# Elasticsearch as vector db **URL:** \ **Category:** Elasticsearch\ **Tags:** vector-search\ **Created:** [December 12, 2023, 8:27pm UTC](https://discuss.elastic.co/t/elasticsearch-as-vector-db/349192 "2023-12-12T20:27:33Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![Alexander\_Gamanyuk1](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/alexander_gamanyuk1/32/87063_2.png) [@Alexander\_Gamanyuk1](https://discuss.elastic.co/u/Alexander_Gamanyuk1)\ **Post date:** [December 12, 2023, 8:27pm UTC](https://discuss.elastic.co/t/elasticsearch-as-vector-db/349192/1 "2023-12-12T20:27:33Z")
I've been using Elasticsearch since early 2010. We have multiple self-hosted clusters with a few terabytes of data, used for search, analytics, and other use cases. But recently, we started building [Retrieval Augmented Generation](https://copilot.us) (RAG) apps as well. For the RAG, we use Qdrant Cloud, which is good. However, I'm interested in exploring the possibility of migrating it to a self-hosted Elasticsearch setup. Does anyone have experience using Elasticsearch as a main vector database for storage and search? ---
**Author:** ![Serena\_Chou](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/serena_chou/32/100087_2.png) [@Serena\_Chou](https://discuss.elastic.co/u/Serena_Chou)\ **Post date:** [December 12, 2023, 10:40pm UTC](https://discuss.elastic.co/t/elasticsearch-as-vector-db/349192/2 "2023-12-12T22:40:17Z")
Hey Alexander, I'm happy to see you exploring our capabilities. As you start down this path, I wanted to put a few things out there for you to get a sense of the possibilities that we provide. One, we have a general site for developers to help with the purposes of building RAG applications [Elastic Search Labs](https://www.elastic.co/search-labs) You'll be able to see tutorials, blogs, notebooks and code applications to bootstrap your journey. Perhaps of use could be taking a look at the tutorial we have here [Welcome — Elastic Search Labs](https://www.elastic.co/search-labs/tutorials/chatbot-tutorial/welcome) Then, I'd like to point out that Elastic is doing a tremendous amount of investment into the technology that is necessary to be a fundamental part of the RAG app - so I'd probably read through a few of these blogs: These two blogs give you a sense of our stance towards the technology that fuels our vector database capabilities: > **[Vector search in Elasticsearch: The rationale behind the design — Elastic...](https://www.elastic.co/search-labs/blog/articles/vector-search-elasticsearch-rationale)** > > There are different ways to implement a vector database, which have different trade-offs. In this blog, you'll learn more about how vector search has been integrated into Elastisearch and the trade-offs that we made. as well as the investments we are pouring into it to make sure it's the fastest and most performant available on the market. > **[Apache Lucene 9.9, the fastest Lucene release ever — Elastic Search Labs](https://www.elastic.co/search-labs/blog/articles/apache-lucene-9.9-search-speedups)** > > Lucene 9.9 was released recently and brings major speedups to query evaluation For RAG application developers like yourself, you may be interested in this walkthrough of RAG evaluation > **[Evaluating RAG: A journey through metrics — Elastic Search Labs](https://www.elastic.co/search-labs/blog/articles/evaluating-rag-metrics)** > > Learn how Elastic is evaluating RAG. And a potential look into how we built our own proprietary model that seamlessly fits into the RAG story. > **[Improving information retrieval in the Elastic Stack: Optimizing retrieval...](https://www.elastic.co/search-labs/blog/articles/introducing-elser-v2-part-2)** > > Learn about how we're reducing retrieval costs for ELSER v2. If you have any questions, we'd really love to hear from you! ---
**Author:** ![joemcelroy](https://sea2.discourse-cdn.com/elastic/user_avatar/discuss.elastic.co/joemcelroy/32/103757_2.png) [@joemcelroy](https://discuss.elastic.co/u/joemcelroy)\ **Post date:** [December 13, 2023, 9:04am UTC](https://discuss.elastic.co/t/elasticsearch-as-vector-db/349192/3 "2023-12-13T09:04:05Z")
Hey @Alexander_Gamanyuk1 would be interesting to hear your use-case and any libraries that you use in conjunction too 🙂 Joe ---
**Author:** ![system](https://us1.discourse-cdn.com/elastic/original/3X/1/a/1ac57faf039f6b580b3f104ef42a2a89e41014de.png) [@system](https://discuss.elastic.co/u/system)\ **Post date:** [January 10, 2024, 9:04am UTC](https://discuss.elastic.co/t/elasticsearch-as-vector-db/349192/4 "2024-01-10T09:04:59Z")
This topic was automatically closed 28 days after the last reply. New replies are no longer allowed.