> Source: https://meetrix.io/store/milvus/ > Markdown copy of that page. Cite the URL above, not this file. [Store](https://meetrix.io/store/) Milvus Open-source vector database # Self-hosted Milvus vector database on AWS and Google Cloud Run Milvus, the open-source vector database behind many RAG pipelines and semantic search engines, from a pre-configured image in your own cloud account. You pay for the server, not per stored vector or per query. [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-74f7pvxzezeno)[ Launch on Google Cloud](https://console.cloud.google.com/marketplace/product/meetrix-public/milvus-vector-database) - Ready in a few minutes - Runs in your own account - No per-query fees ![Milvus vector database deployed on AWS by Meetrix](https://meetrix.io/assets/store/milvus/milvus.webp) ## What is Milvus? Milvus is an open-source database built for storing, indexing and searching embedding vectors, the numbers that text, images, audio and video are turned into before an AI model can compare them. Instead of matching keywords, it finds the nearest vectors to a query, which is what powers retrieval-augmented generation (RAG), semantic search and recommendations. - ### RAG pipelines Store document embeddings and retrieve the closest matches to feed your LLM. - ### Semantic search Search by meaning rather than exact keywords across text, images and more. - ### Recommendations Find similar products, content or users from their vector representations. - ### Similarity search Match images and video frames against large collections of embeddings. - ### Standard SDKs Connect with pymilvus or any client that speaks the Milvus protocol on port 19530. - ### Open source No per-vector or per-query billing, and your data stays in your own account. ## What's in the Meetrix Milvus image Running Milvus by hand means Docker Compose files, dependency versions and several supporting services to wire together. The marketplace image arrives with all of that done. - Milvus installed and started on boot - Client/gRPC port 19530 ready for pymilvus - A default admin user to connect with straight away - A confirmation page on the server address once Milvus is up - On AWS, an IAM role that can request a Let's Encrypt certificate for a Route 53 domain - Support from Meetrix engineers ## How to set up a self-hosted Milvus server 1. ### Launch the server Subscribe on AWS Marketplace or launch from Google Cloud Marketplace, pick a region and machine size, and deploy. Allow a few minutes for Milvus to start. 2. ### Open port 19530 The AWS security group opens it for you. On Google Cloud, confirm a firewall rule allows TCP 19530 from the addresses that will connect. 3. ### Connect with pymilvus Point pymilvus at the server's public IP on port 19530 and sign in with the default root user. 4. ### Secure it Change the default root password before storing real data, and limit the allowed source IPs instead of leaving the port open to everyone. ## Choose your cloud ### Milvus on AWS An AMI on AWS Marketplace, launched into your own AWS account with one-click launch or from the EC2 console. Deploys with One-click launch or EC2 console Recommended size t3a.large Client port 19530 #### Setup guides - [**Developer guide** Launch, connect, SSL, troubleshoot](https://meetrix.io/blogs/milvus-developer-guide/) - [**Milvus on AWS Marketplace** Who it suits and how it compares](https://meetrix.io/blogs/milvus-aws-marketplace/) [Launch on AWS](https://aws.amazon.com/marketplace/pp/prodview-74f7pvxzezeno) ### Milvus on Google Cloud The same database as a Google Cloud Marketplace image, deployed into your own GCP project. Deploys with Marketplace deployment form Recommended size e2-standard-2, 20 GB disk Free trial 5 days, up to USD 50 licence credit #### Setup guides - [**Developer guide** Configure, connect, firewall, troubleshoot](https://meetrix.io/blogs/milvus-gcp-developer-guide/) - [**Milvus on Google Cloud Marketplace** Who it suits and how it compares](https://meetrix.io/blogs/milvus-vector-database-gcp/) [Launch on Google Cloud](https://console.cloud.google.com/marketplace/product/meetrix-public/milvus-vector-database) ## Milvus server ports and requirements Allow these ports in your AWS security group or GCP firewall. If pymilvus cannot connect, check port 19530 first. | Service | Ports | Protocol | | --- | --- | --- | | Milvus client / gRPC | 19530 | TCP | | HTTP and HTTPS | 80, 443 | TCP | | SSH (administration) | 22 | TCP | Server size: t3a.large on AWS or e2-standard-2 (2 vCPU, 8 GB RAM) on Google Cloud to start. Choose a larger machine as your collections and query volume grow. ## Milvus by Meetrix vs Pinecone vs Zilliz Cloud | | Milvus by Meetrix | Pinecone | Zilliz Cloud | | --- | --- | --- | --- | | Hosting | Your AWS account or GCP project | Pinecone's cloud, no self-host option | Zilliz's managed cloud, or a self-hosted enterprise tier | | Data control | Vectors never leave your account | Pinecone stores and indexes your vectors | Zilliz stores and indexes your vectors on the hosted tier | | Pricing model | Cloud compute only, no per-query fee | Usage-based, per stored vector and per query | Usage-based, per compute unit on the hosted tier | | Data residency | Any region you choose | Limited region choice, Pinecone's terms apply | Limited region choice, Zilliz's terms apply | Zilliz Cloud is the managed version of Milvus. [Read the full Milvus on AWS comparison →](https://meetrix.io/blogs/milvus-aws-marketplace/) ## Milvus FAQ What is Milvus used for? Storing and searching embedding vectors at scale: retrieval-augmented generation (RAG), semantic search, recommendation engines, and image or video similarity search. If your app turns content into vectors and needs the closest matches fast, that is what Milvus does. Is Milvus free? Milvus itself is open source and free. Through the Meetrix listings you pay standard AWS or Google Cloud compute costs for the server, plus any Meetrix software fee shown on the marketplace listing, not a per-vector or per-query fee. Which machine size do I need? t3a.large is the recommended starting point on AWS, and e2-standard-2 (2 vCPU, 8 GB RAM) with a 20 GB disk on Google Cloud. Resize the instance as your collections and query volume grow. How do I connect to Milvus after launching it? Use the pymilvus SDK with the server's public IP, port 19530 and the default root user. Visiting http:// in a browser shows a confirmation page once Milvus is running. What is the default login? The image ships with the admin user root and the password Milvus. Change the password before storing anything beyond test data. Does it include a web admin UI? No. Milvus does not ship one and the image stays lean. If you want a UI, run Attu, the open-source Milvus management tool, in a separate container pointed at port 19530. Can I connect my existing RAG pipeline? Yes. It is a standard Milvus instance, so in most cases you only change the host and port your client points at. How do I upgrade? When a new version is published on the marketplace, back up your Milvus data, remove the old deployment and launch the new version. ## Milvus guides and articles ### [Milvus on AWS Marketplace: a Self-Hosted Vector Database for RAG](https://meetrix.io/blogs/milvus-aws-marketplace/) Run your own vector database without the per-query bill, and how it compares to Pinecone and Zilliz Cloud. ### [Milvus on GCP Marketplace: a Self-Hosted Vector Database for RAG](https://meetrix.io/blogs/milvus-vector-database-gcp/) Deploy Milvus on Google Cloud in minutes and keep embeddings in the region you choose. ### [Milvus on GCP: Developer Guide](https://meetrix.io/blogs/milvus-gcp-developer-guide/) Configure the deployment, open port 19530 and connect with pymilvus, step by step. ## Need a hand with your Milvus server? We build and run self-hosted AI infrastructure for teams every day, from instance sizing to index tuning. Tell us what you need. [Contact us](https://meetrix.io/contact-us/)