LlamaIndex

Our friends at Auth0 by Okta are launching a collection of secure ways to build AI applications! Check out their full-stack, open-source demo app: http://demo.auth0.ai/ The code is here: https://lnkd.in/g8M3px7k And you can learn more about Auth0's AI plans at their site: https://www.auth0.ai/

Enhance your AI applications with MongoDB's new hybrid search support for LlamaIndex! 🚀 Vector search and traditional keyword search have different strengths and weaknesses, but you can combine them into a single hybrid approach that gets you the best of both, blended together, now in MongoDB! Check out the full blog post announcing support here: https://lnkd.in/gu9Yn4zk

Build multi-tenant RAG applications easily with LlamaIndex and Nile! 🚀 Multi-tenancy -- the ability to index data from hundreds or thousands of users without leaking it between them -- is a very common question we get from users. Nile have built a full-stack demo application called TaskGenius that uses AI to estimate the complexity of your to-do list items, and shows off how you can handle multiple users with totally separate document databases and embeddings. Learn how to: ➡️ Isolate documents and embeddings for each tenant ➡️ Scale efficiently with virtual tenant databases ➡️ Implement multi-tenant RAG with just a few lines of code Check out the blog post: https://lnkd.in/gJdFgztb And the full-stack TaskGenius demo here: https://lnkd.in/g9yGdPts

This weekend, I enjoyed the opportunity to play with LlamaIndex Workflows at the LlamaIndex Ragathon thanks to Mark Evans, AI Makerspace and 500 Global. Toolhouse and Apify provided easy, out-of-the-box connectors for the function calling of websites in our project to retrieve data. With such quick, easy and reliable setup, I got to step away from web-browsing automation to explore using LLM's for other tasks such as categorization, recommendation and reasoning. My takeaway working with LlamaIndex Workflows is that it is brilliant to have a toolset to orchestrate function-calling and set up agentic architecture as event-driven systems. It was extremely easy to comprehend and fast to implement a LlamaIndex Workflow, which is exactly the point of setting up an agentic, multi-LLM-step system - for prototyping purposes. What this meant for me was that setting up an app that involved a recommendation system was able to be done in a matter of hours, as opposed to the complexity of traditional ML model tooling. It was so easy to set up, my teammate Tanmesh Mishra and I each enjoyed our Saturdays and actually started working around 8pm Saturday night until the 3pm Sunday deadline, and we were still able to submit a working MVP with extra time to prepare slides. I thought that having Event Classes to define what each step would do through its naming convention, and then a Workflow Class to orchestrate all the Event Classes as steps made the entire project extremely minimalistic. Then, making use of Python's type hinting system as a pattern to define how one event would be mapped to another made code extremely organized. Most of all, the ability of keeping the abstractions within a single file, with such clear structure allowed LLM code generation to be extremely successful. As with all agent use-cases, having many LLM calls, especially if they are well-defined with examples and templated output makes agentic use-cases costly in money and time. After having done this project, I would agree with the consensus of keeping the number of function-calling steps as minimal as possible when making multiple LLM requests, or at least having Human in the Loop intervention serving as checkpoints every few steps. As more function-calls involving separate LLM requests stacks up, it makes debugging extremely time-consuming. Here are all the steps in our workflow: 1. Tweet Extractor 2. Tweet Analyzer 3. Interest Mapper 4. Gift Idea Generator 5. Mediation 6. Gift Debater 7. Gift Reasoner 8. Amazon Keyword Generator 9. Amazon Product Link Generator The above takes about 5 - 20 minutes to run start to finish, depending on the number of item categories and items chosen to debate over. Here was the initial submission of GiftGenie: https://lnkd.in/ghBZW2zB Here is a second demo made after adding additional agent logic, Pro and Con agent dialogue over more gift choices, and a progress bar: https://lnkd.in/gS_6n72A Github Repo: https://lnkd.in/gCNPHCKk

We're delighted to be partnering with Reskilll and Meta for the AI Hackathon October 19th-20th in Bengaluru -- catch our own Ravi Theja Desetty who will be mentoring participants! Learn more: https://lnkd.in/dJE_RnTs

Tomorrow! Catch Laurie Voss talking about how to use LlamaIndex with Elastic.

🎉🎉🎉 WINNERS Right Here! A huge congrats to 1st place, Timeline of You, 2nd place, Closing.wtf, 3rd place, OilyRags. See their projects here: https://lnkd.in/g_EA8yW9 LlamaIndex VESSL AI Pinecone AI Makerspace 500 Global #ragathon #rag #agenticrag #genai #arize #box #sap #togotherai Toolhouse

Build a multimodal RAG system using Microsoft Azure AI Search, Azure OpenAI, and Arize AI Phoenix with LlamaIndex! This step-by-step guide walks you through contextual retrieval, a technique to improve the accuracy of retrieval by adding global context to each retrieved chunk, benchmarking it against basic retrieval. And don't miss the section on how to use LlamaParse to handle PowerPoint documents! Check out the full tutorial here: https://lnkd.in/gpjMQb_A

Mistral has released some impressive new edge-class models and we have day 0 support as usual! Just run: pip install llama-index-llms-mistralai

As impressed as I was by the projects that were submitted, it was the people that impressed me the most at the LlamaIndex #Agentic RAG-a-thon with Pinecone and VESSL AI event I attended at 500 Global in Palo Alto this past weekend. I wanted to share my gratitude and a few reflections about the weekend. Thank you to all the sponsors first and foremost. Without your participation, these types of events just wouldn’t be possible. To the AI Makerspace team, you truly made putting on this event look easy, even when things weren’t. Thanks to you Mark for the invite! To the leaders of these companies, especially Laurie at LlamaIndex and Daniele at Toolhouse who I had the pleasure of meeting at a previous hackathon, I want to thank you 🙏 for spending so much 1 on 1 time with myself and others making new releases, real-time product bug fixes, and suggesting workarounds so that projects could move forward. Chris Alexiuk at AI Makerspace, dude you f’n rock. Your workshop on Friday was solid 👊 and without your direction and help many projects, including my own would not have been submitted. Thank you! Super proud of the team I joined 🙌. Our project OpsRocket won 🏆 the award offered by Arize AI for best use of #Phoenix which was used for observability of our agent workflow. Our project didn’t go as expected on Saturday due to some glitches in the matrix as is often the case, but we got it done. I can’t say enough good things about these guys and I was truly humbled to sit beside you Alton Alexander, Brian Reardon, David Zhou and Patrick OBrien. Even under pressure these guys were cool as a cucumber. I learned a lot from each one of you. I hedged on Sunday and decided at the last minute to submit a solo project I had mostly completed on Friday, after asking my OpsRocket team if they would mind. Literally, 1 second before the deadline I pressed the submit button on the entry form. I didn’t think my solo pitch went well. I didn’t even get all the way through it. Somehow my project made it through finals. I have to thank David and Patrick from the OpsRocket team for helping me refine my pitch and tease out pertinent value points. They didn’t have to help me, but despite OpsRocket not making it to finals, they eagerly jumped right in. This is the type of character these guys have. I really appreciate it! I was truly shocked my AI Mechanic Assistant Catalog project won 🥉Third Place out of 40+ other projects by 500+ bleeding-edge AI developers from around the world at a hackathon in the heart of Silicon Valley. I am sharing to encourage folks who may not be super technical but have an idea… start attending these events. See if your idea has legs and build a team! Build. Ship. Share. Shout out to all the sponsors. Thanks!! LlamaIndex, Pinecone, VESSL AI, #SFTechWeek, Arize AI, SAP, Box, Together AI, Toolhouse, AI Makerspace, Mistral AI, #SouthBayGenerativeAI, OpenAI Thank you Christine at 500 Global for letting us use your lovely space!