LlamaIndex | LinkedIn (original) (raw)

Technology, Information and Internet

San Francisco, California 221,616 followers

The fastest way to build production-quality LLM agents over your data

Access all 40 employees

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

Industry

Technology, Information and Internet

Company size

2-10 employees

Headquarters

San Francisco, California

Type

Public Company

Locations

Employees at LlamaIndex

Updates

Multi-agent workflow to Generate a Structured Financial Report 📊 In our new video we show you how to generate simple analyses containing text and tables over a bank of 10K documents. First, we use LlamaCloud to advanced retrieval endpoints allowing you to fetch chunk and document-level context from complex financial reports consisting of text, tables, and sometimes images/diagrams. We then build an agentic workflow on top of LlamaCloud, using OpenAI GPT-4o, consisting of researcher and writer steps in order to generate the final response. Video: https://lnkd.in/gUqRYKbNSignup to LlamaCloud: https://lnkd.in/gi8dxGntFor enterprise usage, come talk to us: https://lnkd.in/g5648-ip
Generating a Multimedia Research Report with LLM Structured Outputs 🧱📑 In our brand-new video 💫, we show you how to build a simple report generator that can summarize insights from complex documents (e.g. a slide deck), and synthesize a report with interleaving text and images. Structured outputs is a key building block towards building agentic RAG / report generation workflows, and this video is a great way to get started. Video: https://lnkd.in/gxMpZ9ckNotebook: https://lnkd.in/geP9f3YBSignup for LlamaCloud: https://lnkd.in/gi8dxGnt
Our Python documentation just got a huge boost thanks to RunLLM! Our new "Ask AI" widget in the bottom-right of every docs page launches a truly magically accurate agentic RAG system that writes accurate, up-to-date code in answer to your questions. Try it out today
Learn to build powerful GenAI apps with LlamaIndex and Memgraph in our upcoming Community Call! Join us to explore: ➡️ Creating knowledge graphs from unstructured data ➡️ Advanced retrieval methods for efficient information extraction ➡️ Transforming data into queryable knowledge graphs ➡️ Performing natural language queries with ease Register now: https://lnkd.in/gWjKfa5e
Automatically generate cloud configurations with RAGformation! 🏗️ Describe your use case in natural language, get a tailored cloud architecture 🖼️ Visualize your setup with dynamically generated flow diagrams 💰 Receive pricing estimates for the generated architecture 🔄 Refine recommendations based on your preferences and budget RAGformation simplifies cloud complexity, accelerates deployment, and optimizes ROI. Built with LlamaIndex Workflows, Box, and Pinecone, it's open-source and won the Box Award at our recent RAG-a-thon! Learn more about RAGformation in their guest post on our blog:https://lnkd.in/djY_kymn
We’re excited to feature a new RAG technique - dynamic section retrieval 💫 - which ensures that you can retrieve entire contiguous sections instead of naive fragmented chunks from a document. This is a top pain point we’ve heard from our community on multi-document RAG challenges - naive RAG returns fragmented context without awareness of the surrounding document. Our approach allows you to start off with a “simple” chunking technique (e.g. per page), but do a post-processing workflow to attach section/sub-section metadata. You can then do GraphRAG-like retrieval (two-pass retrieval): retrieve chunks, look up the attached section metadata, and then do a second call to return all chunks that match the section ID. https://lnkd.in/gEReAKtT
Build robust GenAI pipelines with LlamaIndex, Qdrant, and MLflow for advanced RAG! Learn how to: 🔍 Streamline RAG workflows for better scalability 📊 Ensure performance consistency across model versions 🚀 Optimize indexing systems for efficiency This step-by-step guide covers: • Setting up MLflow for experiment tracking • Configuring Qdrant for vector storage • Integrating Ollama for LLM and embedding models • Creating a playground app to test the full pipeline Check out the full post here:https://lnkd.in/gCnm9JgE
Learn how to use ColPali as a re-ranker for highly relevant results using a multimodal index walks you through the technique: 💡 Cohere's multimodal embeddings for initial retrieval of both text and images 💡 We fetch the top 10 most relevant from both the text and image modalities 💡ColPali generates multi-vector representations for both text and images in the same embedding space 💡 We re-rank to the top 5 for each modality before sending to the LLM Check out the full video here:https://lnkd.in/gZWU3tmK
Case Study: Learn how Pursuit transformed their B2G offerings using LlamaParse: ➡️ Parsed 4 million pages in a single weekend ➡️ Increased accuracy by 25-30% for complex document formats ➡️ Enabled clients to uncover hidden opportunities in public sector data See how LlamaParse helped Pursuit create a searchable database of public sector documents, empowering B2G sellers to identify new initiatives and funding streams:https://lnkd.in/gfCxfm4A
PureML uses LLMs to automatically clean up and refactor ML datasets 🧼🤖 🕳️ Context-aware null handling 🔍 Intelligent feature creation from existing data 🔄 Data consolidation for consistency PureML leverages LlamaIndex, OpenAI's GPT-4, and Reflex to create an efficient, scalable solution for ML engineers. Read the full story and see how it works: https://lnkd.in/gnQ45uF8