
| AI applications without managing servers. It allows you to
| efficiently store and retrieve data using vectors (for AI models)
| and text queries, all without needing to handle infrastructure.
| The system is scalable, cost-effective, and optimized for AI
| workloads, so developers can focus on their projects rather than
| backend management.
| jeffchuber wrote:
| Thanks ChatGPT!
|
| Yes - that's a great explanation.
| swyx wrote:
| what do you think about ColBERT? doing embedding on every token
| feels wrong in ways i can't articulate - is there a time to use
| it and not use it, or is it the one retrieval technique to rule
| them all?
| jeffchuber wrote:
| Colbert is great! - Check out
| https://github.com/AnswerDotAI/RAGatouille by the excellent
| https://x.com/bclavie
|
| Relatedly ColPali (https://arxiv.org/abs/2407.01449) is gaining
| a ton of steam in the IR community.
|
| In general we are skeptical of silver bullets in retrieval.
___________________________________________________________________
(page generated 2024-10-10 23:01 UTC)