breakup fxns

app.py

@@ -30,51 +30,49 @@ def summary(self):
     return f"Number of documents: {num_documents}, Average document length: {avg_doc_length}"
 
 # Gradio state
-summary_state = gr.State(initial_value="pending")
+summary_state = gr.State(initial_value="")
+
+# Initialize loader and load documents
+def load_documents(pdf_doc):
+    loader = OnlinePDFLoader(pdf_doc.name)
+    return loader.load()
+
+# Generate summary using StuffDocumentsChain
+def generate_summary(documents):
+    prompt_template = """Write a concise summary of the following:
+    "{text}"
+    CONCISE SUMMARY:"""
+    prompt = PromptTemplate.from_template(prompt_template)
+    llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo-16k")
+    llm_chain = LLMChain(llm=llm, prompt=prompt)
+    stuff_chain = StuffDocumentsChain(
+        llm_chain=llm_chain, document_variable_name="text"
+    )
+    return stuff_chain.run(documents)
+
+# Setup Chroma, embeddings, and retrieval
+def setup_retrieval(documents):
+    embeddings = OpenAIEmbeddings()
+    db = Chroma.from_documents(documents, embeddings)
+    retriever = db.as_retriever()
+    qa = ConversationalRetrievalChain.from_llm(
+        llm=OpenAI(temperature=0.2, model_name="gpt-3.5-turbo-16k", max_tokens=-1, n=2),
+        retriever=retriever,
+        return_source_documents=False
+    )
+    return db, qa
 
-# PDF summary and query using stuffing
+# Main function to handle PDF changes
 def pdf_changes(pdf_doc):
     try:
-        # Initialize loader and load documents
-        loader = OnlinePDFLoader(pdf_doc.name)
-        documents = loader.load()
-
-        # Define the prompt for summarization
-        prompt_template = """Write a concise summary of the following:
-        "{text}"
-        CONCISE SUMMARY:"""
-        prompt = PromptTemplate.from_template(prompt_template)
-
-        # Define the LLM chain with the specified prompt
-        llm = ChatOpenAI(temperature=0, model_name="gpt-3.5-turbo-16k")
-        llm_chain = LLMChain(llm=llm, prompt=prompt)
-
-        # Initialize StuffDocumentsChain
-        stuff_chain = StuffDocumentsChain(
-            llm_chain=llm_chain, document_variable_name="text"
-        )
-
-        # Generate summary using StuffDocumentsChain
+        documents = load_documents(pdf_doc)
         global full_summary
-        full_summary = stuff_chain.run(documents)
-        # Update the state variable
-        return {summary_state: full_summary}
-
-        # Other existing logic for Chroma, embeddings, and retrieval
-        embeddings = OpenAIEmbeddings()
-        global db
-        db = Chroma.from_documents(documents, embeddings)
-
-        retriever = db.as_retriever()
-        global qa
-        qa = ConversationalRetrievalChain.from_llm(
-            llm=OpenAI(temperature=0.2, model_name="gpt-3.5-turbo-16k", max_tokens=-1, n=2),
-            retriever=retriever,
-            return_source_documents=False
-        )
+        full_summary = generate_summary(documents)
+        summary_state.value = full_summary
+        global db, qa
+        db, qa = setup_retrieval(documents)
         summary_box.set_value(full_summary)
         return f"Ready. Full Summary loaded."
-
     except Exception as e:
         return f"Error processing PDF: {str(e)}"
 
@@ -179,7 +177,7 @@ with gr.Blocks(css=css) as demo:
         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(loading_pdf, None, langchain_status)
         load_pdf.click(pdf_changes, inputs=[pdf_doc], outputs=[langchain_status], queue=False).then(
           update_summary_box
       )
@@ -194,4 +192,4 @@ with gr.Blocks(css=css) as demo:
         bot, chatbot, chatbot
     )
 
-demo.launch()
+demo.launch()