BasetenEmbeddings integration

This will help you get started with Baseten embedding models using LangChain.

Overview

Baseten provides inference designed for production applications. Built on the Baseten Inference Stack, these APIs deliver enterprise-grade performance and reliability for leading open-source or custom models: https://www.baseten.co/library/.

Integration details

Setup

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

Baseten embeddings are only available as dedicated models. You must deploy an embedding model from the Baseten model library before using this integration.

The embeddings functionality uses Baseten's Performance Client for optimized performance, which is automatically included as a dependency.

Credentials

Head to https://app.baseten.co to sign up to Baseten and generate an API key. Once you've done this set the BASETEN_API_KEY environment variable:

import getpass
import os

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

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 Baseten integration lives in the langchain-baseten package:

pip install -qU langchain-baseten

Instantiation

Now we can instantiate our embeddings object using your deployed model's URL:

from langchain_baseten import BasetenEmbeddings

embeddings = BasetenEmbeddings(
    model_url="https://model-<id>.api.baseten.co/environments/production/sync",  # Your model URL
    api_key="your-api-key",  # Or set BASETEN_API_KEY env var
)

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

[0.013201533816754818, 0.02222288027405739, -0.036066457629203796, 0.027374643832445145, -0.01692997

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

[0.013201533816754818, 0.02222288027405739, -0.036066457629203796, 0.027374643832445145, -0.01692997
[0.018247194588184357, 0.007369577884674072, -0.005529594141989946, 0.022589316591620445, -0.0699259