fastembed-haystack 1.4.0

Haystack 2.x component to embed strings and Documents using fastembed embedding model

fastembed-haystack

---

Table of Contents

• Installation
• License

Installation

pip install fastembed-haystack

Usage

You can use FastembedTextEmbedder and FastembedDocumentEmbedder by importing as:

from haystack_integrations.components.embedders.fastembed import FastembedTextEmbedder

text = "fastembed is supported by and maintained by Qdrant."
text_embedder = FastembedTextEmbedder(
    model="BAAI/bge-small-en-v1.5"
)
text_embedder.warm_up()
embedding = text_embedder.run(text)["embedding"]

from haystack_integrations.components.embedders.fastembed import FastembedDocumentEmbedder
from haystack.dataclasses import Document

embedder = FastembedDocumentEmbedder(
    model="BAAI/bge-small-en-v1.5",
)
embedder.warm_up()
doc = Document(content="fastembed is supported by and maintained by Qdrant.", meta={"long_answer": "no",})
result = embedder.run(documents=[doc])

You can use FastembedSparseTextEmbedder and FastembedSparseDocumentEmbedder by importing as:

from haystack_integrations.components.embedders.fastembed import FastembedSparseTextEmbedder

text = "fastembed is supported by and maintained by Qdrant."
text_embedder = FastembedSparseTextEmbedder(
    model="prithvida/Splade_PP_en_v1"
)
text_embedder.warm_up()
embedding = text_embedder.run(text)["embedding"]

from haystack_integrations.components.embedders.fastembed import FastembedSparseDocumentEmbedder
from haystack.dataclasses import Document

embedder = FastembedSparseDocumentEmbedder(
    model="prithvida/Splade_PP_en_v1",
)
embedder.warm_up()
doc = Document(content="fastembed is supported by and maintained by Qdrant.", meta={"long_answer": "no",})
result = embedder.run(documents=[doc])

License

fastembed-haystack is distributed under the terms of the Apache-2.0 license.