#!pip install openai langchain -q

import os 
import openai

openai.api_key = "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"

os.environ["OPENAI_API_KEY"] = openai.api_key 

from IPython.display import display, Markdown

def disp_markdown(text: str) -> None:
  display(Markdown(text))


from langchain.chat_models import ChatOpenAI
from langchain.schema import HumanMessage

chat_model = ChatOpenAI(model_name="gpt-3.5-turbo")

#!wget https://huggingface.co/spaces/JuanKO/question_my_doc/blob/main/thelittleprince.txt

with open("thelittleprince.txt") as f:
    thelittleprince = f.read()

from langchain.text_splitter import CharacterTextSplitter

text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0, separator = ".")
texts = text_splitter.split_text(thelittleprince)

from langchain.embeddings.openai import OpenAIEmbeddings

os.environ["OPENAI_API_KEY"] = openai.api_key

embeddings = OpenAIEmbeddings()

#!pip install tiktoken -q
#!pip install chromadb tiktoken -q

from langchain.vectorstores import Chroma

docsearch = Chroma.from_texts(texts, embeddings, metadatas=[{"source": str(i)} for i in range(len(texts))]).as_retriever() # YOUR CODE HERE



from langchain.chains.question_answering import load_qa_chain
from langchain.llms import OpenAI


query = "Who was the little prince?"
docs = docsearch.get_relevant_documents(query) # YOUR CODE HERE
chain =load_qa_chain(OpenAI(temperature=0), chain_type="stuff")

# run the chain
# YOUR CODE HERE
chain.run(input_documents=docs, question=query)