ChromaDB
Fast, serverless, and scalable search infrastructure supporting vector, full-text, regex, and metadata search. Built on object storage and trusted by millions of developers. Open-source Apache 2.0.
Trusted by teams at
Open source at the core
Chroma is licensed under Apache 2.0. The same codebase powers both the open-source search engine and Chroma Cloud, so there is no vendor lock-in.
Single-node
Run locally with pip, npm, or Docker. In-memory or persistent storage.
Chroma Cloud
Fully managed, serverless, and scalable. No provisioning, no tuning. Get started in under 30 seconds.
Bring your own cloud
Deploy in your own VPC with multi-region replication and point-in-time recovery. Full control over your infrastructure.
Many search methods, one platform
Chroma unifies dense vector search, sparse vector search, full-text search, regex matching, and metadata filtering in a single query interface. Combine them with hybrid search for the best retrieval quality.
◆
Vector search
Semantic similarity search
◇
Sparse vector search
Lexical search (BM25, SPLADE)
●
Full-text Search
Trigram and regex search
◐
Metadata Search
Filtering and faceted search
◊
Forking
Dataset versioning, A/B testing, and roll-outs
▣
CLI
Command-line tools for development
import { ChromaClient } from 'chromadb'
const client = new ChromaClient()
const collection = await client.getOrCreateCollection({
name: "my_collection"
})
// Add documents with embeddings
await collection.add({
ids: ["id1", "id2"],
documents: ["This is a document", "Another doc"],
embeddings: [[1.2, 2.3, ...], [3.4, 4.5, ...]]
})
// Query by vector similarity
const results = await collection.query({
queryEmbeddings: [[1.1, 2.2, ...]],
nResults: 10
})Terminal Output
Run the code above to see the output ^
Fast search over billions of multi-tenant indexes
Chroma's indexes are built and optimized for object storage, offering unparalleled cost and performance. State-of-the-art vector, full-text, and regex search.
Latency
Query Latency
@384 dim at 100k vectors
Warm
Cold
p50
20ms
650ms
p90
27ms
1.2s
p99
57ms
1.5s
Contact us to run a POC for your specific workload.
Dedicated clusters can be scaled to your specific requirements.
Dedicated clusters can be scaled to your specific requirements.
Technical specs
Write throughput (per collection)30 MB/s (2000+ QPS)
Concurrent reads (per collection)5 (100+ QPS)
Collections per database1M
Records per collection5M
Recall90-100%
Zero-ops infra
┌───────────────────────────────┐ │ Query Layer │ │ Fast memory cache (hot) │ │ SSD cache (warm) │ └───────────────────────────────┘ ↕ Intelligent tiering ┌───────────────────────────────┐ │ Storage Layer │ │ S3 / GCS (cold) │ │ • All vectors │ │ • All metadata │ │ • All indexes │ └───────────────────────────────┘
Unlike legacy search systems, Chroma is a database you'll want to be on-call for.
✓Auto-scales with usage
✓No manual tuning
✓Serverless pricing
Chroma takes full advantage of object storage with automatic query-aware data tiering and caching.
✓Vectors are large: 1GB text → 15GB of vectors
✓Memory is expensive: $5/GB/mo
✓Object storage is not: $0.02/GB/mo
