Create app.py

app.py

@@ -0,0 +1,101 @@
+import openai
+import gradio as gr
+from langchain.chains import ConversationalChain
+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 langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
+from PyPDF2 import PdfReader
+import os
+
+# Function to load and process the PDF document
+def load_pdf(file):
+    # Load the PDF using PyPDF2 or LangChain's built-in loader
+    loader = PyPDFLoader(file.name)
+    documents = loader.load()
+    return documents
+
+# Summarization function using GPT-4
+def summarize_pdf(file, openai_api_key):
+    # Set the API key dynamically
+    openai.api_key = openai_api_key
+
+    documents = load_pdf(file)
+
+    # Create embeddings for the documents
+    embeddings = OpenAIEmbeddings()
+
+    # Use LangChain's FAISS Vector Store to store and search the embeddings
+    vector_store = FAISS.from_documents(documents, embeddings)
+
+    # Create a conversational chain that allows us to query the document
+    llm = ChatOpenAI(model="gpt-4")  # Using GPT-4 as the LLM
+    conversational_chain = ConversationalChain(
+        llm=llm, 
+        vectorstore=vector_store,
+        verbose=True
+    )
+
+    # Query the model for a summary
+    response = conversational_chain.run("Summarize the content of the research paper.")
+    return response
+
+# Function to handle user queries and provide answers from the document
+def query_pdf(file, user_query, openai_api_key):
+    # Set the API key dynamically
+    openai.api_key = openai_api_key
+
+    documents = load_pdf(file)
+
+    # Create embeddings for the documents
+    embeddings = OpenAIEmbeddings()
+
+    # Use LangChain's FAISS Vector Store to store and search the embeddings
+    vector_store = FAISS.from_documents(documents, embeddings)
+
+    # Create a conversational chain that allows us to query the document
+    llm = ChatOpenAI(model="gpt-4")  # Using GPT-4 as the LLM
+    conversational_chain = ConversationalChain(
+        llm=llm,
+        vectorstore=vector_store,
+        verbose=True
+    )
+
+    # Query the model for the user query
+    response = conversational_chain.run(user_query)
+    return response
+
+# Define Gradio interface for the summarization
+def create_gradio_interface():
+    with gr.Blocks() as demo:
+        gr.Markdown("### ChatPDF and Research Paper Summarizer using GPT-4 and LangChain")
+        
+        # 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")
+
+        with gr.Tab("Summarize PDF"):
+            with gr.Row():
+                pdf_file = gr.File(label="Upload PDF Document")
+                summarize_btn = gr.Button("Summarize")
+                summary_output = gr.Textbox(label="Summary", interactive=False)
+                
+            summarize_btn.click(summarize_pdf, inputs=[pdf_file, openai_api_key_input], outputs=summary_output)
+        
+        with gr.Tab("Ask Questions"):
+            with gr.Row():
+                pdf_file_q = gr.File(label="Upload PDF Document")
+                user_input = gr.Textbox(label="Enter your question")
+                answer_output = gr.Textbox(label="Answer", interactive=False)
+            
+            user_input.submit(query_pdf, inputs=[pdf_file_q, user_input, openai_api_key_input], outputs=answer_output)
+            user_input.submit(None, None, answer_output)  # Clear answer when typing new query
+    
+    return demo
+
+# Run Gradio app
+if __name__ == "__main__":
+    demo = create_gradio_interface()
+    demo.launch(debug=True)