app.py

# Standard imports
import os
import sys
import warnings

# LangChain community imports (Updated for v0.2+)
from langchain_community.document_loaders import TextLoader, PyPDFLoader, CSVLoader
from langchain_community.embeddings import OpenAIEmbeddings
from langchain_community.vectorstores import FAISS
from langchain_community.llms import OpenAI
from langchain_community.tools import DuckDuckGoSearchRun

# Other imports (you may have these depending on use)
from langchain.chains import RetrievalQA
from langchain.text_splitter import CharacterTextSplitter
from langchain.schema import Document

# Add your environment key for OpenAI if required
os.environ["OPENAI_API_KEY"] = os.getenv("OPENAI_API_KEY", "your-api-key-here")

def load_documents(directory: str):
    """Loads documents from a directory using supported loaders."""
    docs = []
    for filename in os.listdir(directory):
        filepath = os.path.join(directory, filename)
        if filename.endswith(".txt"):
            loader = TextLoader(filepath)
        elif filename.endswith(".pdf"):
            loader = PyPDFLoader(filepath)
        elif filename.endswith(".csv"):
            loader = CSVLoader(filepath)
        else:
            continue
        docs.extend(loader.load())
    return docs

def build_vector_store(docs):
    """Build FAISS index from documents using OpenAI embeddings."""
    embeddings = OpenAIEmbeddings()
    return FAISS.from_documents(docs, embeddings)

def build_qa_chain(vectorstore):
    """Create a RetrievalQA chain from the vector store."""
    retriever = vectorstore.as_retriever()
    llm = OpenAI(temperature=0)
    return RetrievalQA.from_chain_type(llm=llm, retriever=retriever)

def main():
    # Load and process data
    data_path = "data/"  # Change to your actual directory
    print("[INFO] Loading documents...")
    documents = load_documents(data_path)

    print("[INFO] Splitting text...")
    splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
    split_docs = splitter.split_documents(documents)

    print("[INFO] Creating vector store...")
    vectorstore = build_vector_store(split_docs)

    print("[INFO] Building QA chain...")
    qa_chain = build_qa_chain(vectorstore)

    print("\n[READY] Ask questions (type 'exit' to quit):\n")
    while True:
        question = input("Q: ")
        if question.lower() in ["exit", "quit"]:
            print("Goodbye!")
            break
        answer = qa_chain.run(question)
        print("A:", answer)

# Main entry point
if __name__ == "__main__":
    warnings.filterwarnings("ignore", category=DeprecationWarning)
    main()