Text embedding models

info

Head to Integrations for documentation on built-in integrations with text embedding model providers.

The Embeddings class is a class designed for interfacing with text embedding models. There are lots of embedding model providers (OpenAI, Cohere, Hugging Face, etc) - this class is designed to provide a standard interface for all of them.

Embeddings create a vector representation of a piece of text. This is useful because it means we can think about text in the vector space, and do things like semantic search where we look for pieces of text that are most similar in the vector space.

The base Embeddings class in LangChain provides two methods: one for embedding documents and one for embedding a query. The former, .embed_documents, takes as input multiple texts, while the latter, .embed_query, takes a single text. The reason for having these as two separate methods is that some embedding providers have different embedding methods for documents (to be searched over) vs queries (the search query itself). .embed_query will return a list of floats, whereas .embed_documents returns a list of lists of floats.

Get started

Setup

OpenAI

pip install -qU langchain-openai

import getpass

os.environ["OPENAI_API_KEY"] = getpass.getpass()

from langchain_openai import OpenAIEmbeddings

embeddings_model = OpenAIEmbeddings(model="text-embedding-3-large")

Azure

pip install -qU langchain-openai

import getpass

os.environ["AZURE_OPENAI_API_KEY"] = getpass.getpass()

from langchain_openai import AzureOpenAIEmbeddings

embeddings_model = AzureOpenAIEmbeddings(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
)

Google

pip install -qU langchain-google-vertexai

from langchain_google_vertexai import VertexAIEmbeddings

embeddings_model = VertexAIEmbeddings(model="text-embedding-004")

AWS

pip install -qU langchain-aws

from langchain_aws import BedrockEmbeddings

embeddings_model = BedrockEmbeddings(model_id="amazon.titan-embed-text-v2:0")

HuggingFace

pip install -qU langchain-huggingface

from langchain_huggingface import HuggingFaceEmbeddings

embeddings_model = HuggingFaceEmbeddings(model="sentence-transformers/all-mpnet-base-v2")

Ollama

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings_model = OllamaEmbeddings(model="llama3")

Cohere

pip install -qU langchain-cohere

import getpass

os.environ["COHERE_API_KEY"] = getpass.getpass()

from langchain_cohere import CohereEmbeddings

embeddings_model = CohereEmbeddings(model="embed-english-v3.0")

MistralAI

pip install -qU langchain-mistralai

import getpass

os.environ["MISTRALAI_API_KEY"] = getpass.getpass()

from langchain_mistralai import MistralAIEmbeddings

embeddings_model = MistralAIEmbeddings(model="mistral-embed")

Nomic

pip install -qU langchain-nomic

import getpass

os.environ["NOMIC_API_KEY"] = getpass.getpass()

from langchain_nomic import NomicEmbeddings

embeddings_model = NomicEmbeddings(model="nomic-embed-text-v1.5")

NVIDIA

pip install -qU langchain-nvidia-ai-endpoints

import getpass

os.environ["NVIDIA_API_KEY"] = getpass.getpass()

from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings

embeddings_model = NVIDIAEmbeddings(model="NV-Embed-QA")

Fake

pip install -qU langchain-core

from langchain_core.embeddings import DeterministicFakeEmbedding

embeddings_model = DeterministicFakeEmbedding(size=4096)

embed_documents

Embed list of texts

Use .embed_documents to embed a list of strings, recovering a list of embeddings:

embeddings = embeddings_model.embed_documents(
    [
        "Hi there!",
        "Oh, hello!",
        "What's your name?",
        "My friends call me World",
        "Hello World!"
    ]
)
len(embeddings), len(embeddings[0])

(5, 1536)

embed_query

Embed single query

Use .embed_query to embed a single piece of text (e.g., for the purpose of comparing to other embedded pieces of texts).

embedded_query = embeddings_model.embed_query("What was the name mentioned in the conversation?")
embedded_query[:5]

[0.0053587136790156364,
 -0.0004999046213924885,
 0.038883671164512634,
 -0.003001077566295862,
 -0.00900818221271038]