Building an Advanced Knowledge Assistant 📚🤖 RAG was just the beginning. A huge theme we’ve noticed this year is the prevalence of companies building an advanced knowledge interface over unstructured data, to produce more unstructured outputs. Check out my talk at the AI Conference regarding the 4 main ingredients for agent interfaces within the LlamaIndex ecosystem: 1. High quality data and retrieval 2. Agentic reasoning over complex inputs 3. Agent decision-making and output generation 4. Building a scalable full-stack application Slides and resources below! Slides: https://lnkd.in/g6vQ2Fxe LlamaCloud as the data layer: https://lnkd.in/gi8dxGnt Workflows for agentic orchestration: https://lnkd.in/gqWwz7Xs
LlamaIndex
Technology, Information and Internet
San Francisco, California 203,504 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
-
Learn to build an AI Scheduler for smart meetings using Zoom, LlamaIndex & Qdrant @ the AWS Loft on September 20th! Join us for a hands-on workshop where you'll: 🚀 Create a RAG recommendation engine for meeting productivity 🔍 Use Zoom's transcription SDK to analyze missed content 🧠 Fine-tune models for more accurate meeting suggestions Our co-founder Simon Suo will be presenting the closing talk! Event details and registration: https://lu.ma/csll5v5j
-
-
LlamaIndex reposted this
AI Strategist & Ecosystem Builder | Innovation & Partnerships Leader | Driving Collaboration Between Startups & Enterprises
🚀🚀🚀 Countdown - 4 weeks to the Agentic RAG-a-thon @ 500 Global HQ in Palo Alto. A big shout out to early-adopter enterprises, Box and SAP as platinum sponsors. Let's build together, Oct. 11-13. Reg here: https://lnkd.in/gQ4NJR-z #arize #hanahaus #500global #llamaindex #pinecone Scott Hurrey Dawn Lauter Stephanie Mosqueda Collin Sommerhauser Yi Ding Laurie Voss
-
-
Build your own RAG-based document QA system with Kotaemon, an open-source UI for chatting with your documents 📚🤖 Learn how to: ➡️ Set up a clean, customizable RAG UI for end users and developers ➡️ Organize LLM & embedding models, supporting both local and API providers ➡️ Implement hybrid RAG pipelines with full-text & vector retrieval ➡️ Enable multi-modal QA support for documents with figures & tables Kotaemon offers: ✅ Multi-user login and document collection management ✅ Advanced citations with document preview ✅ Support for complex reasoning methods ✅ Configurable settings UI for fine-tuning retrieval & generation Get started with Kotaemon: https://lnkd.in/gapR3jVy
-
-
A nice quick tutorial on building retrieval-augmented generation with LlamaIndex! https://lnkd.in/gSQ8VnAh
-
Check out this Maven course, Search For RAG in the LLM era, featuring a guest lecture by Jerry Liu! You get: 🔥 Live Code Walkthroughs: Engage with code examples and implementations by coding along in real-time 🚀 Expert-led Sessions: Learn from industry veterans with over 2-decades of experience, providing practical knowhow and tricks 📚 Comprehensive Course Content: Gain a deep working knowledge of GenerativeAI technologies and their applications 🏃♀️ Intensive Week-long Case Study Sprint: Dive into practical projects like building your own LM, Customer Support Bot, and more https://lnkd.in/g-Pv4y6y
-
-
Catch a recording of Laurie Voss last week talking about Agentic RAG in 2024! This talk covers a lot of ground: ➡️ What is LlamaIndex and why should you use it? ➡️ What is RAG and how does it work? ➡️ Why RAG is necessary but not sufficient ➡️ Adding agentic strategies to improve RAG ➡️ Building full agents with reasoning, reflection and planning ➡️ LlamaIndex workflows and how to build agents with them Check it out here! https://lnkd.in/gPamCU5d
-
-
LlamaIndex reposted this
RAGapp makes hosting your custom GPTs with any LLM a breeze. v0.0.23 adds HTTPS deployments using your domains and full-state persistence. Thanks to Arturo Castellanos from William & Mary – Raymond A. Mason School of Business for sponsoring this feature! Open-source and built using LlamaIndex. 🖥️ $ docker run -p 8000:8000 ragapp/ragapp 📄 https://lnkd.in/guXjrpJe
-
Learn to build advanced LLM agents in this comprehensive course from llmagents-learning.org, including a guest lecture from co-founder Jerry Liu! 🤖🧠 Gain expertise in: 🔹 LLM foundations and essential abilities for task automation 🔹 Agent applications like code generation, robotics, and web automation 🔹 Ethical considerations, safety, and human-agent interaction Course highlights: • Guest lectures from industry leaders at Google DeepMind, OpenAI, and more • Hands-on topics covering reasoning, planning, and multi-agent collaboration • Insights into the future of AI and its impact on daily life Explore the full syllabus and enroll now: https://lnkd.in/gKFjZHSW
-
-
Watch Ravi Theja Desetty implement our multi-step query engine using workflows! The multi-step query pattern breaks a complex question up into sequential sub-questions. This video covers: ➡️ The process of creating a workflow that includes query decomposition, stopping conditions, and response synthesis ➡️ Implementation details such as generating step queries, and updating reasoning based on intermediate responses ➡️ How to use OpenAI's API, index data, and set up the necessary components for the multi-step query engine Check out the video here: https://lnkd.in/gbptsUbP
-