import gradio as gr
import PyPDF2

from secret1 import GOOGLE_API as google_api
from langchain.llms import GooglePalm
from langchain.embeddings import HuggingFaceInstructEmbeddings
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import GooglePalmEmbeddings
from langchain.vectorstores import FAISS
from langchain.document_loaders import PyPDFLoader
from langchain.chains import RetrievalQA
import google.generativeai as genai
# Define chatbot response function
def chatbot_response(user_input):
    # Example: returning a placeholder response, update with actual chatbot logic
    bot_response = "You said: " + user_input
    # history.append((user_input, bot_response))
    return "hii"

# Define text splitter function
def text_splitter_function(text):
    text_splitter = CharacterTextSplitter(
        separator = '\n',
        chunk_size = 1000,
        chunk_overlap = 40,
        length_function = len,
    )
    texts = text_splitter.split_text(text)
    return texts

# Helper function for text processing
def helper(text_splitter):
    db = FAISS.from_texts(text_splitter, embeddings)  # Use 'embeddings' for FAISS
    return 'hi'

# PDF text extraction function
def text_extract(file):
    pdf_reader = PyPDF2.PdfReader(file.name)
    num_pages = len(pdf_reader.pages)
    text = ""
    for page_num in range(num_pages):
        page = pdf_reader.pages[page_num]
        text += page.extract_text() or ""
    # text_splitter = text_splitter_function(text) 
    # embeddings = GooglePalmEmbeddings(google_api_key=google_api)
    # print(embeddings)
    # db = FAISS.from_texts(text_splitter, embeddings)
    # print(db)
    # retriever = db.as_retriever(search_type="similarity", search_kwargs={"k": 2})
    # llm=GooglePalm(google_api_key=google_api)
    # qa = RetrievalQA.from_chain_type(
    #     llm=llm, chain_type="stuff", retriever=retriever, return_source_documents=True
    # )
    # result1 = qa.invoke(({"how r u"}))
    # print("FitBot:",result1['result'])
    # Split extracted text into chunks
    # result = helper(text_splitter)  # Call helper to process text chunks
    client = genai.Client(api_key="AIzaSyBaY8zx4ak0t4TkBp28lL2hLqREzlN_Mb0",location='us-central1')
    response = client.models.generate_content(
    model="gemini-2.0-flash", contents=f"you will be given the input data you have to answer the question according to the user input : {text}"
)
    return print(response.text)

# Define Gradio interface
with gr.Blocks() as demo:
    gr.Markdown("# Chat with ChatGPT-like Interface")

    output = gr.Textbox(label="Output Box")
    state = gr.State([])

    with gr.Row():
        with gr.Column():
            user_input = gr.Textbox(show_label=False, placeholder="Type your message here...")
            send_btn = gr.Button("Send")
        with gr.Column():
            input_file = gr.File(label="Upload PDF", file_count="single")
            submit_btn = gr.Button("Submit")
    
    # Connect submit button to text_extract function
    submit_btn.click(text_extract, inputs=input_file, outputs=output)

    # Connect send button to chatbot_response function
    send_btn.click(chatbot_response, inputs=user_input, outputs=output)

# Initialize embeddings and launch the app
if __name__ == "__main__":
  # Replace with your actual Google API key
   
    demo.launch()