Skip to content

nvidiatextembedder.mdx

Latest commit

 

History

History
141 lines (105 loc) · 4.98 KB

nvidiatextembedder.mdx

File metadata and controls

141 lines (105 loc) · 4.98 KB
title NvidiaTextEmbedder
id nvidiatextembedder
slug /nvidiatextembedder
description This component transforms a string into a vector that captures its semantics using NVIDIA-hosted models.

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

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:

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 Deploying Text Embedding Models.

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:

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:

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:

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