Update app.py

app.py

@@ -1,5 +1,4 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
 import fitz  # PyMuPDF
 import re
 from langchain_openai.embeddings import OpenAIEmbeddings
@@ -15,7 +14,7 @@ openai_api_key = os.getenv("OPENAI_API_KEY")
 vectorstore = None
 llm = None
 qa_instance = None
-chat_history = []
+chat_history = []  # Global chat history
 
 def extract_text_from_pdf(pdf_bytes):
     document = fitz.open("pdf", pdf_bytes)
@@ -32,9 +31,9 @@ def clean_text(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):
+def initialize_chatbot(cleaned_text, openai_api_key):
     global vectorstore, llm, qa_instance
-    if vectorstore is None:
+    if vectorstore is None:  # Only create embeddings and Chroma once
         embeddings = OpenAIEmbeddings(api_key=openai_api_key)
         text_splitter = SemanticChunker(embeddings)
         docs = text_splitter.create_documents([cleaned_text])
@@ -46,15 +45,17 @@ def initialize_chatbot(cleaned_text):
     qa_instance = ConversationalRetrievalChain.from_llm(llm, retriever=retriever, memory=memory)
 
 def setup_qa_system(pdf_file):
+    global chat_history
     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)
+    initialize_chatbot(cleaned_text, openai_api_key)
     chat_history = [("Chatbot initialized. Please ask a question.", "")]
     return chat_history
 
 def answer_query(question):
+    global chat_history
     if qa_instance is None:
         return [("Please upload a PDF and initialize the system first.", "")]
     if not question.strip():
@@ -71,4 +72,5 @@ with gr.Blocks() as demo:
     upload.change(setup_qa_system, inputs=[upload], outputs=[chatbot])
     question.submit(answer_query, inputs=[question], outputs=[chatbot])
 
-demo.launch()
+if __name__ == "__main__":
+    demo.launch()