app.py

# Continue with the rest of the code
from langchain.chains import RetrievalQA
from langchain.document_loaders import TextLoader
from langchain.embeddings import SentenceTransformerEmbeddings
from langchain.vectorstores import FAISS
from transformers import pipeline



# Paste your data here
data = """
Enter your text data here. For example:
"""

# Split data into chunks for embedding
def chunk_text(text, chunk_size=500):
    words = text.split()
    chunks = [" ".join(words[i:i + chunk_size]) for i in range(0, len(words), chunk_size)]
    return chunks

# Prepare the text chunks
text_chunks = chunk_text(data)

# Generate embeddings and index the data
embeddings = SentenceTransformerEmbeddings(model_name="all-MiniLM-L6-v2")
vectorstore = FAISS.from_texts(text_chunks, embeddings)

# Load a simple LLM (Hugging Face model)
from transformers import pipeline
qa_pipeline = pipeline("question-answering", model="distilbert-base-uncased-distilled-squad")

# Define a function to perform QA
def answer_question(question):
    retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
    relevant_docs = retriever.get_relevant_documents(question)
    context = " ".join([doc.page_content for doc in relevant_docs])
    answer = qa_pipeline(question=question, context=context)
    return answer["answer"]

# Ask a question
print("Paste the text and ask your question.")
question = input("Your question: ")
answer = answer_question(question)
print("Answer:", answer)