What types of search does Chroma support?

Chroma supports a comprehensive range of search types including vector search for semantic similarity, sparse vector search (BM25, SPLADE), full-text search with trigram and regex capabilities, and metadata search for filtering and faceted results. This allows for highly flexible and powerful retrieval in AI applications.

How does Chroma's pricing work?

Chroma offers a freemium model with a Starter plan that includes $5 in free credits, followed by usage-based pricing for writes, storage, queries, and network usage. There are also Team and Enterprise plans with additional features, support, and volume discounts, including custom pricing for large organizations.

Can I run Chroma on my own infrastructure?

Yes, Chroma is open-source (Apache 2.0) and can be run locally or deployed on your own infrastructure using provided deployment guides. For enterprise needs, Chroma also offers BYOC (Bring Your Own Cloud) options within your VPC, providing control over data and compliance while leveraging Chroma's managed control plane.

Chroma

Chroma is an open-source search infrastructure for AI, offering fast, serverless, and scalable vector, full-text, regex, and metadata search. It is built on object storage and trusted by millions of developers.

Claim this tool

3views

Visit site

At a glance

Pricing

Freemium · Usage-based · Enterprise · Open Source

Free tier

Yes

API

Yes

Skill level

Advanced

About

What is Chroma?

Chroma provides open-source search infrastructure specifically designed for AI applications, supporting a wide range of search capabilities including vector, full-text, regex, and metadata search. It is built on object storage, ensuring scalability and cost-efficiency, and is trusted by millions of developers. The platform offers fast, serverless performance with low-latency queries over billions of multi-tenant indexes. Chroma is Apache 2.0 licensed and features automatic data tiering, making it up to 10x cheaper than traditional solutions. It supports various search types like sparse vector search (BM25, SPLADE), semantic similarity search, trigram search, and faceted search. Additionally, it includes features like dataset versioning, A/B testing, CLI tools, and enterprise-grade options for security and compliance.

Best used for

Ideal for developers who need to build scalable AI applications, implement advanced search functionalities, and manage large datasets efficiently. Especially valuable for those requiring vector, full-text, and metadata search capabilities with low latency and cost-effective object storage.

Capabilities

Key features

Vector search
Full-text search
Regex search
Metadata filtering
Sparse vector search
Dataset versioning
Object storage optimized

Audience

developer individual freelancer smb developers enterprise

Integrations

github

FAQs

Common questions

Trending

Subcategories trending in Coding & Development

Open Source & Models DevOps & Infrastructure No-Code / Low-Code Backend & APIs Testing & QA Prompt Engineering

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce