由 deepset 维护
集成：FastEmbed
使用 FastEmbed 嵌入模型
作者
deepset
Nicola Procopio
目录
概述
FastEmbed 是一个轻量级、快速的 Python 库，专为嵌入生成和文档排序而构建。
- 轻巧快速：量化模型权重；通过 Optimum 使用 ONNX Runtime 进行推理。
- 高性能嵌入模型：支持的模型列表 - 包括多语言模型。
- 支持稀疏嵌入模型。
- 与 Qdrant 文档存储和检索器良好集成。
安装
pip install fastembed-haystack
使用
组件
fastembed-haystack 集成提供了以下组件
- 嵌入器
FastembedTextEmbedder：为文本创建密集嵌入（用于查询/RAG 管道）。FastembedDocumentEmbedder：使用密集嵌入丰富文档（用于索引管道）。FastembedSparseTextEmbedder：为文本创建稀疏嵌入（用于查询/RAG 管道）。FastembedSparseDocumentEmbedder：使用稀疏嵌入丰富文档（用于索引管道）。
- Ranker
FastembedRanker：根据查询对文档进行排序（用于检索后的查询/RAG 管道）。
密集嵌入示例
from haystack import Document, Pipeline
from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack_integrations.components.embedders.fastembed import FastembedDocumentEmbedder, FastembedTextEmbedder
document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
documents = [
Document(content="My name is Wolfgang and I live in Berlin"),
Document(content="I saw a black horse running"),
Document(content="Germany has many big cities"),
Document(content="fastembed is supported by and maintained by Qdrant."),
]
document_embedder = FastembedDocumentEmbedder()
document_embedder.warm_up()
documents_with_embeddings = document_embedder.run(documents)["documents"]
document_store.write_documents(documents_with_embeddings)
query_pipeline = Pipeline()
query_pipeline.add_component("text_embedder", FastembedTextEmbedder())
query_pipeline.add_component("retriever", InMemoryEmbeddingRetriever(document_store=document_store))
query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
query = "Who supports fastembed?"
result = query_pipeline.run({"text_embedder": {"text": query}})
有关更详细的示例，请参阅此笔记本。
稀疏嵌入示例
目前，稀疏嵌入检索仅受 QdrantDocumentStore 支持。您可以按如下方式安装该包
pip install qdrant-haystack
from haystack import Document, Pipeline
from haystack_integrations.components.retrievers.qdrant import QdrantSparseEmbeddingRetriever
from haystack_integrations.document_stores.qdrant import QdrantDocumentStore
from haystack_integrations.components.embedders.fastembed import FastembedDocumentEmbedder, FastembedTextEmbedder
document_store = QdrantDocumentStore(
":memory:",
recreate_index=True,
use_sparse_embeddings=True
)
documents = [
Document(content="My name is Wolfgang and I live in Berlin"),
Document(content="I saw a black horse running"),
Document(content="Germany has many big cities"),
Document(content="fastembed is supported by and maintained by Qdrant."),
]
sparse_document_embedder = FastembedSparseDocumentEmbedder()
sparse_document_embedder.warm_up()
documents_with_sparse_embeddings = sparse_document_embedder.run(documents)["documents"]
document_store.write_documents(documents_with_sparse_embeddings)
query_pipeline = Pipeline()
query_pipeline.add_component("sparse_text_embedder", FastembedSparseTextEmbedder())
query_pipeline.add_component("sparse_retriever", QdrantSparseEmbeddingRetriever(document_store=document_store))
query_pipeline.connect("sparse_text_embedder.sparse_embedding", "retriever.query_sparse_embedding")
query = "Who supports fastembed?"
result = query_pipeline.run({"sparse_text_embedder": {"text": query}})
有关更详细的示例，请参阅此笔记本。
Ranker 示例
from haystack import Document, Pipeline
from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack_integrations.components.embedders.fastembed import FastembedDocumentEmbedder, FastembedTextEmbedder
from haystack_integrations.components.rankers.fastembed import FastembedRanker
document_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
query = "Who supports fastembed?"
documents = [
Document(content="My name is Wolfgang and I live in Berlin"),
Document(content="I saw a black horse running"),
Document(content="Germany has many big cities"),
Document(content="fastembed is supported by and maintained by Qdrant."),
]
document_embedder = FastembedDocumentEmbedder()
document_embedder.warm_up()
documents_with_embeddings = document_embedder.run(documents)["documents"]
document_store.write_documents(documents_with_embeddings)
query_pipeline = Pipeline()
query_pipeline.add_component("text_embedder", FastembedTextEmbedder())
query_pipeline.add_component("retriever", InMemoryEmbeddingRetriever(document_store=document_store))
query_pipeline.add_component("ranker", FastembedRanker(top_k=2))
query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
query_pipeline.connect("retriever.documents", "ranker.documents")
result = query_pipeline.run({"text_embedder": {"text": query}, "ranker": { "query" : query }})
许可证
fastembed-haystack 在 Apache-2.0 许可证的条款下分发。