Chroma vs Vearch

Chroma is open-source infrastructure for storing embeddings and metadata, then searching and retrieving information across text, images, and other modalities. Search options include dense, sparse, and hybrid vector search, plus full-text and regex search and metadata filtering. It can run locally through pip, npm, or Docker, on Chroma Cloud, or in a customer’s own VPC. The maker says its Apache 2.0-licensed codebase powers both the open-source database and Chroma Cloud. Documented integrations include embedding providers such as OpenAI, Cohere, Google Gemini, Hugging Face, Jina AI, and Ollama, and frameworks such as LangChain, LlamaIndex, Haystack, Streamlit, and DeepEval. Cloud security features include encryption in transit and at rest, SSO, role-based access control, and employee MFA; Chroma Cloud has completed a SOC 2 Type II examination. Starter is free, with 10 databases and 10 team members. Team is $250 a month plus usage and includes $100 credits, 100 databases, and 30 team members.

Vearch is a free, open-source, cloud-native distributed vector database for similarity search in AI applications. It searches embedding vectors and can combine vector queries with scalar filtering for metadata conditions. The project describes replication and elastic scale-out and says it can retrieve vectors among millions of objects in milliseconds. Its Router exposes REST operations for upserting, deleting, searching, and querying data. Client SDKs are listed for Python, Go, Java, and Rust, with integrations for LangChain, LlamaIndex, LangChainGo, and LangChain4j. Deployment options include Kubernetes through Helm, Docker Compose in standalone or cluster mode, Docker, and compilation from source. PartitionServer uses Raft-based replication for document partitions, while Gamma is a Faiss-based vector search engine. Vearch is licensed under Apache License 2.0 and supports Linux and macOS self-hosted deployments. Community support is available through GitHub Issues, an email discussion group, and Slack. The VisualSearch demo requires an image retrieval plugin for object detection and feature extraction.