Update app.py

app.py

@@ -1,45 +1,37 @@
 import gradio as gr
-import fitz  # PyMuPDF
+from PyPDF2 import PdfReader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-import os
 from langchain_google_genai import GoogleGenerativeAIEmbeddings
 import google.generativeai as genai
 from langchain.vectorstores import FAISS
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain.chains.question_answering import load_qa_chain
 from langchain.prompts import PromptTemplate
-from dotenv import load_dotenv
-
-# Load environment variables from .env file
-load_dotenv()
+import os
 
-# Configure the Google Generative AI
+# Set up environment variables
+os.environ["GOOGLE_API_KEY"] = "your_google_api_key_here"
 genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
 
-def get_pdf_text(pdf_docs):
-    """Extracts text from PDF files."""
+def get_pdf_text(pdf_files):
     text = ""
-    for pdf in pdf_docs:
-        pdf_reader = fitz.open(pdf.name)
-        for page in pdf_reader:
-            text += page.get_text()
-        pdf_reader.close()
+    for pdf in pdf_files:
+        pdf_reader = PdfReader(pdf)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
     return text
 
 def get_text_chunks(text):
-    """Splits the extracted text into chunks."""
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
     chunks = text_splitter.split_text(text)
     return chunks
 
 def get_vector_store(text_chunks):
-    """Creates and saves a FAISS vector store from text chunks."""
     embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
     vector_store = FAISS.from_texts(text_chunks, embedding=embeddings)
     vector_store.save_local("faiss_index")
 
 def get_conversational_chain():
-    """Returns a conversational chain with a prompt template."""
     prompt_template = """
     Answer the question as detailed as possible from the provided context, make sure to provide all the details, if the answer is not in
     provided context just say, "answer is not available in the context", don't provide the wrong answer\n\n
@@ -52,41 +44,43 @@ def get_conversational_chain():
     model = ChatGoogleGenerativeAI(model="gemini-pro", temperature=0.3)
     prompt = PromptTemplate(template=prompt_template, input_variables=["context", "question"])
     chain = load_qa_chain(model, chain_type="stuff", prompt=prompt)
-
     return chain
 
-def user_input(user_question, pdf_docs):
-    """Processes user input and returns a response."""
-    raw_text = get_pdf_text(pdf_docs)
+def process_pdf(pdf_files, user_question):
+    raw_text = get_pdf_text(pdf_files)
     text_chunks = get_text_chunks(raw_text)
     get_vector_store(text_chunks)
     
     embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
     new_db = FAISS.load_local("faiss_index", embeddings)
     docs = new_db.similarity_search(user_question)
-    
+
     chain = get_conversational_chain()
     response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
     
     return response["output_text"]
 
 def main():
-    """Main function to run the Gradio app."""
-    with gr.Blocks() as demo:
-        gr.Markdown("# Chat with PDF using Gemini💁")
+    with gr.Blocks() as app:
+        gr.Markdown("## Chat with PDF using Gemini 💁")
         
         with gr.Row():
             with gr.Column():
-                pdf_upload = gr.File(label="Upload PDF Files", type="file", file_count="multiple")
-                question_input = gr.Textbox(label="Ask a Question from the PDF Files")
+                pdf_files = gr.File(label="Upload your PDF Files", file_count="multiple", type="file")
+                user_question = gr.Textbox(label="Ask a Question from the PDF Files")
                 submit_button = gr.Button("Submit & Process")
-                
+            
             with gr.Column():
-                output_text = gr.Textbox(label="Reply", interactive=False)
+                output_text = gr.Textbox(label="Reply", lines=10)
+        
+        def update_output(files, question):
+            if files and question:
+                return process_pdf(files, question)
+            return "Please upload PDFs and ask a question."
         
-        submit_button.click(fn=user_input, inputs=[question_input, pdf_upload], outputs=output_text)
+        submit_button.click(fn=update_output, inputs=[pdf_files, user_question], outputs=output_text)
     
-    demo.launch()
+    app.launch()
 
 if __name__ == "__main__":
     main()