Skip to content

Vector DBNeuML

txtai

All-in-one open-source embeddings database for semantic search and RAG.

Category
Vector DB
Pricing
FREE
Source
Open source
Hosting
Self-host
Platforms
APICLI
Models
Model-agnostic
Verified
Jun 13, 2026

txtai is an embeddings database that unifies dense and sparse vector indexes, graph networks, and a relational database into a single store for semantic search and LLM workflows. Beyond vector search it ships retrieval-augmented generation, pipelines, and agents, and can be built with Python or declarative YAML. It runs locally or self-hosted and exposes API bindings for JavaScript, Java, Rust, and Go.

Capabilities 6

What it actually does — grouped by capability family.

  • Agent framework (secondary capability)
  • Trigger-action automation (secondary capability)
  • Embeddings (primary capability)
  • Vector search (primary capability)
  • RAG pipeline (secondary capability)
  • Knowledge graph (secondary capability)

Pros & cons

  • Fully open source (Apache-2.0), runs locally
  • Vector + graph + SQL in one store
  • Build with Python or YAML
  • API bindings for JS, Java, Rust, Go
  • Built-in RAG, agents, and pipelines
  • Maintained by a small team, not a big vendor
  • Smaller ecosystem than Pinecone/Weaviate
  • No managed cloud offering
  • More concepts than a plain vector DB

Tags

Alternatives to txtai (4)

View all Vector DB →
  • View Chroma details
    Vector DBFREEMIUMOpen core

    Chroma

    Chroma

    Embedded vector DB. Pip-install, prototype, scale later.

    The low-friction starting point — Chroma runs embedded inside your Python process or as a hosted service. Great for prototypes and small-to-medium RAG apps; upgrade to a managed option when you outgrow it.

    Pip-install, embedded in-process
    Not built for massive scale
    • open-source
    • embedded
    • prototype
    • python
    Open
  • View LanceDB details
    Vector DBFREEMIUMOpen core

    LanceDB

    LanceDB

    Embedded multimodal vector database on the Lance format.

    An open-source retrieval engine for AI built on the Lance columnar format. It runs in-process alongside your app — no separate server — and stores, indexes, and searches vectors, metadata, and multimodal data (text, images, video) with vector, full-text, and SQL queries. A managed enterprise lakehouse tier scales the same engine to petabytes.

    Embeds in your app; runs on edge/desktop
    Newer; smaller community than Qdrant/Milvus
    • vector-search
    • multimodal
    • embedded
    • lance
    • +1
    Open
  • View Weaviate details
    Vector DBFREEMIUMOpen core

    Weaviate

    Weaviate

    Open-source vector database with built-in vectorisers.

    Cloud-native vector DB that can compute embeddings inline — pass raw text in, store vectors out. Strong hybrid (BM25 + vector) search; self-hostable or managed.

    Hybrid BM25 + vector search
    Resource-heavy at large scale
    • open-source
    • self-hosted
    • hybrid-search
    • rag
    Open
  • View Qdrant details
    Vector DBFREEMIUMOpen core

    Qdrant

    Qdrant

    Open-source, Rust-based vector DB. Fast, predictable, self-hostable.

    Vector database written in Rust with a strong focus on filtering, payloads, and predictable latency at scale. Self-host on a single binary or use the managed cloud.

    Open source, written in Rust
    More ops than fully-managed rivals
    • open-source
    • rust
    • self-hosted
    • fast
    Open
Open txtai