Skip to main content


Atlas is a platform by Nomic made for interacting with both small and internet scale unstructured datasets. It enables anyone to visualize, search, and share massive datasets in their browser.

You'll need to install langchain-community with pip install -qU langchain-community to use this integration

This notebook shows you how to use functionality related to the AtlasDB vectorstore.

%pip install --upgrade --quiet  spacy
!python3 -m spacy download en_core_web_sm
%pip install --upgrade --quiet  nomic

Load Packages

import time

from langchain_community.document_loaders import TextLoader
from langchain_community.vectorstores import AtlasDB
from langchain_text_splitters import SpacyTextSplitter

Prepare the Data

loader = TextLoader("../../how_to/state_of_the_union.txt")
documents = loader.load()
text_splitter = SpacyTextSplitter(separator="|")
texts = []
for doc in text_splitter.split_documents(documents):

texts = [e.strip() for e in texts]

Map the Data using Nomic's Atlas

db = AtlasDB.from_texts(
name="test_index_" + str(time.time()), # unique name for your vector store
description="test_index", # a description for your vector store
index_kwargs={"build_topic_model": True},

Here is a map with the result of this code. This map displays the texts of the State of the Union.

Was this page helpful?

You can leave detailed feedback on GitHub.