DataStax is introducing significant updates to its AI platform, focusing on Retrieval Augmented Generation (RAG) technology. These updates include LongRAG, a new approach combining long-context LLMs with RAG, enabling larger retriever units up to 4K-tokens. The RAG++ event featured presentations, live demos, and hands-on hacking sessions, with collaborations from various partners like LangChainAI and NVIDIA. DataStax aims to simplify backend processes for developers, emphasizing the new visual framework for RAG applications, Langflow AI 1.0. The company also hosted the RAG++ AI Hack Night, showcasing tools like DataStax Langflow, RAGStack 1.0, Vectorize, and Unstructured to accelerate GenAI and RAG apps to production.
Elastic has just released a new tool called Playground that will enable users to experiment with retrieval-augmented generation (RAG) more easily. @elastic https://t.co/pu2nj0r0aR
Get the highlights from our RAG++ Hack Night in this @TechCrunch article! From a panel session with DataStax Chairman and CEO @ChetKapoor, LangChain CEO @hwchase17 and Unstructured CEO @_Brian_Raymond, through to customers @priceline and @Supplant_me sharing their GenAI…
🔓Unlock the power of visuals in AI! → https://t.co/l3kSmn5sLx In this technical session, we review Retrieval-Augmented Generation (RAG) for multimodal applications. Learn how we leverage embeddings and question answering to retrieve data, with live demos and practical… https://t.co/hA55jggBhY
We’re excited to introduce Playground, a low-code interface that enables developers to build RAG applications using Elasticsearch in minutes. Find out how this intuitive interface allows for more flexibility & simplicity when building #GAI experiences: https://t.co/8SSayGUOLK
Missed our RAG++ AI Hack Night? No problem! Developers and AI enthusiasts got the scoop on the latest tools like DataStax Langflow, RAGStack 1.0, Vectorize, and Unstructured—all designed to fast-track your GenAI and RAG apps to production. With @LangChainAI @Microsoft @nvidia… https://t.co/qk1byFgwUu
Missed ourRAG++ AI Hack Night? No problem! Developers and AI enthusiasts got the scoop on the latest tools like DataStax Langflow, RAGStack 1.0, Vectorize, and Unstructured—all designed to fast-track your GenAI and RAG apps to production. With @LangChainAI @Microsoft @nvidia… https://t.co/uso5vbpvdl
Learn how DataStax simplifies backend processes so developers can focus on building apps, not infrastructure management, with @langflow_ai 1.0, our new visual framework for RAG apps, and our @UnstructuredIO partnership. 🚀 @Forbes @ABridgwater https://t.co/oTtulPG1Il
Learn how DataStax simplifies backend processes so developers can focus on building amazing apps, not infrastructure management, with @langflow_ai 1.0, our new visual framework for RAG apps, and our @UnstructuredIO partnership. Full article in @Forbes by @ABridgwater:…
DataStax is transforming the AI application lifecycle. 🚀 Learn how we're making backend processes easier so developers can focus on building amazing applications, not infrastructure management. 🔧 @langflow_ai 1.0 Launch: Our new visual framework for RAG applications, now…
Retrieval augmented generation (RAG) is one of the best ways to tailor an LLM using your own data, especially for production or industry use cases. What does a RAG workflow look like? 1) Query Process: A user asks a question, which is sent to a vector database like @weaviate_io… https://t.co/kqt373TNXv
Retrieval augmented generation (RAG) is one of the best ways to tailor an LLM using your own data, especially for production or industry use cases. What does a RAG workflow look like? 1) Query Process: A user asks a question, which is sent to a vector database like Weaviate to… https://t.co/bN3uLh6rQj
RAG is an incredibly useful mechanism to introduce contextually aware interactions for your users in your applications. RAG = Retrieval Augmented Generation When people think RAG, they commonly think Vector Database, like @weaviate_io, but turns out RAG has no mention of… https://t.co/2vI5ZcO0h8
DataStax updates tools for building gen AI applications https://t.co/9LDjYkwcga
Had a great time at #RAG++! It was insightful connecting with RAG professionals, exploring live AI demos, and participating in hands-on hacking sessions. #rag++ #datastax #langflow #genai https://t.co/YMamq6pVTQ
Introducing DataStax Langflow: Design and Test GenAI Apps with Ease https://t.co/nrx16iSRN8 from @DataStax
🚀@MyScaleDB and @LangChainAI are transforming data retrieval with advanced SQL vector queries, delivering unprecedented accuracy and efficiency to elevate your #RAG application. How? 🔍Let's explore this powerful combination by creating a Hacker News #AIassistant.…
Such an AWESOME RAG++ event yesterday! ✨ 🙌🏼 We were joined by superstar partners @LangChainAI, @NVIDIA, @unstructuredio — and many more! Thanks so much to everyone who made it — hope you enjoyed it as much as we did. 🫶🏼 #DataStax #GenAI #Langflow https://t.co/5n2Dz568Y7
For the first time ever, the @DataStaxDevs DevRel team got to serve developers at the RAG++ AI Hack Night with each other in person! It's such a privilege to work with @TejasKumar_ @philnash @SonicDMG & @sribala_ and felt great to finally meet up IRL 💜 https://t.co/c4Z6Tu95m8
Wrapping up an incredible RAG++ Event! 🎉 Presented by @DataStax in partnership with @TechCrunch, @LangChainAI, @nvidia, @UnstructuredIO, and more. Until next time, keep building! 🚀 #DataStax #GenAI #RAGApplications #VectorDB https://t.co/OitcLa47rK
“Build, fuel, and serve AI apps with RAG!” RAG++ is live with a packed venue for with a keynote from DataStax Chairman & CEO @ChetKapoor and CPO @edanuff 🚀 #RAGApplications #GenAI #VectorDB https://t.co/VmnobQY4A4
We're live at the @DataStax RAG++ AI Hack Night! This venue is PACKED 🔥 https://t.co/WnVSdsHUKI
Getting pumped for the @datastax RAG++: AI Hack Night, come see us at the @UnstructuredIO table. 👋 https://t.co/4qiyEVCIID
[CL] LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs Z Jiang, X Ma, W Chen [University of Waterloo] (2024) https://t.co/2bOyCsJqf7 - Traditional RAG framework operates on short retrieval units (100-word passages), which forces the retriever to search… https://t.co/RVcZJf1Q6s
DataStax Launches Major AI Platform Updates at RAG++ Event https://t.co/LIqeNBkMf3 @DataStax #datanami #TCIwire
BREAKING NEWS! DataStax to Launch New AI Platform Updates -- https://t.co/1ifI3c1PJT #AI #GenAI #RAG @DataStax
Retrieval Augmented Generation (RAG): A Comprehensive Visual Walkthrough 🧠📖🔗🤖 https://t.co/yrj3YhC9m3 #analytics #datascience, #artificialintelligence, #bigdata, #datascience, #datascience #ds, #machinelearning, inoreader
DataStax is making a number of improvements to its development platform that will allow developers to more easily implement retrieval augmented generation (RAG) in their generative AI applications. @DataStax https://t.co/xkXBN7wsms
How to combine Long-context LLM with RAG? We are happy to introduce LongRAG, a new approach to boost RAG with long-context LLMs. 1. Building larger retriever units to 4K-tokens, which is 30x longer than traditional RAG systems like DPR, RAG, FiD, Atlas, etc. 2. Retrieval… https://t.co/8AfuOFDxb1 https://t.co/kABkRljEoJ