Getting Started with ActiveloopAI Deep Lake

main.py

# Taken from https://docs.activeloop.ai/quickstart
# !pip3 install deeplake langchain openai tiktoken

from langchain.embeddings.openai import OpenAIEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.document_loaders import TextLoader
from langchain.vectorstores import DeepLake
from langchain.chains import RetrievalQA
from langchain.llms import OpenAIChat
import os

os.environ['OPENAI_API_KEY'] = <OPENAI_API_KEY>

source_text = '<your-txt-file>.txt'
dataset_path = '<dataset-path>'

embedding = OpenAIEmbeddings(model='text-embedding-ada-002')

documents = TextLoader(source_text).load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)

db = DeepLake.from_documents(docs, dataset_path=dataset_path, embedding=embedding)

qa = RetrievalQA.from_chain_type(llm=OpenAIChat(model='gpt-3.5-turbo'), chain_type='stuff', retriever=db.as_retriever())
query = 'A question'
print(qa.run(query))