LlamaIndex

Multi-agent system for RFP Response Generation 🔥✍️ We’re excited to release a brand-new guide showing you how to build an agentic workflow that can take in an input RFP template and generate a full response to the RFP, grounded in your knowledge base and adhering to the relevant guidelines. This is much more than a standard RAG or ReAct agent architecture, and requires the careful orchestration of a set of steps + components. 1. Parse the input RFP template using LlamaParse, extract out a set of questions that you would need answered. 2. For each question, use a Research agent (ReAct loop) with access to a set of tools in the knowledge base to retrieve relevant information and generate an answer 3. Aggregate question/answer pairs into a single file 4. Generate the final report with the RFP template and QA pairs as input. Bonuses 💫: it’s fully async, and you get back event and final response streaming! Notebook: https://lnkd.in/g_RgrYme LlamaParse signup: https://lnkd.in/gi8dxGnt

Multi-agent workflow for multi-strategy business analysis 📊📑 This is a neat tutorial of a workflow by Lakshmi narayana U showing you how to build a multi-strategy business analysis workflow - consisting of company history analysis, market analysis, and then joint strategy canvas + Four Actions generation to produce the final strategic recommendations. It’s a nice example of a workflow that has multiple branches and merges, and you’re able to trust that it runs fully async to optimize LLM calls. https://lnkd.in/gPJSGFd5

🚀 Big news! 🚀 VESSL AI and LlamaIndex have teamed up 🤝 Exciting projects coming soon. We can't wait to share more - stay connected! #AI #MLOps #LLMOps #LLM #Llamaindex #VESSLAI #Partnership

Deploying advanced RAG is challenging. We make it a simple 3-step process: 1. Write your advanced RAG workflow in Python 2. Deploy it as API services with persistence and message queues through llama_deploy 3. Run it! Kameshwara Pavan Kumar Mantha has an excellent tutorial showing you how to build a RAG pipeline with in-built reflection/filtering/retries, and then deploy them as services through llama_deploy. It’s great weekend reading if you’re looking to not only code a workflow in a notebook, but put it behind an API server https://lnkd.in/gz8-Xd8u

Check out this video from Amazon Web Services (AWS) Developers on how to build a RAG pipeline with LlamaIndex! This quickly covers ➡️ Basic RAG workflow and components ➡️ Simple RAG implementation with LlamaIndex ➡️ Router query technique for advanced RAG ➡️ Improved accuracy through targeted indexing ➡️ Enhanced efficiency with specialized indexes https://lnkd.in/gtpfw5-B

Getting ready for the #RAGathon by AI Makerspace, LlamaIndex, VESSL AI hosted by Futureproof!

South bay folks! Our own Biswaroop Palit will be speaking at AI Builders Night at Zoom HQ in San Jose on Monday! Hear about multi-agent system in production and more from Zoom and Qdrant! https://lu.ma/0ho01c5x

Data quality is essential for a high-performance gen AI application. Argilla is a tool that lets you generate and annotate datasets for fine-tuning, RLHF, and evaluation, and it's got a first-class LlamaIndex integration! Check out their demo notebook walking you through the full steps of using the integration: https://lnkd.in/d9yYKBpq

Want to use OpenAI's Realtime API but you're a Python developer? We're excited to introduce a Python client for the OpenAI Realtime API, powered by LlamaIndex. 🔥 It supports both turn-based and streaming modes, allowing you to interrupt the chatbot in realtime. 🔥 It also lets you plug in arbitrary Python functions as tools, courtesy of LlamaIndex tool abstractions. Check it out. Huge props to Logan Markewich for building this. https://lnkd.in/geAixMsR

Watch Logan Markewich chat with an AI agent using his voice and LlamaIndex! This demo app shows how to use the OpenAI realtime API client to chat interactively, including using tools to answer. It's open source, so you can build your own voice agents! https://lnkd.in/gASAFZ7S