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.
works with