from langchain.embeddings.openai import OpenAIEmbeddings

from langchain.vectorstores import Chroma

from langchain.llms import OpenAI

from langchain.chains import RetrievalQA

# Set OpenAI API key

import os

os.environ[“OPENAI_API_KEY”] = “YOUR_OPENAI_API_KEY”

# Initialize the embedding model and LLM

embeddings = OpenAIEmbeddings()

llm = OpenAI(temperature=0)

# Load the document and split into chunks

with open(“document.txt”, “r”) as f:

    document = f.read()

chunks = document.split(“\n\n”)  # Split by empty lines

# Generate contextual information for each chunk

contextualized_chunks = []

for chunk in chunks:

    context = llm(f”””

    <document>

    {{Content of the entire document}}

    </document>

    Here is the chunk to be placed within the whole document.

    <chunk>

    {{Content of the chunk}}

    </chunk>

    Please describe a concise context for positioning this chunk within the whole document to improve its searchability. Only provide the concise context.

    “””)

    contextualized_chunks.append(f”{context} {chunk}”)

# Save the chunks with contextual information into a vector database

db = Chroma.from_texts(contextualized_chunks, embeddings)

# Create a RetrievalQA chain

retriever = db.as_retriever()

qa = RetrievalQA.from_chain_type(llm=llm, chain_type=”stuff”, retriever=retriever)

# Input a query and retrieve the answer

query = “What were the company’s Q2 earnings?”

answer = qa.run(query)

# Output the answer

print(answer)