hackathon time: MongoDB with support of Fireworks AI, Upstage, and LlamaIndex 🦙 in SF
let‘s see what I can learn 🧵 — it will be a long day: 9:30am breakfast and planned finish at 10pm

JSON structured output from invoice document with Llama3:8b Instruct. Running in Sparrow RAG with LlamaIndex 🦙, Weaviate • vector database and ollama 🚀

Katana

Of course, with Meta's Llama 3 release, we also need a template that uses it in create-llama.

Call `npx create-llama` and select the `nextjs-llama3` community template.

Running with LlamaIndexTS, the Typescript version of LlamaIndex 🦙.

Excited to feature a fantastic tutorial on building a local coding agent 🤖💻 by Tech With Tim!

This agent will take in user requests and write code.

✅ It is RAG-augmented: equipped with a LlamaParse + LlamaIndex 🦙 powered RAG tool to help look up relevant information from

How to build a RAG app using MetaAI's Llama-3 (100% local):

Build a full-stack local RAG application with Llama 3 🧵

Stack: LlamaIndex 🦙, ollama, Streamlit, Lightning AI ⚡️

Llama 3 is the most powerful open-source LLM to date, and the best part is you can run it completely locally!
Amazing work by Akshay 🚀 for a day 1 tutorial

Learn how to build an agent that reads your documentation to write code for you! In our latest collaboration with Tech With Tim, you'll learn how to:
➡️ Set up local LLMs with ollama
➡️ Parse documentation with LlamaParse
➡️ Build an agent
➡️ Teach the agent to write code!

arxiv.org/abs/2404.11792

Real-Reasoning RAG, or Where to Get Performance Gains Out of RAG (from A I T O M A T I C & IBM Research, #AIAlliance ):

• Fine-tuning the retriever model gives you more bang for your buck than the generator model.
• Employing reasoning yields significant

Let's build a RAG app using MetaAI's Llama-3 (100% local):

🦙🔥

The llama^3 stack 🦙🦙🦙: Llama 3 + ollama + LlamaIndex 🦙

The primary stack you should be using for high-performing local LLM applications.

Build amazing apps powered by local models, from CLI RAG tools that index your entire file system to local agents that can automate your

Firecrawl is awesome 🔥

One of the most popular data sources for any LLM app is web pages, whether you're building QA search or a browser agent.

A huge blocker has been figuring out how to parse HTML appropriately. Leaving the raw tags in creates a ton of clutter and messes up

To get the best performance out of Llama 3 (AI at Meta), you need to apply special tokens!

Our day 0 LlamaIndex 🦙 cookbook lets you build RAG with Llama 3 with in-built support for special tokens, like end-of-turn and begin-of-text.

The capabilities are impressive. The 8B and

Want to run Llama 3 locally instead? Our friends at ollama have gotchu! Just `ollama run llama3` and you're good to go, follow our notebook and change 'llama2' to 'llama3': docs.llamaindex.ai/en/stable/exam…

twitter.com/ollama/status/…

Meta'a Llama 3 model is released and we have day 0 support! Ravi Theja and Logan Markewich put together this cookbook showing how to use Llama 3 directly from Hugging Face, from running basic prompts to a full RAG pipeline:

docs.llamaindex.ai/en/latest/exam…

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

500 stars by Day 2 🤯 We're working hard to implement all the Firecrawl feedback

Here is what we shipped today:
🧹 - Remove non content elements (option)
📄 - PDF parsing powered by LlamaIndex 🦙
🖼️ - Absolute paths on images
📁 - New docs website powered by Mintlify

🧵👇

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…

Build RAG, Function Calling, and Agents with LlamaIndex 🦙 and Mistral AI 8x22b - the most powerful Mistral AI model to date, and the best model in its (active) parameter class so far!

Features: 64k token context, multilingual, coding, function calling, math, and more. Uses 39B