OpenAIEmbeddings integration | LangChain 简体中文

This will help you get started with OpenAI embedding models using LangChain. For detailed documentation on OpenAIEmbeddings features and configuration options, please refer to the API reference.

Overview

Integration details

Setup

To access OpenAI embedding models you'll need to create an OpenAI account, get an API key, and install the langchain-openai integration package.

Credentials

Head to platform.openai.com to sign up to OpenAI and generate an API key. Once you’ve done this set the OPENAI_API_KEY environment variable:

import getpass
import os

if not os.getenv("OPENAI_API_KEY"):
    os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter your OpenAI API key: ")

If you're routing requests through a proxy or service emulator, you can set the base URL via env var instead of passing base_url. Resolution order (first match wins):

Explicit base_url (or openai_api_base) kwarg.
OPENAI_API_BASE — read by LangChain at init.
OPENAI_BASE_URL — read by the underlying openai SDK client.

To enable automated tracing of your model calls, set your LangSmith API key:

os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")

Installation

The LangChain OpenAI integration lives in the langchain-openai package:

pip install -qU langchain-openai

Instantiation

Now we can instantiate our model object and generate chat completions:

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-large",
    # With the `text-embedding-3` class
    # of models, you can specify the size
    # of the embeddings you want returned.
    # dimensions=1024
)

Info

Azure OpenAI v1 API support

As of langchain-openai>=1.0.1, OpenAIEmbeddings can be used directly with Azure OpenAI endpoints using the new v1 API, including support for Microsoft Entra ID authentication. See the Using with Azure OpenAI section below for details.

Indexing and retrieval

Embedding models are often used in retrieval-augmented generation (RAG) flows, both as part of indexing data as well as later retrieving it. For more detailed instructions, please see our RAG tutorials.

Below, see how to index and retrieve data using the embeddings object we initialized above. In this example, we will index and retrieve a sample document in the InMemoryVectorStore.

# Create a vector store with a sample text
from langchain_core.vectorstores import InMemoryVectorStore

text = "LangChain is the framework for building context-aware reasoning applications"

vectorstore = InMemoryVectorStore.from_texts(
    [text],
    embedding=embeddings,
)

# Use the vectorstore as a retriever
retriever = vectorstore.as_retriever()

# Retrieve the most similar text
retrieved_documents = retriever.invoke("What is LangChain?")

# show the retrieved document's content
retrieved_documents[0].page_content

'LangChain is the framework for building context-aware reasoning applications'

Direct usage

Under the hood, the vectorstore and retriever implementations are calling embeddings.embed_documents(...) and embeddings.embed_query(...) to create embeddings for the text(s) used in from_texts and retrieval invoke operations, respectively.

You can directly call these methods to get embeddings for your own use cases.

Embed single texts

You can embed single texts or documents with embed_query:

single_vector = embeddings.embed_query(text)
print(str(single_vector)[:100])  # Show the first 100 characters of the vector

[-0.019276829436421394, 0.0037708976306021214, -0.03294256329536438, 0.0037671267054975033, 0.008175

Embed multiple texts

You can embed multiple texts with embed_documents:

text2 = (
    "LangGraph is a library for building stateful, multi-actor applications with LLMs"
)
two_vectors = embeddings.embed_documents([text, text2])
for vector in two_vectors:
    print(str(vector)[:100])  # Show the first 100 characters of the vector

[-0.019260549917817116, 0.0037612367887049913, -0.03291035071015358, 0.003757466096431017, 0.0082049
[-0.010181212797760963, 0.023419594392180443, -0.04215526953339577, -0.001532090245746076, -0.023573

Using with Azure OpenAI

Info

Azure OpenAI v1 API support

As of langchain-openai>=1.0.1, OpenAIEmbeddings can be used directly with Azure OpenAI endpoints using the new v1 API. This provides a unified way to use OpenAI embeddings whether hosted on OpenAI or Azure.

For the traditional Azure-specific implementation, continue to use AzureOpenAIEmbeddings.

Using Azure OpenAI v1 API with API Key

To use OpenAIEmbeddings with Azure OpenAI, set the base_url to your Azure endpoint with /openai/v1/ appended:

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-large",  # Your Azure deployment name
    base_url="https://{your-resource-name}.openai.azure.com/openai/v1/",
    api_key="your-azure-api-key"
)

# Use as normal
vector = embeddings.embed_query("Hello world")

Using Azure OpenAI with Microsoft entra ID

The v1 API adds native support for Microsoft Entra ID authentication with automatic token refresh. Pass a token provider callable to the api_key parameter:

from azure.identity import DefaultAzureCredential, get_bearer_token_provider
from langchain_openai import OpenAIEmbeddings

# Create a token provider that handles automatic refresh
token_provider = get_bearer_token_provider(
    DefaultAzureCredential(),
    "https://cognitiveservices.azure.com/.default"
)

embeddings = OpenAIEmbeddings(
    model="text-embedding-3-large",  # Your Azure deployment name
    base_url="https://{your-resource-name}.openai.azure.com/openai/v1/",
    api_key=token_provider  # Callable that handles token refresh
)

# Use as normal
vectors = embeddings.embed_documents(["Hello", "World"])

Tip

Installation requirements

To use Microsoft Entra ID authentication, install the Azure Identity library:

pip install azure-identity

You can also pass a token provider callable to the api_key parameter when using asynchronous functions. You must import DefaultAzureCredential from azure.identity.aio:

from azure.identity.aio import DefaultAzureCredential
from langchain_openai import OpenAIEmbeddings

credential = DefaultAzureCredential()

embeddings_async = OpenAIEmbeddings(
    model="text-embedding-3-large",
    api_key=credential
)

# Use async methods when using async callable
vectors = await embeddings_async.aembed_documents(["Hello", "World"])

Note

When using an async callable for the API key, you must use async methods (aembed_query, aembed_documents). Sync methods will raise an error.

API reference

For detailed documentation on OpenAIEmbeddings features and configuration options, please refer to the API reference.