Vectara

🚀 Milestone Reached: 2 Million Downloads!🚀 We are thrilled to announce that our Hughes Hallucination Detection Model (HHEM) has officially reached 2 million cumulative downloads on Hugging Face! What an exciting journey it's been—HHEM launched just last November, and only three weeks ago, we celebrated 1 million downloads. Now, with our downloads doubling, we couldn’t be more grateful to the incredible community of researchers, developers, and AI experts supporting this work. This recent acceleration is a very clear indication that the RAG AI Assistant market is maturing and moving into more production mission-critical use cases where the accuracy of the results is paramount. A massive thank you to all who are using HHEM to bring more factual consistency to AI Assistants and Agents. Here’s to even more innovation and growth ahead! Want to learn more about HHEM’s journey and how we’re continuing the fight against LLM hallucinations? Check out our latest blog post for all the details: https://bit.ly/4h1f8sy 📖 #GenAI #NLP #HallucinationDetection #MachineLearning #RAGaaS

💡 Why Building a RAG Pipeline Isn’t as Simple as It Seems 💡 Building a #RAG (Retrieval-Augmented Generation) pipeline is more challenging than it looks. From handling complex data ingestion to ensuring low-latency, high-quality retrieval—building a scalable, secure pipeline requires deep expertise. In our latest blog, Vectara's Nikhil Bysani and Ofer Mendelevitch explore the difficulties of creating a RAG pipeline yourself and why RAG-as-a-service might be the smarter choice. 🔍 Discover: 🔷 Common challenges in RAG pipeline development 🔷Why smaller models like Vectara’s Mockingbird are game-changers 🔷How Vectara simplifies the process with an end-to-end platform Check it out today! 👉 https://bit.ly/3NxQwu6 #RAG #LLM #GenAI #AIforEnterprise

Portfolio company Vectara's Hughes Hallucination Detection Model (HHEM) has reached 2 million downloads on Hugging Face! As the #1 hallucination detection model, Vectara remains committed to reducing hallucinations through detection and innovative correction techniques. Learn more below!

🚨 Upcoming Webinar with Intel Corporation! 🚨 Tackling Hallucinations at Scale in the Enterprise 📅 October 30, 2024 | 11:00 AM PT Join Ofer Mendelevitch, Head of Developer Relations, as he dives into one of the biggest challenges in AI: LLM hallucinations. In collaboration with Intel, this webinar explores proven methods to detect and eliminate hallucinations at scale, particularly in enterprise settings. Topics include: 🔹 Why LLMs hallucinate and how to mitigate them 🔹 Vectara’s RAG as-a-service and the Hughes Hallucination Evaluation Model 🔹 Learn how Vectara Mockingbird enhances RAG-specific output generation 🚀 Don’t miss out—register today: https://intel.ly/407VlSw

🚀 Calling all AI Developers in NYC! We're bringing RAG on the Road to your city on November 12, 2024 at Alumni Ventures. Learn from the best as the Vectara ML team dives deep into Retrieval-Augmented Generation (#RAG) patterns that can transform your AI implementations. Sign up for FREE here: https://bit.ly/3TXqdkG Seats are limited—grab yours today! 📈

Want to build smarter AI assistants? 🤖 John Gilhuly and Ofer Mendelevitch (Vectara) will be giving an in-depth workshop this Thursday on building AI assistants using Agentic RAG. Here's what you'll learn... ✅ How to create dynamic AI systems that adapt retrieval strategies in real-time. ✅ Hands-on experience with Vectara-agentic, a powerful Python library for AI assistant development. ✅ Integrating Arize Phoenix for monitoring and evaluating RAG-based agents (for reliability and transparency) Join us here: https://lnkd.in/gmhrUXfm

During my last 9 years at Cloudera, and in the data industry, I have learnt so much about the challenges our customers had along their Data journey. The impact of certain business painpoints as well as the criticality of certain Business processes and use cases convinced me that Vectara is definitely a solution to some of the biggest challenges executives in the enterprises have but also a great solution to innovate and be ahead of the new Gen Ai wave: As an advisor of Vectara, I have faced lots of questions and sometimes have seen lots of confusion about what vectara really is ! And no „gen ai“ isn‘t too early neither a trend, it’s just happening and at pace ! Boards need to embrace it and understand why and how they will be able to trust and secure the outcomes and results of their solution, because it‘s possible ! So here is an clear elevator pitch about what Vectara is and does : ————————————————————————————- Vectara developed an integrated AI Assistant/Agent platform which focuses on enterprise readiness for mission-critical applications, especially when it comes to: Accuracy (eliminating “Hallucinations”), Security (access control, prompt injection attacks, SOC2/HIPAA compliance), and Explainability of results/actions (for compliance and troubleshooting of bad results). More technically, under the hood Vectara provides an end-to-end Retrieval Augmented Generation (RAG for short) platform which combines multi-lingual hybrid (semantic+lexical) information retrieval with AI-generated responses/actions while giving enterprise developers the optionality to optimize its behavior vs messing around with its guts (analogous to giving a database a hint to change the join strategy versus changing the join algorithm directly). Enterprise customers and technology partners embed Vectara’s GenAI RAG platform in their own applications through easy plug-n-play API integrations vs re-inventing the wheel by building their own do-it-yourself solutions (which are hard to maintain overtime as the models underneath keep evolving rapidly). To top it off, Vectara has a strong focus on solution testability, scalability, reliability, availability, resilience to prompt attacks, copyright protection, and bias mitigation, ensuring that applications built on top of Vectara are trustworthy for mission-critical enterprise applications. You want to learn more ? Please ping me and let‘s have a discussion: we are looking for 10 additional pilotes on strategic projects. And here a quick link to Amr Awadallah recent pitch on stage !

🚀 Meet Jeff Chapman, Field CTO at Vectara, at AIAI Boston! 🚀 Vectara's very own, Jeff Chapman, will be speaking at AIAI Boston about a topic that’s critical to enterprise AI: tackling hallucinations in generative AI models. His talk, "Stop Enterprise Hallucinations: How RAG Can Be Your Best Defense," will explore the power of Retrieval-Augmented Generation (#RAG) in solving one of AI’s biggest challenges. Don't miss out on this insightful session! 🗓️ Date: October 17, 2024 📍 Location: Boston, MA 🔗 Register here: https://bit.ly/3YlP5oW AI Accelerator Institute Schedule time on Jeff's calendar today! https://bit.ly/402fJUZ #GenAI #RAGaaS #AIConference #AIforEnterprise

🎤 Today’s the day! Catch Ofer Mendelevitch at AIAI Boston 🎤 Ofer Mendelevitch, Head of Developer Relations at Vectara, will take the stage today to share groundbreaking insights into how #RAG (Retrieval-Augmented Generation) can be the key to stopping enterprise AI hallucinations. His passion for helping teams leverage the full potential of GenAI makes this a must-see session! Get ready for an engaging talk that tackles one of AI’s toughest problems. 🕑 Time to register: https://bit.ly/3YlP5oW Schedule time on Ofer's calendar today! https://bit.ly/4dXSW00 AI Accelerator Institute #GenAI #AIConference #StopHallucinations #AIforEnterprise

Looking to separate #GenerativeAI fact from fiction? The Generation AI podcast delivers just that with unfiltered insights from those at the forefront of AI innovation. Tune in as Vectara’s Ofer Mendelevitch and Sean Anderson go deep with leaders pioneering the next wave of AI. Available on Spotify 👇