Integration: Voyage AI

A component for computing embeddings using Voyage AI embedding models - built for Haystack 2.0.

Ashwin Mathur

PyPI PyPI - Python Version

Table of Contents

Custom component for Haystack (2.x) for creating embeddings using the VoyageAI Embedding Models.

Voyage’s embedding models, such as voyage-2 and voyage-large-2, are state-of-the-art in retrieval accuracy. These models outperform top performing embedding models like intfloat/e5-mistral-7b-instruct and OpenAI/text-embedding-3-large on the MTEB Benchmark. voyage-2 is current ranked second on the MTEB Leaderboard.

The available models can be found on the Embeddings Documentation.


pip install voyage-embedders-haystack


You can use Voyage Embedding models with two components: VoyageTextEmbedder and VoyageDocumentEmbedder.

To create semantic embeddings for documents, use VoyageDocumentEmbedder in your indexing pipeline. For generating embeddings for queries, use VoyageTextEmbedder.

Once you’ve selected the suitable component for your specific use case, initialize the component with the model name and VoyageAI API key. You can also set the environment variable VOYAGE_API_KEY instead of passing the API key as an argument.

Information about the supported models, can be found on the Embeddings Documentation.

To get an API key, please see the Voyage AI website.


Below is the example Semantic Search pipeline that uses the Simple Wikipedia Dataset from HuggingFace. You can find more examples in the examples folder.

Load the dataset:

# Install HuggingFace Datasets using "pip install datasets"
from datasets import load_dataset
from haystack import Pipeline
from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
from haystack.components.writers import DocumentWriter
from haystack.dataclasses import Document
from haystack.document_stores.in_memory import InMemoryDocumentStore

# Import Voyage Embedders
from haystack_integrations.components.embedders.voyage_embedders import VoyageDocumentEmbedder, VoyageTextEmbedder

# Load first 100 rows of the Simple Wikipedia Dataset from HuggingFace
dataset = load_dataset("pszemraj/simple_wikipedia", split="validation[:100]")

docs = [
            "title": doc["title"],
            "url": doc["url"],
    for doc in dataset

Index the documents to the InMemoryDocumentStore using the VoyageDocumentEmbedder and DocumentWriter:

doc_store = InMemoryDocumentStore(embedding_similarity_function="cosine")
retriever = InMemoryEmbeddingRetriever(document_store=doc_store)
doc_writer = DocumentWriter(document_store=doc_store)

doc_embedder = VoyageDocumentEmbedder(
text_embedder = VoyageTextEmbedder(model="voyage-law-2", input_type="query")

# Indexing Pipeline
indexing_pipeline = Pipeline()
indexing_pipeline.add_component(instance=doc_embedder, name="DocEmbedder")
indexing_pipeline.add_component(instance=doc_writer, name="DocWriter")
indexing_pipeline.connect("DocEmbedder", "DocWriter"){"DocEmbedder": {"documents": docs}})

print(f"Number of documents in Document Store: {len(doc_store.filter_documents())}")
print(f"First Document: {doc_store.filter_documents()[0]}")
print(f"Embedding of first Document: {doc_store.filter_documents()[0].embedding}")

Query the Semantic Search Pipeline using the InMemoryEmbeddingRetriever and VoyageTextEmbedder:

text_embedder = VoyageTextEmbedder(model="voyage-law-2", input_type="query")

# Query Pipeline
query_pipeline = Pipeline()
query_pipeline.add_component(instance=text_embedder, name="TextEmbedder")
query_pipeline.add_component(instance=retriever, name="Retriever")
query_pipeline.connect("TextEmbedder.embedding", "Retriever.query_embedding")

# Search
results ={"TextEmbedder": {"text": "Which year did the Joker movie release?"}})

# Print text from top result
top_result = results["Retriever"]["documents"][0].content
print("The top search result is:")


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