query_data.py

import sys
from dotenv import load_dotenv
import os
from langchain_openai import OpenAIEmbeddings, ChatOpenAI
from langchain_community.vectorstores import Chroma
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_core.prompts import ChatPromptTemplate

load_dotenv()
openai_api_key = os.getenv("OPENAI_API_KEY")

def main():
    if len(sys.argv) < 2:
        print("Please provide a query as a command-line argument.")
        sys.exit(1)
    
    query = sys.argv[1]

    embedding_function = OpenAIEmbeddings(openai_api_key=openai_api_key)
    
    print("Loading Chroma database...")
    vectorstore = Chroma(persist_directory="./chroma_db2", embedding_function=embedding_function)
    
    print(f"Chroma collection name: {vectorstore._collection.name}")
    print(f"Number of documents in Chroma: {vectorstore._collection.count()}")

    retriever = vectorstore.as_retriever()
    model = ChatOpenAI(openai_api_key=openai_api_key)

    template = """Answer the question based only on the following context:
    {context}

    Question: {question}
    """
    prompt = ChatPromptTemplate.from_template(template)

    chain = (
        {"context": retriever, "question": RunnablePassthrough()}
        | prompt
        | model
        | StrOutputParser()
    )

    print("Invoking the chain...")
    response = chain.invoke(query)
    print("Response:", response)

    print("\nRetrieving relevant documents...")
    docs = retriever.invoke(query)
    print(f"Number of retrieved documents: {len(docs)}")
    
    print("\nSources:")
    for i, doc in enumerate(docs, 1):
        print(f"Document {i}:")
        print(f"  Metadata: {doc.metadata}")
        print(f"  Content (first 100 chars): {doc.page_content[:100]}...")
        print()

    if not docs:
        print("No documents were retrieved. This might indicate an issue with the document storage or retrieval process.")

if __name__ == "__main__":
    main()