Update app.py

app.py

@@ -1,63 +1,75 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+import fitz  # PyMuPDF
+import re
+from langchain_openai.embeddings import OpenAIEmbeddings
+from langchain_chroma import Chroma
+from langchain.retrievers.multi_query import MultiQueryRetriever
+from langchain.chains import ConversationalRetrievalChain
+from langchain.memory import ConversationBufferMemory
+from langchain_openai import ChatOpenAI
+from langchain_experimental.text_splitter import SemanticChunker
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+# Place your OpenAI API key in a safe place, such as an environment variable or a secure vault
+openai_api_key = "YOUR_OPENAI_API_KEY_HERE"
+
+vectorstore = None
+llm = None
+qa_instance = None
+chat_history = []
+
+def extract_text_from_pdf(pdf_bytes):
+    document = fitz.open("pdf", pdf_bytes)
+    text = ""
+    for page_num in range(len(document)):
+        page = document.load_page(page_num)
+        text += page.get_text()
+    document.close()
+    return text
+
+def clean_text(text):
+    cleaned_text = re.sub(r'\s+', ' ', text)
+    cleaned_text = re.sub(r'(.)\1{2,}', r'\1', cleaned_text)
+    cleaned_text = re.sub(r'\b(\w+)\b(?:\s+\1\b)+', r'\1', cleaned_text)
+    return cleaned_text.strip()
+
+def initialize_chatbot(cleaned_text):
+    global vectorstore, llm, qa_instance
+    if vectorstore is None:
+        embeddings = OpenAIEmbeddings(api_key=openai_api_key)
+        text_splitter = SemanticChunker(embeddings)
+        docs = text_splitter.create_documents([cleaned_text])
+        vectorstore = Chroma.from_documents(documents=docs, embedding=embeddings)
+    if llm is None:
+        llm = ChatOpenAI(api_key=openai_api_key, temperature=0.5, model="gpt-4o", verbose=True)
+    retriever = MultiQueryRetriever.from_llm(retriever=vectorstore.as_retriever(), llm=llm)
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+    qa_instance = ConversationalRetrievalChain.from_llm(llm, retriever=retriever, memory=memory)
+
+def setup_qa_system(pdf_file):
+    if pdf_file is None:
+        return [("Please upload a PDF file.", "")]
+    extracted_text = extract_text_from_pdf(pdf_file)
+    cleaned_text = clean_text(extracted_text)
+    initialize_chatbot(cleaned_text)
+    chat_history = [("Chatbot initialized. Please ask a question.", "")]
+    return chat_history
+
+def answer_query(question):
+    if qa_instance is None:
+        return [("Please upload a PDF and initialize the system first.", "")]
+    if not question.strip():
+        return [("Please enter a question.", "")]
+    result = qa_instance({"question": question})
+    chat_history.append((question, result['answer']))
+    return chat_history
+
+with gr.Blocks() as demo:
+    upload = gr.File(label="Upload PDF", type="binary", file_types=["pdf"])
+    chatbot = gr.Chatbot(label="Chatbot")
+    question = gr.Textbox(label="Ask a question", placeholder="Type your question after uploading PDF...")
+
+    upload.change(setup_qa_system, inputs=[upload], outputs=[chatbot])
+    question.submit(answer_query, inputs=[question], outputs=[chatbot])
+
+demo.launch()