Skip to main content


SambaNova's Sambastudio is a platform for running your own open-source models

This example goes over how to use LangChain to interact with SambaNova embedding models


SambaStudio allows you to train, run batch inference jobs, and deploy online inference endpoints to run open source models that you fine tuned yourself.

A SambaStudio environment is required to deploy a model. Get more information at

Register your environment variables:

import os

sambastudio_base_url = "<Your SambaStudio environment URL>"
sambastudio_project_id = "<Your SambaStudio project id>"
sambastudio_endpoint_id = "<Your SambaStudio endpoint id>"
sambastudio_api_key = "<Your SambaStudio endpoint API key>"

# Set the environment variables
os.environ["SAMBASTUDIO_EMBEDDINGS_BASE_URL"] = sambastudio_base_url
os.environ["SAMBASTUDIO_EMBEDDINGS_PROJECT_ID"] = sambastudio_project_id
os.environ["SAMBASTUDIO_EMBEDDINGS_ENDPOINT_ID"] = sambastudio_endpoint_id
os.environ["SAMBASTUDIO_EMBEDDINGS_API_KEY"] = sambastudio_api_key

Call SambaStudio hosted embeddings directly from LangChain!

from langchain_community.embeddings.sambanova import SambaStudioEmbeddings

embeddings = SambaStudioEmbeddings()

text = "Hello, this is a test"
result = embeddings.embed_query(text)

texts = ["Hello, this is a test", "Hello, this is another test"]
results = embeddings.embed_documents(texts)

API Reference:

Help us out by providing feedback on this documentation page: