Update app.py

app.py

@@ -1,106 +1,76 @@
-import gradio as gr
 import os
-import time
-import spaces
-from langchain_community.document_loaders import OnlinePDFLoader
-
-from langchain.text_splitter import CharacterTextSplitter
-
-
-from langchain_community.llms import OpenAI
-
-from langchain_community.embeddings import OpenAIEmbeddings
-from langchain_community.vectorstores import Chroma
-
-
-
+import gradio as gr
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
 from langchain.chains import ConversationalRetrievalChain
-@spaces.GPU
-def loading_pdf():
-    return "Loading..."
-
-def pdf_changes(pdf_doc, open_ai_key):
-    if openai_key is not None:
-        os.environ['OPENAI_API_KEY'] = open_ai_key
-        loader = OnlinePDFLoader(pdf_doc.name)
-        documents = loader.load()
-        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-        texts = text_splitter.split_documents(documents)
-        embeddings = OpenAIEmbeddings()
-        db = Chroma.from_documents(texts, embeddings)
-        retriever = db.as_retriever()
-        global qa 
-        qa = ConversationalRetrievalChain.from_llm(
-            llm=OpenAI(temperature=0.5), 
-            retriever=retriever, 
-            return_source_documents=False)
-        return "Ready"
-    else:
-        return "You forgot OpenAI API key"
+from langchain.chat_models import ChatOpenAI
+from langchain.memory import ConversationBufferMemory
 
-def add_text(history, text):
-    history = history + [(text, None)]
-    return history, ""
 
-def bot(history):
-    response = infer(history[-1][0], history)
-    history[-1][1] = ""
-    
-    for character in response:     
-        history[-1][1] += character
-        time.sleep(0.05)
-        yield history
-    
+class AdvancedPdfChatbot:
+    def __init__(self, openai_api_key):
+        os.environ["OPENAI_API_KEY"] = openai_api_key
+        self.embeddings = OpenAIEmbeddings()
+        self.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+        self.llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo")
+        self.memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+        self.qa_chain = None
 
-def infer(question, history):
-    
-    res = []
-    for human, ai in history[:-1]:
-        pair = (human, ai)
-        res.append(pair)
+    def load_and_process_pdf(self, pdf_path):
+        loader = PyPDFLoader(pdf_path)
+        documents = loader.load()
+        texts = self.text_splitter.split_documents(documents)
+        self.db = FAISS.from_documents(texts, self.embeddings)
+        self.setup_conversation_chain()
+
+    def setup_conversation_chain(self):
+        self.qa_chain = ConversationalRetrievalChain.from_llm(
+            self.llm,
+            retriever=self.db.as_retriever(),
+            memory=self.memory
+        )
+
+    def chat(self, query):
+        if not self.qa_chain:
+            return "Please upload a PDF first."
+        result = self.qa_chain({"question": query})
+        return result['answer']
+
+# Initialize the chatbot
+openai_api_key = "your-openai-api-key-here"
+pdf_chatbot = AdvancedPdfChatbot(openai_api_key)
+
+def upload_pdf(pdf_file):
+    if pdf_file is None:
+        return "Please upload a PDF file."
+    file_path = pdf_file.name
+    pdf_chatbot.load_and_process_pdf(file_path)
+    return "PDF uploaded and processed successfully. You can now start chatting!"
+
+def respond(message, history):
+    bot_message = pdf_chatbot.chat(message)
+    history.append((message, bot_message))
+    return "", history
+
+# Create the Gradio interface
+with gr.Blocks() as demo:
+    gr.Markdown("# PDF Chatbot")
     
-    chat_history = res
-    #print(chat_history)
-    query = question
-    result = qa({"question": query, "chat_history": chat_history})
-    #print(result)
-    return result["answer"]
-
-css="""
-#col-container {max-width: 700px; margin-left: auto; margin-right: auto;}
-"""
+    with gr.Row():
+        pdf_upload = gr.File(label="Upload PDF", file_types=[".pdf"])
+        upload_button = gr.Button("Process PDF")
 
-title = """
-<div style="text-align: center;max-width: 700px;">
-    <h1>Chat with PDF • OpenAI</h1>
-    <p style="text-align: center;">Upload a .PDF from your computer, click the "Load PDF to LangChain" button, <br />
-    when everything is ready, you can start asking questions about the pdf ;) <br />
-    This version is set to store chat history, and uses OpenAI as LLM, don't forget to copy/paste your OpenAI API key</p>
-</div>
-"""
+    upload_status = gr.Textbox(label="Upload Status")
+    upload_button.click(upload_pdf, inputs=[pdf_upload], outputs=[upload_status])
 
+    chatbot_interface = gr.Chatbot()
+    msg = gr.Textbox()
+    clear = gr.Button("Clear")
 
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.HTML(title)
-        
-        with gr.Column():
-            openai_key = gr.Textbox(label="You OpenAI API key", type="password")
-            pdf_doc = gr.File(label="Load a pdf", file_types=['.pdf'], type="filepath")
-            with gr.Row():
-                langchain_status = gr.Textbox(label="Status", placeholder="", interactive=False)
-                load_pdf = gr.Button("Load pdf to langchain")
-        
-        chatbot = gr.Chatbot([], elem_id="chatbot")
-        
-        question = gr.Textbox(label="Question", placeholder="Type your question and hit Enter ")
-        submit_btn = gr.Button("Send Message")
-    load_pdf.click(loading_pdf, None, langchain_status, queue=False)    
-    load_pdf.click(pdf_changes, inputs=[pdf_doc, openai_key], outputs=[langchain_status], queue=False)
-    question.submit(add_text, [chatbot, question], [chatbot, question]).then(
-        bot, chatbot, chatbot
-    )
-    submit_btn.click(add_text, [chatbot, question], [chatbot, question]).then(
-        bot, chatbot, chatbot)
+    msg.submit(respond, inputs=[msg, chatbot_interface], outputs=[msg, chatbot_interface])
+    clear.click(lambda: None, None, chatbot_interface, queue=False)
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()