Top all-time · #7277
Vectara
Company blog · vectara.com/blogaidata
Vectara is the company blog at vectara.com, writing about ai and data. Since 2022, 11 different Hacker News readers have linked it 35 times, most often “Show HN: Boomerang, a new embedding model for RAG and semantic search”. No feed was found, so read it on the site itself.
Too few sampled comments (6) to say how often HN recommends it.?
Why HN links it
Linked mainly in company-related comments: product and hiring pitches for its RAG platform, plus posts on hallucination detection, small fine-tuned models and a comparison with Pinecone.
Summarised by Claude from a sample of 6 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Vectara turns complex, multimodal data into actionable intelligence that drives better business outcomes. Vectara is an enterprise agent platform that powers intelligent, managed AI agents used by global companies in multiple industries.
Most-linked posts?
- Show HN: Boomerang, a new embedding model for RAG and semantic search3 people · 3 mentions · first linked 2023-09-26
- Detecting Hallucinations in Large Language Models3 people · 3 mentions · first linked 2023-11-06
- You don't need a vector database. You need a GenAI Platform2 people · 2 mentions · first linked 2023-08-08
What Hacker News says?
Vectara ( https://vectara.com ) | Field Engineer, Front-end Engineer, Platform (back-end) Engineer, and Product Managers | Full-time | Egypt, Pakistan, and/or Remote (depends on position) Vectara is a retrieval augmented generation (RAG) as a service platform. We have a ton of IP already: an embedding model that outperforms Cohere and OpenAI, a reranking model that does similarly, a generative model that outperforms…
Comment linking /careers/
on “Ask HN: Who is hiring? (August 2024)”Submitted Show HN: Sankofa – Browser extension to semantically search your history as a story · 19 points
HN discussionThat's correct. We've got a blog that talks a bit about it: https://vectara.com/blog/do-smaller-models-hallucinate-more/ Some people are surprised by smaller models having the ability to outperform bigger models, but it's something we've been able to exploit: if you fine tune a small model for a specific task (e.g. reduced hallucinations on a summarization task) as Intel has done, you can achieve great performance e…
Comment linking /blog/do-smaller-models-hallucinate-more/
on “CriticGPT: Finding GPT-4's mistakes with GPT-4”Submitted Mockingbird: A RAG-Focused LLM as a story · 18 points
HN discussionNice to see yet another open source approach to LLM/RAG. For those who do not want to meddle with the complexity of do-it-youself, Vectara ( https://vectara.com ) provides a RAG-as-a-service approach - pretty helpful if you want to stay away from having to worry about all the details, scalability, security, etc - and just focus on building your RAG application.
Comment linking /
on “Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data”Submitted Show HN: Open-source model and scorecard for measuring hallucinations in LLMs as a story · 13 points
HN discussionSomewhat related: I actually think vector databases are not as important as people are led to believe. Read more here: https://vectara.com/blog/vector-database-do-you-really-need-...
Comment linking /blog/vector-database-do-you-really-need-one/
on “Show HN: I built a vector database API on Cloudflare”Submitted Show HN: Boomerang, a new embedding model for RAG and semantic search as a story · 12 points
HN discussionIt's important to note that this fine-tuning is what is known as "supervised fine-tuning" where you give the LLM a set of question/answer pairs and it tunes to those (see https://huyenchip.com/2023/05/02/rlhf.html ). This is quite different then fine-tuning the base model or doing RLHF (reinforcement learning from human feedback). My guess is that it could work well to adjust the goal of the LLM, i.e. tell it to beh…
Comment linking /fine-tuning-vs-grounded-generation/
on “GPT-3.5 Turbo fine-tuning and API updates”Submitted Correcting Hallucinations in Large Language Models as a story · 11 points
HN discussionhttps://vectara.com/compare-pinecone-io-vs-vectara/
Comment linking /compare-pinecone-io-vs-vectara/
on “Pinecone raises $100M Series B”Submitted Show HN: Mockingbird is an LLM that outperforms GPT4 on RAG as a story · 9 points
HN discussionThere are so many options for vector databases that it's so confusing. But those are just a piece of the puzzle when you create applications using large language models. As mentioned in the comments, you have to choose an embeddings model, the LLM, and manage all the interaction in between. With Vectara (full disclosure: I work there; https://vectara.com ) we provide a simple API to implement applications with Groun…
Comment linking /
on “Comparison of Vector Databases”Submitted LLM Hallucinations: why they occur and how to avoid them as a story · 5 points
HN discussionYes agree there, and that was my question too: more focused on how design might change due AI and ChatGPT coming in. My colleague Deryk wrote a nice article about it too: https://vectara.com/blog/user-interfaces-for-ai-applications...
Comment linking /blog/user-interfaces-for-ai-applications/
on “Ask HN: How does AI transform UI design?”Submitted You don't need a vector database. You need a GenAI Platform as a story · 4 points
HN discussionWe may write a research paper at some point. For now, see here: https://vectara.com/cut-the-bull-detecting-hallucinations-in... Given the number of models involved, we have over 9k rows currently. Judging for this task is quite time consuming as you need to read a whole document and check it against a several sentence summary and some of the docs are a 1-3 min read. We wanted to automate this process and also make i…
Comment linking /cut-the-bull-detecting-hallucinations-in-large-language-models/
on “Show HN: Open-source model and scorecard for measuring hallucinations in LLMs”Submitted The Great Search Disruption as a story · 3 points
HN discussionThis link gives a lot more context for the less informed: https://vectara.com/cut-the-bull-detecting-hallucinations-in... I really want to know more about the hallucinations produced! Were some sources more likely to produce errors! I would be curious if other document sets were explored for use with this test and if different source material would change the results in a meaningful way.
Comment linking /cut-the-bull-detecting-hallucinations-in-large-language-models/
on “Show HN: Open-source model and scorecard for measuring hallucinations in LLMs”Submitted Vectara Releases “Grounded Generation” as a story · 3 points
HN discussionTotally agree. retrieval augmented generation is still the preferred way to give the LLM more knowledge. Fine-tuning is mostly useful for adapting the base model for another task. I wrote about this in a recent blog post: https://vectara.com/fine-tuning-vs-grounded-generation/ . Anyone knows how this new capability works in terms of where the model inference be done? Would it still be at the OpenAI side or is this g…
Comment linking /fine-tuning-vs-grounded-generation/
on “Introducing ChatGPT Enterprise”Submitted Why does Deepseek-R1 hallucinate so much? as a story · 2 points
HN discussionHi HN! I lead product at Vectara. Yesterday, we launched Vectara Chat, which is a set of APIs to help organizations combine chatbots with RAG (Retrieval Augmented Generation). One of the most common things we've heard from the community of users trying to build chatbots is that they hallucinate (and hence the release of our hallucination evaluation model: https://huggingface.co/vectara/hallucination_evaluation_mode.…
Comment linking /blog/vectara-chat-revolutionizing-chat-development-for-the-modern-business/
on “Show HN: Chat-focused RAG with automated memory management”Submitted Show HN: New and more powerful OSS hallucination detection as a story · 2 points
HN discussionretrieval augmented generation (we call it "grounded generation" at Vectara) is a great way to build GenAI apps with your data. This blog post can be useful: https://vectara.com/a-reference-architecture-for-grounded-ge... . The long and short of it is: building RAG applications seems easy at the start but gets complicated as you go from toy application to scalable enterprise deployment.
Comment linking /a-reference-architecture-for-grounded-generation/
on “How do domain-specific chatbots work? A retrieval augmented generation overview”Submitted Reasons to Use Vectara with LangChain as a story · 2 points
HN discussionFirst time I ran into embeddings was with word2vec and could not resist showing that, similar to the "king - man + woman ~ queen", it also the case that "yoda - good + evil ~ vader". It's also cool that the semantic meaning is the same in vector space, regardless of the language. Embeddings are also super important in retrieval-augmented-generation (RAG), and getting the best "embeddings model" is important to achie…
Comment linking /introducing-boomerang-vectaras-new-and-improved-retrieval-model/
on “Embeddings: What they are and why they matter”Submitted Correcting LLM Hallucinations as a story · 1 points
HN discussionI agree. my experience is that hybrid search does provide better results in many cases, and is honestly not as easy to implement as may seem at first. In general, getting search right can be complicated today and the common thinking of "hey I'm going to put up a vector DB and use that" is simplistic. Disclaimer: I'm with Vectara ( https://vectara.com ), we provide an end-to-end platform for building GenAI products.
Comment linking /
on “Do we think about vector dbs wrong?”Submitted Detecting Hallucinations in Large Language Models as a story · 1 points
HN discussion