Milvus
by Zilliz
At a glance
Open-source vector database that scales from an embedded library to distributed retrieval clusters.
vector developer-tools
- Licence
- Not recorded
- Category
- Platforms & Infrastructure
- Business model
- Open (open weights/source)
- Availability
- Not recorded
- Launched
- Not recorded
Overview
Typical uses include Semantic retrieval for RAG; Search over embedded application data. Documented capabilities: Store embeddings and search with structured metadata; Lite, standalone and distributed deployment modes; Hybrid search and support for multiple vector types.
Compare this tool Suggest a correction
Key features
- Store embeddings and search with structured metadata
- Lite, standalone and distributed deployment modes
- Hybrid search and support for multiple vector types
Use cases
- Semantic retrieval for RAG
- Search over embedded application data
Pricing
The open-source software can be run on your own infrastructure. Compute, storage and any external model API usage are separate costs; a managed service is not included.
Record details
Provenance, dates and links are kept here so the main sections stay about the product itself.
Links, dates and provenance
- Record updated
- 2026-11-03
- Canonical URL
- https://globalaiproductindex.com/products/milvus/
Selection profile
Every field says where its value comes from. "Unknown" means we have not confirmed it — it does not mean the product lacks the feature.
Selection profile11 fields6 unknown
- Tasks it fits
- Search
Editorial classification of the documented features; not a product-performance test.
Suggest a correction - How you use it
- Self-run service
Editorial classification of the documented features; not a product-performance test.
Suggest a correction - Runs on
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Where it runs
- Self-hosted
Editorial classification of the documented features; not a product-performance test.
Suggest a correction - Works offline
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Official service region
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Public API
- Yes
Editorial classification of the documented features; not a product-performance test.
Suggest a correction - Licence
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Commercial use
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Interface languages
- Not recorded
This product-specific field was not established in this entry’s source review.
Suggest a correction - Billing
- Open source Free allowance: Yes Subscription required: No
Prices are the vendor’s advertised entry price and exclude taxes; always confirm on the vendor’s own page.
Suggest a correction
Where each value comes from
- Tasks it fits
- Our inference
- How you use it
- Our inference
- Runs on
- Unknown
- Where it runs
- Our inference
- Works offline
- Unknown
- Official service region
- Unknown
- Public API
- Our inference
- Licence
- Unknown
- Commercial use
- Unknown
- Interface languages
- Unknown
Key facts and their evidence
Each fact lists the conditions it holds under, the page it was read from and the day it was checked.
-
Capability: Store embeddings and search with structured metadata Verified 2026-11-03 milvus.io ↗
Suggest a correction
Frequently asked questions
Where does Milvus fit in a workflow?
Open-source vector database that scales from an embedded library to distributed retrieval clusters. Store embeddings and search with structured metadata.
What costs and limits should I compare before choosing Milvus?
The open-source software can be run on your own infrastructure. Compute, storage and any external model API usage are separate costs; a managed service is not included.
Similar products
- Chroma — Retrieval infrastructure with an open-source database and serverless cloud search.
- LanceDB — Multimodal data platform and embedded retrieval library built around Lance tables.
- Qdrant — Vector search engine for semantic retrieval with payload filters and hybrid query support.
- turbopuffer — Object-storage-native search engine for vector and full-text retrieval with cached compute.
- Vespa — Search and ranking platform combining vector retrieval, lexical search and model-based relevance.
- Andi — Conversational AI search engine that answers questions and summarizes pages instead of showing ad-driven links.
All Milvus alternatives → · All Platforms & Infrastructure products →
Sources
- Milvus — official product ↗
- Milvus — official documentation and terms ↗
- Milvus — official documentation and terms ↗
This record was last reviewed on 2026-11-03.
Machine-readable record: /api/products/milvus.json · Spot an error? Suggest a correction