from langchain.embeddings.sentence_transformer import SentenceTransformerEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.document_loaders import TextLoader

# load the document and split it into chunks
loader = TextLoader("")
documents = loader.load()
len(documents)
print(documents[0])

# split it into chunks
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
len(docs)
print(docs[0])


# create the open-source embedding function
embedding_function = HuggingFaceEmbeddings

# load it into Chroma
db = Chroma.from_documents(docs, embedding_function, persist_directory="./chroma_db")

# query it
#query = "Question"
#docs = db.similarity_search(query)

# print results
print(docs[0].page_content)

docs = db2.similarity_search(query)