You loved the first one, so we're doing another! LlamaIndex is hosting our second RAG-a-thon in cooperation with Pinecone and Arize AI! Hosted at the 500 Global offices in Palo Alto, the hackathon will run a whole weekend from October 11-13, so you have plenty of time to register and think of ideas! As always we love to see your RAG applications, and this time around we're particularly interested in seeing what you can build with agentic solutions. Current prizes are $3500 in cash and expected to rise as we get more sponsors on board! Stay tuned for more details, but you can register here: https://lnkd.in/g5z3pciV
LlamaIndex
Technology, Information and Internet
San Francisco, California 191,672 followers
The central interface between LLMs and your external data.
About us
The data framework for LLMs Python: Github: https://github.com/jerryjliu/llama_index Docs: https://docs.llamaindex.ai/ Typescript/Javascript: Github: https://github.com/run-llama/LlamaIndexTS Docs: https://ts.llamaindex.ai/ Other: Discord: discord.gg/dGcwcsnxhU LlamaHub: llamahub.ai Twitter: https://twitter.com/llama_index Blog: blog.llamaindex.ai #ai #llms #rag
- Website
-
https://www.llamaindex.ai/
External link for LlamaIndex
- Industry
- Technology, Information and Internet
- Company size
- 2-10 employees
- Headquarters
- San Francisco, California
- Type
- Public Company
Locations
-
Primary
San Francisco, California, US
Employees at LlamaIndex
Updates
-
This blog by Kameshwara Pavan Kumar Mantha shows you how to build a local multi-agent system that relies on RabbitMQ to broker communication between different agents (and uses Ollama + Qdrant!) This entire setup is possible with llama-agents - our main tool to help you build agents in production. The end result is a research assistant that can look up information from various tools and synthesize a response. Take a look at the RabbitMQ console to view the system metrics 📈 Blog: https://lnkd.in/dhZa4caT llama-agents repo: https://lnkd.in/g37FkPyx
-
-
Join us, Weaviate, Neosync and Arize AI for a fun night of hacking and prizes on August 13! You'll get games, networking, lightning talks, and then a demo challenge where you can complete quick 10-15 minute challenges to win prizes! Sign up here: https://lnkd.in/gqFDPyWw
-
-
Observe, evaluate and optimize your RAG stack! Observability and evaluation are always hot topics in Llama-land, and this step-by-step tutorial will show you how to use Arize AI's Phoenix and LlamaTrace as well as Microsoft Azure AI Search to build a RAG app, debug and optimize it. https://lnkd.in/gF73VB_M
-
-
Composio (Composio) is a cool production-ready toolset for AI agents 🛠️ - it includes 100+ tools including Github, Slack, Salesforce, and more. We are eager to feature tutorial by the Composio team on how to build a PR review agent using Composio Github/Slack tools and LlamaIndex agent abstractions Check it out: https://lnkd.in/gHNaXk3P
-
-
We’ve found there’s a general dearth of content around deploying and productionizing your RAG application. This blog post by Benito Martin is one of the most comprehensive tutorials on showing you how to deploy and scale your “chat with your code” app on Google Kubernetes Engine, step-by-step 🧑🏫 1. First, understand how Kubernetes works 2. Write the GKE configuration file, enable horizontal/vertical scaling 3. Write the Kustomization file 4. Deploy your app and test it with Github Actions Check it out https://lnkd.in/dPtnZmaC
-
-
This is a neat blog post on building high-quality RAG on top of payslips through automated extraction. Use LlamaExtract to define a schema (or optionally infer a schema from your document), and then use the schema to perform extraction into metadata. This metadata can then be attached on top of every document for metadata filtering, better retrieval, and better LLM synthesis. Big shoutout to Chew Loong Nian for this tutorial! https://lnkd.in/gBdXcCCg Get started with LlamaExtract: https://lnkd.in/gVg5gahy
-
-
Agentic Terraform Assistant with LlamaIndex Workflows If you’re a devops engineer who’s an aspiring AI engineer, this weekend learn how to build an agentic terraform assistant with LlamaIndex and Qdrant. Define an LLM workflow to automatically generate a terraform script for any given topic (e.g. Azure), validate it, and store it. Define a RAG workflow to index these scripts into Qdrant and retrieve from it. This is a lightning quick blog post by Kameshwara Pavan Kumar Mantha on workflows, released in LlamaIndex just this past week. Workflows provide an event-driven system where each step can respond to events and respond to actions. It lets you model agent interactions with error correction, async, state management, and more. Check it out: https://lnkd.in/gS7G74_P Original workflows blog: https://lnkd.in/gqWwz7Xs
-
-
Build a ReAct agent from scratch using new LlamaIndex workflows! ReAct agents are a super-useful building block in agentic systems, which is why they're built-in to LlamaIndex. But with Workflows you can explode the internal logic and see in detail what's going on, and even visualize it with our handy-dandy built-in flow visualizer (shown below). Check out the tutorial with full code: https://lnkd.in/gxqzXdHe
-
-
AI Voice Agent for Indian Farmers India's agriculture is vital but many farmers lack access to essential government support, impacting their productivity and livelihoods. To address this, Samarth P, Manas Bam and their team have developed an AI Voice Agent during the Stellaris VP Hackathon. This solution is designed to bridge the information gap for farmers, ensuring they have easier access to necessary support. Tech Stack: 1. LlamaIndex: For constructing the AI agent. 2. Twilio: Manages phone calls and SMS services. 3. Flask: Serves as backend server. 4. OpenAI GPT-4: Powers our LLM capabilities. Check it out here: https://lnkd.in/gqwWSHGp Or check out the full repo: https://lnkd.in/gAqCZHrd
-