Chroma Vector Database for AI | Support by cloudimg

This is a repackaged open source software product wherein additional charges apply for cloudimg support services.

Chroma is the popular open source vector database for AI applications. It stores embeddings with their metadata and runs fast similarity search, making it a simple, developer-friendly backend for retrieval augmented generation (RAG), semantic search, and recommendation systems. This AMI delivers the Chroma server fully installed and configured as a system service, so a production-ready vector database is running within minutes of launch. The current release available is Chroma 1.5.

Deploying Chroma manually on EC2 means configuring Python environments, setting up reverse proxies, hardening authentication, separating storage volumes, and writing systemd units - work that can take hours and introduces security risk if done incorrectly. Many community images ship with shared default credentials or no authentication at all. This AMI eliminates that effort and risk: you get a hardened, production-grade deployment with unique-per-instance credentials, a dedicated data volume, and automatic service recovery - all backed by 24/7 expert support from cloudimg.

Chroma is installed into a dedicated Python virtual environment under /opt/chroma and run by an unprivileged service account on Python 3.12. It listens on the loopback address and an nginx reverse proxy fronts it on port 80. A systemd service starts the server on boot and restarts it on failure.

Access is gated by HTTP Basic Authentication at the nginx reverse proxy. This image generates a fresh password, unique to your instance, on its first boot and writes it to a root-only file. The public heartbeat endpoint stays open for load balancers; everything else requires the password. The Chroma client authenticates with its built-in basic auth provider. No shared or default credentials ship in the image.

Connect with the Chroma client, create a collection, and add documents with your own embeddings. Your data lives on a dedicated, independently resizable storage volume kept separate from the operating system disk. The image ships no embedding model and is CPU only.

• Amazon S3 - Back up your Chroma data volume to S3 for durable, cost-effective storage and disaster recovery.
• Amazon CloudWatch - Monitor instance health, nginx access logs, and Chroma service status using CloudWatch agent and alarms.
• Amazon Bedrock - Generate embeddings with Bedrock foundation models (e.g., Titan Embeddings) and store them directly in Chroma for RAG workflows.
• LangChain and LlamaIndex - Use Chroma as the vector store in popular orchestration frameworks to build end-to-end RAG pipelines.

• E-commerce product discovery - Ingest millions of product description embeddings and serve real-time semantic search to surface relevant items beyond keyword matching.
• IT support knowledge base - Ingest support tickets and documentation nightly, then query at request time to surface the most relevant knowledge-base articles for agents or chatbots.
• Healthcare research - Store embeddings of clinical literature and retrieve contextually similar papers for retrieval augmented generation, keeping sensitive data within your own VPC for compliance.
• RAG pipelines - Prototyping and production retrieval augmented generation backends for any LLM-powered application.
• Data residency - A self-hosted, in-your-own-VPC vector database for teams with compliance or data residency requirements.

24/7 technical support by email and live chat. Our engineers help with Chroma deployment, collection design, embedding functions, backups, TLS termination, scaling, and AWS integration configuration.

All product and company names are trademarks or registered trademarks of their respective holders. Use of them does not imply any affiliation with or endorsement by them.