Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Which vector database should I use? A comparison cheatsheet

navidre.medium.com

Post reply on HN
Print view View original

51–60 of 91 posts

Re: Which vector database should I use? A comparison cheatsheet

#51

Post by zach_miller »

shon wrote: post #36

* Shameless plug and a free ticket: Etienne Dilocker, The Co-founder/CTO of Weaviate and Ram Sriharsha, the VP of R&D at Pinecone are both presenting at The AI Conference. Lots of other smart people are presenting including Nazneen from Hugging Face, Harrison from Langchain, Jerry from Llamaindex, Ben the co-founder of Anthropic and many more. A hackathon is happening in the evening at the event as well. If you can't…

Thanks so much!! Really looking forward to the conference.

Re: Which vector database should I use? A comparison cheatsheet

#52

Post by kesor »

tanseydavid wrote: post #18

Has anyone attempted to utilize the vector storage capability in Redis? What was your experience with it?

I have used RedisSearch with chatgtp-retrieval-plugin and several megabytes of documents. It works well. And setting it up is just a single docker run command away ... so I don't see myself using anything else for local development. LangChain also has support for it.

Re: Which vector database should I use? A comparison cheatsheet

#53

Post by shon »

zach_miller wrote: post #51
shon wrote: post #36

* Shameless plug and a free ticket: Etienne Dilocker, The Co-founder/CTO of Weaviate and Ram Sriharsha, the VP of R&D at Pinecone are both presenting at The AI Conference. Lots of other smart people are presenting including Nazneen from Hugging Face, Harrison from Langchain, Jerry from Llamaindex, Ben the co-founder of Anthropic and many more. A hackathon is happening in the evening at the event as well. If you can't…

Thanks so much!! Really looking forward to the conference.

Awesome, glad you got one!

Re: Which vector database should I use? A comparison cheatsheet

#54

Post by kesor »

weird-eye-issue wrote: post #32
CodeCompost wrote: post #4

How do they compare to embeddings in OpenAI? (Sorry I'm new to all this.)

Where you gonna put that embedding?

You put the vector in a vector database that gives you the ability to search based on the vectors. So when you create a new vector based on some input (question/etc...) you can use the vector search to find semantically similar topics in your vector database.

Re: Which vector database should I use? A comparison cheatsheet

#55

Post by shon »

sankumsek wrote: post #48
shon wrote: post #36

* Shameless plug and a free ticket: Etienne Dilocker, The Co-founder/CTO of Weaviate and Ram Sriharsha, the VP of R&D at Pinecone are both presenting at The AI Conference. Lots of other smart people are presenting including Nazneen from Hugging Face, Harrison from Langchain, Jerry from Llamaindex, Ben the co-founder of Anthropic and many more. A hackathon is happening in the evening at the event as well. If you can't…

Looks like those tickets went fast. :) But looking forward to seeing those talks on YT.

They did go fast! I'll be giving away a few more on Twitter later this week

Re: Which vector database should I use? A comparison cheatsheet

#56

Post by shon »

Beefin wrote: post #47
shon wrote: post #36

* Shameless plug and a free ticket: Etienne Dilocker, The Co-founder/CTO of Weaviate and Ram Sriharsha, the VP of R&D at Pinecone are both presenting at The AI Conference. Lots of other smart people are presenting including Nazneen from Hugging Face, Harrison from Langchain, Jerry from Llamaindex, Ben the co-founder of Anthropic and many more. A hackathon is happening in the evening at the event as well. If you can't…

darn any chance you could send one to me? ethan at mixpeek dot com

Keep an eye on @shon twitter and @aiconference, I'm giving more away there this week. Always good to have more hackers in the room ;)

Re: Which vector database should I use? A comparison cheatsheet

#57

Post by neilsharma »

shon wrote: post #36

* Shameless plug and a free ticket: Etienne Dilocker, The Co-founder/CTO of Weaviate and Ram Sriharsha, the VP of R&D at Pinecone are both presenting at The AI Conference. Lots of other smart people are presenting including Nazneen from Hugging Face, Harrison from Langchain, Jerry from Llamaindex, Ben the co-founder of Anthropic and many more. A hackathon is happening in the evening at the event as well. If you can't…

Thanks Shon! Got one a bit earlier while they were still there -- really excited for this :)

Re: Which vector database should I use? A comparison cheatsheet

#58

Post by spullara »

Pure vector databases are a dead end. Almost every search engine (Vespa, Elastic, etc) and every database (Postgres, SQLite, Redis, etc) already has a solution for searching vectors in addition to everything else you need to query or search. If any of these vector databases become anything they will have to also implement either a full search engine or a full database.

Re: Which vector database should I use? A comparison cheatsheet

#59

Post by ofermend »

There 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 Grounded Generation (aka retrieval augmented generation). The embeddings model, the vector store, the retrieval engine and all the other functionality - implemented by the Vectara platform, so you don't have to choose which vector DB to use, which embeddings model to use, and so on. Makes life easy and simple, and you can focus on developing your application.

Re: Which vector database should I use? A comparison cheatsheet

#60

Post by yujian »

Interesting graphic, bland and unvoiced conclusion

You're also missing a lot of details. For example, Milvus and Zilliz are actually a little different, check this out for more details: https://github.com/zilliztech/VectorDBBench (of course run it on your own stuff, don't blindly trust companies just because their product is open source)

Also if you want to throw some more comparisons in their checkout elastic search

Post reply on HN