NvidiaTextEmbedder

This component transforms a string into a vector that captures its semantics using NVIDIA-hosted models.

Most common position in a pipeline	Before an embedding Retriever in a query/RAG pipeline
Mandatory init variables	api_key: API key for the NVIDIA NIM. Can be set with NVIDIA_API_KEY env var.
Mandatory run variables	text: A string
Output variables	embedding: A list of float numbers (vectors) meta: A dictionary of metadata strings
API reference	NVIDIA
GitHub link	https://github.com/deepset-ai/haystack-core-integrations/tree/main/integrations/nvidia
Package name	nvidia-haystack

Overview

NvidiaTextEmbedder embeds a simple string (such as a query) into a vector.

You can use this component with self-hosted models using NVIDIA NIM or models hosted on the NVIDIA API Catalog.

To embed a list of documents, use NvidiaDocumentEmbedder, which enriches each document with the computed embedding.

Usage

To start using NvidiaTextEmbedder, install the nvidia-haystack package:

shell

pip install nvidia-haystack

You can use NvidiaTextEmbedder with all the embedding models available on the NVIDIA API Catalog or with a model deployed using NVIDIA NIM. For more information, refer to NIM for Embedding.

On its own

To use models from the NVIDIA API Catalog, you need to specify the api_url and your API key. You can get your API key from the NVIDIA API Catalog.

NvidiaTextEmbedder uses the NVIDIA_API_KEY environment variable by default. Otherwise, you can pass an API key at initialization with the api_key parameter:

python

from haystack.utils.auth import Secret
from haystack_integrations.components.embedders.nvidia import NvidiaTextEmbedder

embedder = NvidiaTextEmbedder(
    model="nvidia/nv-embedqa-e5-v5",
    api_url="https://integrate.api.nvidia.com/v1",
    api_key=Secret.from_token("<your-api-key>"),
)

result = embedder.run("A transformer is a deep learning architecture")
print(result["embedding"])
print(result["meta"])

To use a locally deployed model, set the api_url to your localhost and set api_key to None:

python

from haystack_integrations.components.embedders.nvidia import NvidiaTextEmbedder

embedder = NvidiaTextEmbedder(
    model="nvidia/nv-embedqa-e5-v5",
    api_url="http://localhost:9999/v1",
    api_key=None,
)

result = embedder.run("A transformer is a deep learning architecture")
print(result["embedding"])
print(result["meta"])

In a pipeline

The following example shows how to use NvidiaTextEmbedder in a RAG pipeline:

python

from haystack import Pipeline, Document
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.components.writers import DocumentWriter
from haystack.components.retrievers.in_memory import InMemoryEmbeddingRetriever
from haystack.utils.auth import Secret
from haystack_integrations.components.embedders.nvidia import (
    NvidiaTextEmbedder,
    NvidiaDocumentEmbedder,
)

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"),
]

indexing_pipeline = Pipeline()
indexing_pipeline.add_component(
    "embedder",
    NvidiaDocumentEmbedder(
        model="nvidia/nv-embedqa-e5-v5",
        api_url="https://integrate.api.nvidia.com/v1",
        api_key=Secret.from_token("<your-api-key>"),
    ),
)
indexing_pipeline.add_component("writer", DocumentWriter(document_store=document_store))
indexing_pipeline.connect("embedder", "writer")

indexing_pipeline.run({"embedder": {"documents": documents}})

query_pipeline = Pipeline()
query_pipeline.add_component(
    "text_embedder",
    NvidiaTextEmbedder(
        model="nvidia/nv-embedqa-e5-v5",
        api_url="https://integrate.api.nvidia.com/v1",
        api_key=Secret.from_token("<your-api-key>"),
    ),
)
query_pipeline.add_component(
    "retriever",
    InMemoryEmbeddingRetriever(document_store=document_store),
)
query_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")

query = "Who lives in Berlin?"

result = query_pipeline.run({"text_embedder": {"text": query}})

print(result["retriever"]["documents"][0])

Related

• Cookbook: Haystack RAG Pipeline with Self-Deployed AI models using NVIDIA NIMs