Vectara Neural Search VS Annoy

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 / 3 months ago

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: 5 months ago

Hi HN! I lead product for Vectara (https://vectara.com) and we recently worked with OpenSource connections to both evaluate our new home-grown embedding model (Boomerang) as well as to help users start more quantitatively evaluating these systems on their own data/with their own queries. OSC maintains a fantastic open source tool, Quepid, and we worked with them to integrate Vectara (and to use it to... - Source: Hacker News / 7 months ago

RAG is a very useful flow but I agree the complexity is often overwhelming, esp as you move from a toy example to a real production deployment. It's not just choosing a vector DB (last time I checked there were about 50), managing it, deciding on how to chunk data, etc. You also need to ensure your retrieval pipeline is accurate and fast, ensuring data is secure and private, and manage the whole thing as it... - Source: Hacker News / 8 months ago

I 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. - Source: Hacker News / 8 months ago

The focus on the top 10 in vector search is a product of wanting to prove value over keyword search. Keyword search is going to miss some conceptual matches. You can try to work around that with tokenization and complex queries with all variations but it's not easy. Vector search isn't all that new a concept. For example, the annoy library (https://github.com/spotify/annoy), an open source embeddings database. - Source: Hacker News / 8 months ago

If you want to go larger you could still use some simple setup in conjunction with faiss, annoy or hnsw. Source: 11 months ago

I then use annoy to compare them. Annoy can use different measures for distance, like cosine, euclidean and more. Source: 12 months ago

Yes you can do this for equality predicates if your row groups are sorted . This blog post (that I didn't write) might add more color. You can't do this for any kind of text searching. If you need to do this with file based storage I'd recommend using a vector based text search and utilize a ANN index library like Annoy. Source: 12 months ago

If you need large scale (1000+ dimension, millions+ source points, >1000 queries per second) and accept imperfect results / approximate nearest neighbors, then other people have already mentioned some of the best libraries (FAISS, Annoy). Source: 12 months ago