LLMs session Fully Connected kicking off with Jerry Liu and whats beyond RAG

Build RAG using totally open and free components! We love this blog post from Elastic that uses ollama and Mistral AI to show how to put together a RAG application with LlamaIndex using entirely free software.

elastic.co/search-labs/bl…

With the release of Meta Llama3, we're entering an era where most of the major models: GPT-4-turbo, Claude, and now Llama3 are multimodal by default.

We have out-of-the-box support in LlamaIndex 🦙 for Snowflake SOTA arctic-embed models - it's a one-liner through our Hugging Face integration!

And in ~4 more lines of code, you can build a RAG indexing pipeline over your data with these embedding models.

Check out the

The latest model from Mistral AI, the hugely powerful 8x22b, defines the state of the art in open models and is now available! As usual, we have day 0 support: check out Ravi Theja's Mistral cookbook showing
➡️ RAG
➡️ Query routing
➡️ Tool use

docs.llamaindex.ai/en/latest/exam…

Build hybrid search and sub-question querying with Azure AI Search and LlamaIndex!

In this tutorial, Khye Wei of Microsoft shows you how you can use LlamaIndex with Azure's AI Search to create powerful RAG applications, including
➡️ Hybrid Search
➡️ Query rewriting
➡️ the…

Today Qdrant are launching their hybrid cloud offering, and we're delighted to be a launch partner! You can run Qdrant anywhere -- as a hosted service, at the edge, or in your own environment with full control of your data.

Check out this in-depth tutorial about how to…

We’re excited to release a brand-new tutorial series 💫 : an introduction to agents and tools 🎬🤖

There’s a lot of well-deserved interest around agents, but there’s also a lot of ambiguity about core agent interfaces and applications. This short course is the perfect beginner…

A Principled Guide to Build and Evaluate Advanced RAG 🧑‍🏫

This blog-sized masterclass in principled advanced RAG development is perfect for your weekend learning.

What we like about it - rather than dumping the hundreds of advanced techniques in LlamaIndex 🦙, this blog post…

Using LLM-generated Knowledge Graphs to Accelerate Biomaterials Discovery 🧬🧠

This paper by Markus J. Buehler constructed a massive knowledge graph over 1000 scientific papers on biological materials, in a “local-to-global” approach. By creating this massive ontology, the paper

How to do better RAG? 🤔Check out in this webinar with Jerry Liu on the shortcoming of today's RAG 👀and how a few simple tricks to create a fine-tuning data-set can vastly improve performance for in-domain RAG! And thanks to Ravi Theja RAFT is now already part of…

🎥 ICYMI: Check out the recording of our latest LlamaIndex Webinar on retrieval-augmented fine-tuning (RAFT)!

In the webinar, Tianjun Zhang and Shishir Patil, the lead co-authors of RAFT, explain how combining an “open-book exam” approach (RAG) with a “closed-book exam”…

A key challenge in productionizing LLM apps is data management - how do you deal with live, constantly changing data while minimizing cost and latency?

Both LlamaIndex 🦙 open-source and LlamaCloud have key features for efficiently managing documents, their associated chunks, and…

Here’s a great reference guide for building a full-stack RAG application with AWS Bedrock 👇

1. Setup access to Bedrock embeddings/LLMs
2. Use LlamaIndex 🦙 to index and retrieve over PDFs
3. Build a full-stack Streamlit interface that you can interact with

Big shoutout to…

E2E RAG Stack powered by cohere

This is an excellent thread by Akshay 🚀 showing you how to use ALL the latest and greatest cohere models to build a state-of-the-art RAG pipeline

This includes the following:
1. cohere ⌘R+ LLM
2. cohere Embed V3
3. cohere's latest…

Chain of Abstraction ⛓️💭

Lots of LLMs (OpenAI, Mistral AI, Anthropic) now support function calling for single-shot tool use, but existing frameworks struggle with multi-step query planning with tool use.

Chain of Abstraction by (@silin_gao et al.) is a new technique where…

Introducing create-tsi - a toolkit to generate a full-stack, enterprise-grade (GDPR compliant) AI Application through a CLI interface! 🇪🇺🛠️🤖

This was done in collaboration with T-Systems, Marcus Schiesser, and inspired by the LlamaIndex 🦙 create-llama toolkit.

Build a…

Ready to build a “Chat with your GitHub repository” application with Mistral via ollama, Weaviate • vector database, and LlamaIndex 🦙?

I’ve just dropped a Lightning AI ⚡️ Studio template.
No setup, just copy and dive right into action.

Jump right in here: lightning.ai/weaviate/studi…