sie-haystack 0.3.0

SIE integration for Haystack

sie-haystack

SIE integration for Haystack.

Installation

pip install sie-haystack

Imports

Preferred import paths follow Haystack's namespace convention:

from haystack_integrations.components.embedders.sie import (
    SIEDocumentEmbedder,
    SIETextEmbedder,
)
from haystack_integrations.components.rankers.sie import SIERanker
from haystack_integrations.components.extractors.sie import SIEExtractor

The legacy flat imports remain supported for compatibility:

from sie_haystack import SIEDocumentEmbedder, SIEExtractor, SIERanker, SIETextEmbedder

Usage

from haystack import Document
from haystack_integrations.components.embedders.sie import SIEDocumentEmbedder, SIETextEmbedder
from haystack_integrations.components.rankers.sie import SIERanker

# Embed a query
text_embedder = SIETextEmbedder(base_url="http://localhost:8080", model="BAAI/bge-m3")
result = text_embedder.run(text="What is machine learning?")
query_embedding = result["embedding"]

# Embed documents
doc_embedder = SIEDocumentEmbedder(base_url="http://localhost:8080", model="BAAI/bge-m3")
docs = [Document(content="Python is a programming language.")]
result = doc_embedder.run(documents=docs)
embedded_docs = result["documents"]

# Rerank documents
ranker = SIERanker(
    base_url="http://localhost:8080",
    model="jinaai/jina-reranker-v2-base-multilingual"
)
result = ranker.run(query="What is Python?", documents=embedded_docs, top_k=3)
ranked_docs = result["documents"]