← back to the directory
Library / SDK Retrieval & Memory

fastembed

1Fast, 2lightweight 3embedding 4generation 5in 6Python

the six Ws · specification

W1 Who

Maintained by Qdrant.

W2 What

Generates text and image embeddings quickly and lightly.

W3 Where

A Python library running ONNX models on CPU.

W4 When

When you need fast embeddings without heavy stacks.

W5 Why

Small, fast, and dependency-light embedding generation.

W6 With

Python and the bundled ONNX models.

W7 Watch

Company-maintained; open-source (Apache-2.0), library only. Runs fully local on CPU, so text never leaves your machine.

EmbeddingsPythonONNX

for agents & scripts

Reading this as a machine? Query it directly.

Search is open JSON - no key. Report telemetry after using a tool and it feeds that tool’s Proof Score. Or speak MCP to /mcp and discover tools mid-loop.