Why not just use pgvector for Postgres. It’s free and works great. You can even do cosine distance between embeddings.
A good sales team, tons of devs, and some custom integrations might answer this question in the future
Pinecone raises $100M Series B
61–70 of 100 posts
Re: Pinecone raises $100M Series B
#62Why not just use pgvector for Postgres. It’s free and works great. You can even do cosine distance between embeddings.
Same with opensearch and elasticsearch, both of which have added vector search as well (slight differences between their implementations). And since vector search is computationally expensive, there is a lot of value in narrowing down your result set with a regular query before calculating the best matches from the narrowed down result set.
From what I've seen, the big limitation currently is dimensionality. Most of the more advanced models have a high dimensionality and especially Elasticsearch and Lucene limit the dimensionality to 1024. E.g. several of the openai models have a much higher dimensionality. Opensearch works around this by supporting alternate implentations to lucene for vectors.
Of course it's a sane limitation from a cost and computation point of view, having these huge embeddings doesn't scale that well. But it does limit the quality of the results unless you can train your own models and tailor them to your use case.
If you are curious on how to use this stuff, I invested some time a few weeks ago getting my kt-search kotlin library to support this and wrote some documentation for this: https://jillesvangurp.github.io/kt-search/manual/KnnSearch.h.... The quality was underwhelming IMHO but that might be my complete lack of experience with this stuff.
I have no experience with pinecone and I'm sure it's great. But I do share the sentiment that they might not come out on top for this. There are too many players here and it's a fast moving field. OpenAI just majorly moved the whole field forward enormously in terms of what is possible and feasible.
Re: Pinecone raises $100M Series B
#63Plug: If you're ever looking for an open source alternative to Pinecone, we recently added vector search to Typesense: https://typesense.org/docs/0.24.1/api/vector-search.html
The key thing is that it's in-memory and allows you to combine attribute-based filtering, together with nearest-neighbor search.
We're also working on a way to automatically generate embeddings from within Typesense using any ML models of your choice.
So Algolia + Pinecone + Open Source + Self-Hostable with a cloud hosted option = Typesense
Re: Pinecone raises $100M Series B
#64there's at least $168m being poured into vector db's this year. recent vector database fundraises: - Chroma - $18M seed https://www.trychroma.com/blog/seed - Weaviate - $50m A https://www.theinformation.com/articles/index-ventures-leads... - Pinecone - $100M B
- Qdrant - $7.5m seed https://qdrant.tech/articles/seed-round/
i had a feeling i missed something.. thanks!
Re: Pinecone raises $100M Series B
#65Plug: If you're ever looking for an open source alternative to Pinecone, we recently added vector search to Typesense: https://typesense.org/docs/0.24.1/api/vector-search.html The key thing is that it's in-memory and allows you to combine attribute-based filtering, together with nearest-neighbor search. We're also working on a way to automatically generate embeddings from within Typesense using any ML models of your…
This is what we’re using. We already sync database content to a typesense DB for regular search so it wasn’t much more work to add in embeddings and now we can do semantic search.
Re: Pinecone raises $100M Series B
#66I was using pinecone before installing pgvector in Postgres. Pinecone works and all but having the vectors in Postgres resulted in an explosion of use for us. Full relational queries with where clauses and order by etc AND vector embeddings is wicked.
Do you know of anything similar available for SQL Server 2019?
Re: Pinecone raises $100M Series B
#67Plug: If you're ever looking for an open source alternative to Pinecone, we recently added vector search to Typesense: https://typesense.org/docs/0.24.1/api/vector-search.html The key thing is that it's in-memory and allows you to combine attribute-based filtering, together with nearest-neighbor search. We're also working on a way to automatically generate embeddings from within Typesense using any ML models of your…
Could you do boosting with Typesense, like favoring more recent results?
Re: Pinecone raises $100M Series B
#68> We raised $100 million in Series B funding, led by Andreessen Horowitz,
I closed the browser tab here. It's a usual techbro hustle, nothing to see here, move along. Hype, whatnot, couldn't care less. I am sure they will make money but it'll be detrimental to society. As always.
Re: Pinecone raises $100M Series B
#69Plug: If you're ever looking for an open source alternative to Pinecone, we recently added vector search to Typesense: https://typesense.org/docs/0.24.1/api/vector-search.html The key thing is that it's in-memory and allows you to combine attribute-based filtering, together with nearest-neighbor search. We're also working on a way to automatically generate embeddings from within Typesense using any ML models of your…
Could you do boosting with Typesense, like favoring more recent results?
Yup. If you store timestamps as Unix timestamps you can gave Typesense sort on text match score and the timestamp field: https://typesense.org/docs/guide/ranking-and-relevance.html#...
Re: Pinecone raises $100M Series B
#70Why not just use pgvector for Postgres. It’s free and works great. You can even do cosine distance between embeddings.
A good sales team, tons of devs, and some custom integrations might answer this question in the future
>A good sales team
It quite angers me that people (on HN) will consider the following to be benefits worth mentioning as pros to the consumer:
>Sleek/shiny finish
>Marketing/Branding
>Ability to Monetize
We arent shareholders, all 3 of these are bad for the customer.