Atlas

%pip install -qU  spacy

!python3 -m spacy download en_core_web_sm

%pip install -qU  nomic

import time

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

ATLAS_TEST_API_KEY = "7xDPkYXSYDc1_ErdTPIcoAR9RNd8YDlkS3nVNXcVoIMZ6"

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.extend(doc.page_content.split("|"))

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

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

db.project.wait_for_project_lock()

db.project