# Best vector database to use with RAG **URL:** \ **Category:** ChatGPT\ **Tags:** embeddings, chatgpt, vector-db, rag\ **Created:** [February 5, 2024, 5:43pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350 "2024-02-05T17:43:11Z")\ **Posts on this page:** 18\ **Page:** 1
**Author:** ![ahmed-shaaban](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ahmed-shaaban/32/288518_2.png) [@ahmed-shaaban](https://community.openai.com/u/ahmed-shaaban)\ **Post date:** [February 5, 2024, 5:43pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/1 "2024-02-05T17:43:11Z")
I am using RAG but i find alot vector databases so what is the best vector database to use with (RAG) and what is the best solution to fit chatgpt4 tokens limitaion ---
**Author:** ![Macha](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/macha/32/171757_2.png) [@Macha](https://community.openai.com/u/Macha)\ **Post date:** [February 5, 2024, 10:21pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/2 "2024-02-05T22:21:53Z")
Weeeell, have you worked with DBs before? If you have, you may be able to find a vector DB that may integrate with or resemble closely what you like 🙂 Are you looking for Free? Open Source? Enterprise Grade / organization / business? Ease of use? How big is the data? ---
**Author:** ![chbussler](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/chbussler/32/220299_2.png) [@chbussler](https://community.openai.com/u/chbussler)\ **Post date:** [February 5, 2024, 11:22pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/3 "2024-02-05T23:22:04Z")
Down in section “Benchmarks, comparisons, standardization” are a few references that have comparisons (for sure not complete): [Vector Databases (are All The Rage) | by Christoph Bussler | Google Cloud - Community | Medium](https://medium.com/google-cloud/vector-databases-are-all-the-rage-872c888fa348) Maybe you could use this, at least as a start. ---
**Author:** ![ahmed-shaaban](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ahmed-shaaban/32/288518_2.png) [@ahmed-shaaban](https://community.openai.com/u/ahmed-shaaban)\ **Post date:** [February 5, 2024, 11:38pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/4 "2024-02-05T23:38:23Z")
Yes, I used (qdrant, chroma, and faiss) I think Pinecone is good but I didn’t use it -I have big data to deal with and right now I use qdrant -I need it Open Source @Macha ---
**Author:** ![ahmed-shaaban](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ahmed-shaaban/32/288518_2.png) [@ahmed-shaaban](https://community.openai.com/u/ahmed-shaaban)\ **Post date:** [February 5, 2024, 11:40pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/5 "2024-02-05T23:40:56Z")
I really appreciate your help. Thank you. @chbussler ---
**Author:** ![Macha](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/macha/32/171757_2.png) [@Macha](https://community.openai.com/u/Macha)\ **Post date:** [February 5, 2024, 11:58pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/6 "2024-02-05T23:58:26Z")
Soo, this? > **[Qdrant - Vector Database](https://qdrant.tech/)** > > Qdrant is an Open-Source Vector Database and Vector Search Engine written in Rust. It provides fast and scalable vector similarity search service with convenient API. ---
**Author:** ![ahmed-shaaban](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ahmed-shaaban/32/288518_2.png) [@ahmed-shaaban](https://community.openai.com/u/ahmed-shaaban)\ **Post date:** [February 6, 2024, 12:11am UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/7 "2024-02-06T00:11:05Z")
Yes, I am using it for my data. @Macha ---
**Author:** ![Macha](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/macha/32/171757_2.png) [@Macha](https://community.openai.com/u/Macha)\ **Post date:** [February 6, 2024, 12:25am UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/8 "2024-02-06T00:25:43Z")
Then just stick with that? I don’t see any reason to use anything different 🤷‍♀️. Qdrant is a very popular and well respected choice for this. ---
**Author:** ![ahmed-shaaban](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ahmed-shaaban/32/288518_2.png) [@ahmed-shaaban](https://community.openai.com/u/ahmed-shaaban)\ **Post date:** [February 6, 2024, 12:33am UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/9 "2024-02-06T00:33:48Z")
I feel like it didn’t work well and I there might be something more efficient. @Macha ---
**Author:** ![Macha](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/macha/32/171757_2.png) [@Macha](https://community.openai.com/u/Macha)\ **Post date:** [February 6, 2024, 12:53am UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/10 "2024-02-06T00:53:20Z")
In what ways? What was inefficient about it? ---
**Author:** ![fern2gue](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/fern2gue/32/301203_2.png) [@fern2gue](https://community.openai.com/u/fern2gue)\ **Post date:** [February 6, 2024, 9:12am UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/11 "2024-02-06T09:12:17Z")
have you tried SuperDuperDB? It can do that and much more ---
**Author:** ![ahmed-shaaban](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ahmed-shaaban/32/288518_2.png) [@ahmed-shaaban](https://community.openai.com/u/ahmed-shaaban)\ **Post date:** [February 6, 2024, 1:18pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/12 "2024-02-06T13:18:32Z")
When I insert many tokens in one place, it may split into two or not take all the text, corrupting the meaning. @Macha ---
**Author:** ![ahmed-shaaban](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ahmed-shaaban/32/288518_2.png) [@ahmed-shaaban](https://community.openai.com/u/ahmed-shaaban)\ **Post date:** [February 6, 2024, 1:19pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/13 "2024-02-06T13:19:57Z")
No, I have never tried it. Thanks, I will try it right now. @fern2gue ---
**Author:** ![dignity\_for\_all](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/dignity_for_all/32/300058_2.png) [@dignity\_for\_all](https://community.openai.com/u/dignity_for_all)\ **Post date:** [February 6, 2024, 1:21pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/14 "2024-02-06T13:21:58Z")
> [@ahmed-shaaban](#): > > what is the best solution to fit chatgpt4 tokens limitaion I think Chroma or Faiss would be great! ---
**Author:** ![ahmed-shaaban](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ahmed-shaaban/32/288518_2.png) [@ahmed-shaaban](https://community.openai.com/u/ahmed-shaaban)\ **Post date:** [February 6, 2024, 1:25pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/15 "2024-02-06T13:25:12Z")
I tried using ChromaDB but it didn’t work. I think Faiss is a better option. @fern2gue ---
**Author:** ![frankocean](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/frankocean/32/301399_2.png) [@frankocean](https://community.openai.com/u/frankocean)\ **Post date:** [February 6, 2024, 2:52pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/16 "2024-02-06T14:52:24Z")
Hi, I tried SuperDuperDB It worked really well, You can try to use their in-memory or lancedb configuration for vector search support. Thanks ---
**Author:** ![ahmed-shaaban](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/ahmed-shaaban/32/288518_2.png) [@ahmed-shaaban](https://community.openai.com/u/ahmed-shaaban)\ **Post date:** [February 6, 2024, 3:15pm UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/17 "2024-02-06T15:15:38Z")
Thank you, I will give it a try. @frankocean ---
**Author:** ![bbqchickenrobot](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/bbqchickenrobot/32/538671_2.png) [@bbqchickenrobot](https://community.openai.com/u/bbqchickenrobot)\ **Post date:** [January 19, 2025, 2:13am UTC](https://community.openai.com/t/best-vector-database-to-use-with-rag/615350/18 "2025-01-19T02:13:38Z")
Funny nobody mentioned Milvus… google “milvus vector database” and you’ll be on your way