mirror of https://github.com/qdrant/fastembed.git synced 2026-08-04 09:01:06 -05:00

Files

NirantK 2017fdc22a * fix(docs): change method name from encode to embed in DefaultEmbedding class

* fix(README.md): change method name from encode to embed in Embedding class
* fix(docs/Getting Started.ipynb): change method name from encode to embed in Embedding class

2023-08-23 09:49:48 +05:30

1.2 KiB

Raw Blame History

⚡️ What is FastEmbed?

FastEmbed is an easy to use -- lightweight, fast, Python library built for retrieval augmented generation. The default embedding supports "query" and "passage" prefixes for the input text.

🚀 Installation

To install the FastEmbed library, pip works:

pip install fastembed

📖 Usage

from fastembed.embedding import DefaultEmbedding

documents: List[str] = [
    "passage: Hello, World!",
    "query: Hello, World!", # these are two different embedding
    "passage: This is an example passage.",
    # You can leave out the prefix but it's recommended
    "fastembed is supported by and maintained by Qdrant." 
]
embedding_model = DefaultEmbedding() 
embeddings: List[np.ndarray] = list(embedding_model.embed(documents))

🚒 Under the hood

Why fast?

It's important we justify the "fast" in FastEmbed. FastEmbed is fast because:

Quantized model weights
ONNX Runtime which allows for inference on CPU, GPU, and other dedicated runtimes

Why light?

No hidden dependencies on PyTorch or TensorFlow via Huggingface Transformers

Why accurate?

Better than OpenAI Ada-002
Top of the Embedding leaderboards e.g. MTEB

1.2 KiB Raw Blame History Unescape Escape