Introducing
LlamaIndex
2024-11-12 BoxWorks
Why should I care about this?
LLMs: a revolution in understanding
Retrieval-Augmented Generation
(RAG)
How RAG works
Basic RAG pipeline
What is LlamaIndex?
Python: docs.llamaindex.ai
TypeScript: ts.llamaindex.ai
Why LlamaIndex?
- Build faster
- Skip the boilerplate
- Avoid early pitfalls
- Get best practices for free
- Go from prototype to production
- 3M+ monthly downloads
- 20k+ Discord members
- 600+ integrations
- 34k+ GitHub stars
- 200k+ followers on LinkedIn
- 70k+ followers on Twitter/X
LlamaIndex is an ecosystem
Trusted in production
LlamaHub
- Data loaders
- Embedding models
- Vector stores
- LLMs
- Agent tools
- Pre-built strategies
- More!
LlamaParse
Free for 1000 pages/day!
“As an AI Applied Data Scientist who was granted one of the first ML patents in the U.S., and who is building cutting-edge AI capabilities at one of the world’s largest Private Equity Funds, I can confidently say that LlamaParse from LlamaIndex is currently the best technology I have seen for parsing complex document structures for Enterprise RAG pipelines. Its ability to preserve nested tables, extract challenging spatial layouts, and images is key to maintaining data integrity in advanced RAG and agentic model building.”
— Dean Barr, Applied AI Lead at Carlyle
LlamaCloud
2. Get on the waitlist!
1. Sign up!
Let LlamaIndex
build LlamaIndex
for you
Select source
Enter credentials
Embedding model
Vector store
Deploy!
Build your app
RAG is just the beginning
Thanks!
Follow me on BlueSky:
@seldo.com
