Update app.py

app.py

@@ -1,110 +1,35 @@
-import openai
 import gradio as gr
-from langchain.chains import RetrievalQA
-from langchain.llms import OpenAI
 from langchain.document_loaders import PyPDFLoader
 from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.chat_models import ChatOpenAI
-from PyPDF2 import PdfReader
+from langchain.llms import OpenAI
 
-# Function to load and process multiple PDFs
-def load_pdfs(files):
-    documents = []
+def process_pdfs(files):
+    """Process uploaded PDFs and return extracted text."""
+    texts = []
     for file in files:
         loader = PyPDFLoader(file.name)
-        documents.extend(loader.load())  # Append documents from each file
-    return documents
-
-# Summarization function using GPT-4 for multiple PDFs
-def summarize_pdfs(files, openai_api_key):
-    openai.api_key = openai_api_key  # Set OpenAI API key
-
-    # Load and process the PDFs
-    documents = load_pdfs(files)
-
-    # Create embeddings for the documents
-    embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
-
-    # Use Langchain's FAISS Vector Store to store and search the embeddings
-    vector_store = FAISS.from_documents(documents, embeddings)
-
-    # Create a RetrievalQA chain for summarization
-    llm = ChatOpenAI(model='gpt-4o', openai_api_key=openai_api_key)
-    qa_chain = RetrievalQA.from_chain_type(
-        llm=llm,
-        chain_type="stuff",
-        retriever=vector_store.as_retriever()
-    )
-
-    # Query the model for a summary of all PDFs
-    response = qa_chain.run("Summarize the content of the research papers.")
-    return response
-
-# Function to handle user queries for multiple PDFs
-def query_pdfs(files, user_query, openai_api_key):
-    openai.api_key = openai_api_key  # Set OpenAI API key
+        docs = loader.load()
+        texts.append("\n".join([doc.page_content for doc in docs]))
+    return "\n\n".join(texts)
 
-    # Load and process the PDFs
-    documents = load_pdfs(files)
-
-    # Create embeddings for the documents
-    embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)
-
-    # Use LangChain's FAISS Vector Store to store and search the embeddings
-    vector_store = FAISS.from_documents(documents, embeddings)
-
-    # Create a RetrievalQA chain for querying the documents
-    llm = ChatOpenAI(model="gpt-4o", openai_api_key=openai_api_key)
-    qa_chain = RetrievalQA.from_chain_type(
-        llm=llm,
-        chain_type="stuff",
-        retriever=vector_store.as_retriever()
-    )
-
-    # Query the model for the user query
-    response = qa_chain.run(user_query)
-    return response
-
-# Define Gradio interface for handling multiple PDFs
 def create_gradio_interface():
+    """Create and launch the Gradio interface."""
     with gr.Blocks() as demo:
-        gr.Markdown("### Multi-PDF Chat and Research Paper Summarizer using GPT-4 and LangChain")
+        gr.Markdown("# PDF Text Extractor")
 
-        # Input field for API Key
-        with gr.Row():
-            openai_api_key_input = gr.Textbox(label="Enter OpenAI API Key", type="password", placeholder="Enter your OpenAI API key here")
+        pdf_files = gr.Files(label="Upload PDF Documents", type="file")  # Fixed multiple file issue
 
-        with gr.Tab("Summarize PDFs"):
-            with gr.Row():
-                pdf_files = gr.File(label="Upload PDF Documents", file_types=[".pdf"])
-                summarize_btn = gr.Button("Summarize")
-                summary_output = gr.Textbox(label="Summary", interactive=False)
-                clear_btn_summary = gr.Button("Clear Response")
+        output_text = gr.Textbox(label="Extracted Text", lines=10)
 
-            # Summarize Button Logic
-            summarize_btn.click(summarize_pdfs, inputs=[pdf_files, openai_api_key_input], outputs=summary_output)
+        extract_button = gr.Button("Extract Text")
 
-            # Clear Response Button Logic for Summary Tab
-            clear_btn_summary.click(lambda: "", inputs=[], outputs=summary_output)
-
-        with gr.Tab("Ask Questions"):
-            with gr.Row():
-                pdf_files_q = gr.File(label="Upload PDF Documents", file_types=[".pdf"], multiple=True)
-                user_input = gr.Textbox(label="Enter your question")
-                answer_output = gr.Textbox(label="Answer", interactive=False)
-                query_btn = gr.Button("Ask")
-                clear_btn_answer = gr.Button("Clear Response")
-
-            # Submit Question Logic
-            query_btn.click(query_pdfs, inputs=[pdf_files_q, user_input, openai_api_key_input], outputs=answer_output)
-
-            # Clear Response Button Logic for Answer Tab
-            clear_btn_answer.click(lambda: "", inputs=[], outputs=answer_output)
+        extract_button.click(process_pdfs, inputs=[pdf_files], outputs=[output_text])
 
     return demo
 
-# Run Gradio app
 if __name__ == "__main__":
     demo = create_gradio_interface()
-    demo.launch(debug=True)
+    demo.launch()
+