TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

LlamaIndex: Unleash the power of LLMs over your data

208 pointsby danboarderalmost 2 years ago

9 comments

mritchie712almost 2 years ago
If you&#x27;re interested in the SQL component of this, we&#x27;re building a product strictly focused on that at <a href="https:&#x2F;&#x2F;www.definite.app&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.definite.app&#x2F;</a>. We let non-technical users ask questions of their SQL database. We do this by:<p>1. Pulling in your schema information and structuring it in a way LLM&#x27;s can reason about it<p>2. Pulling in your prior query history against the database to understand how you actually use your data (e.g. what JOIN&#x27;s are common, what tables are used most frequently, etc.)<p>3. Adding context from other tools you may be using (e.g. we can pull in metadata and tests from your dbt project)<p>We also have a Slackbot you can add to your #urgent-data-requests channel. If you @Definite in a thread, it&#x27;ll parse out messages that can be converted to SQL tasks and return the answer from your database.<p>You could certainly build this yourself with (or without) LlamaIndex, but it&#x27;s still quite a bit of work to set up.
评论 #36643474 未加载
评论 #36643936 未加载
评论 #36650974 未加载
评论 #36643550 未加载
评论 #36644079 未加载
patrakovalmost 2 years ago
The name is misleading: this project is not based on LLaMA as released by Meta. It sends data to OpenAI by default.
评论 #36642536 未加载
评论 #36645626 未加载
freezed88almost 2 years ago
Hey all! Jerry here (from LlamaIndex).<p>We love the feedback, and one main point especially seems to be around making the docs better: - Improve the organization to better expose both our basic and our advanced capabilities - Improve the documentation around customization (from LLM&#x27;s to retrievers etc.) - Improve the clarity of our examples&#x2F;notebooks.<p>Will have an update in a day or two :)
qwertoxalmost 2 years ago
There once existed Google Desktop which was really useful.<p>Is this something similar, but with the added feature of being able to query the data with the help of a LLM?<p>Like: Find me all the text files which I&#x27;ve modified last month, there should be one containing a log snippet with a TODO I added to it.
rollinDynoalmost 2 years ago
I gave this a shot a while back and found plenty of examples but little documentation.<p>For instance, there is a tree structure for storing the embeddings and the library is able to construct it with a single line. However, I couldn’t find an clear explanation of how that tree is constructed and how to take advantage of it.
评论 #36646181 未加载
评论 #36646079 未加载
ramozalmost 2 years ago
If you’re doing legitimate retrieval rerank in the commercial enterprise setting, then I doubt this is a library that can support you beyond prototyping.<p>Retrieval involves complex integration (not just data connectors and open API wrappers), and meaningful rerank requires domain&#x2F;context-specific trained models (that you can deploy performantly and cost effectively). If you’re doing these things, you’re well beyond the capability at platform scale vs what a python library provides
评论 #36645480 未加载
bandyabootalmost 2 years ago
This sounds really cool. I predict it will consume a good chunk of my free time in the next week or so.
poxrudalmost 2 years ago
Is this an alternative&#x2F;competitor to langchain? If so which one is easier to use?
评论 #36644285 未加载
评论 #36647754 未加载
评论 #36646210 未加载
评论 #36645982 未加载
aleccoalmost 2 years ago
What&#x27;s the difference vs embeddings on a vector database combined with GPT?
评论 #36642746 未加载
评论 #36644005 未加载