Typesense Reviews

Vectara Neural Search Reviews

Typesense mentions (58)

• Meilisearch – search engine API bringing AI-powered hybrid search

  You might want to look at https://typesense.org/ for that. - Source: Hacker News / about 2 months ago

• Understanding the BM25 full text search algorithm

  We use https://typesense.org/ for regular search, but it now has support for doing hybrid search, curious if anyone has tried it yet? - Source: Hacker News / 7 months ago

• Show HN: Self-Hostable Algolia DocSearch Replacement

  Took me a little poking around to figure out what the underlying search engine was: it's https://typesense.org/ hosted in a Docker container. - Source: Hacker News / 8 months ago

• Release Radar · August 2024: Major updates from the open source community

  We all make mistakes at times, and we've all made a typo here and there at some point in our lives. Typesense is here to change all that, with a typo-tolerant, in-memory, fuzzy search engine. The latest release has a new mode, better typo tolerance, support for new references and synonyms, new search parameters, and AI search improvements. Check out all the breaking changes and major updates in the Typesense... - Source: dev.to / 9 months ago

• What Postgres Full Text Search Is Missing

  Alternatives to both are https://www.meilisearch.com/ https://typesense.org/ and maybe https://github.com/Sygil-Dev/whoosh-reloaded. - Source: Hacker News / 10 months ago

Vectara Neural Search mentions (16)

• Show HN: Create RAG-powered pages to get answers from your docs– without coding

  Hey folks! I wanted to share one of the latest projects I worked on, called Vectara Portal. It's an application that allows users of our platform (https://vectara.com/) to create shareable pages that let you and other users (privately, if you wish) chat with, search through, or get answers from your documents. This began as a side project resulting from a question over lunch: "How do we put the power of our... - Source: Hacker News / 10 months ago

• Show HN: New and more powerful OSS hallucination detection

  Hi HN! At Vectara (https://vectara.com) were hyper focused on providing best in class retrieval-augmented-generation. We've just released a new open source hallucination detection model (available on HuggingFace and Kaggle) and associated leaderboard to show which LLMs are best at producing accurate summaries. It's far more accurate than our previous model, which has been referenced by a number of HN users here... - Source: Hacker News / 10 months ago

• Ask HN: Who is hiring? (August 2024)

  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... - Source: Hacker News / 10 months ago

• Launch HN: Danswer (YC W24) – Open-source AI search and chat over private data

  Nice 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. - Source: Hacker News / over 1 year ago

• Which LLM framework(s) do you use in production and why?

  You should also check us out (https://vectara.com) - we provide RAG as a service so you don't have to do all the heavy lifting and putting together the pieces yourself. Source: over 1 year ago