Update app.py

app.py

@@ -187,96 +187,6 @@ def delete_documents(selected_docs):
     
     return f"Deleted documents: {', '.join(deleted_docs)}", display_documents()
 
-def generate_chunked_response(prompt, model, max_tokens=10000, num_calls=3, temperature=0.2, should_stop=False):
-    print(f"Starting generate_chunked_response with {num_calls} calls")
-    full_response = ""
-    messages = [{"role": "user", "content": prompt}]
-    
-    if model == "@cf/meta/llama-3.1-8b-instruct":
-        # Cloudflare API
-        for i in range(num_calls):
-            print(f"Starting Cloudflare API call {i+1}")
-            if should_stop:
-                print("Stop clicked, breaking loop")
-                break
-            try:
-                response = requests.post(
-                    f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/@cf/meta/llama-3.1-8b-instruct",
-                    headers={"Authorization": f"Bearer {API_TOKEN}"},
-                    json={
-                        "stream": true,
-                        "messages": [
-                            {"role": "system", "content": "You are a friendly assistant"},
-                            {"role": "user", "content": prompt}
-                        ],
-                        "max_tokens": max_tokens,
-                        "temperature": temperature
-                    },
-                    stream=true
-                )
-                
-                for line in response.iter_lines():
-                    if should_stop:
-                        print("Stop clicked during streaming, breaking")
-                        break
-                    if line:
-                        try:
-                            json_data = json.loads(line.decode('utf-8').split('data: ')[1])
-                            chunk = json_data['response']
-                            full_response += chunk
-                        except json.JSONDecodeError:
-                            continue
-                print(f"Cloudflare API call {i+1} completed")
-            except Exception as e:
-                print(f"Error in generating response from Cloudflare: {str(e)}")
-    else:
-        # Original Hugging Face API logic
-        client = InferenceClient(model, token=huggingface_token)
-        
-        for i in range(num_calls):
-            print(f"Starting Hugging Face API call {i+1}")
-            if should_stop:
-                print("Stop clicked, breaking loop")
-                break
-            try:
-                for message in client.chat_completion(
-                    messages=messages,
-                    max_tokens=max_tokens,
-                    temperature=temperature,
-                    stream=True,
-                ):
-                    if should_stop:
-                        print("Stop clicked during streaming, breaking")
-                        break
-                    if message.choices and message.choices[0].delta and message.choices[0].delta.content:
-                        chunk = message.choices[0].delta.content
-                        full_response += chunk
-                print(f"Hugging Face API call {i+1} completed")
-            except Exception as e:
-                print(f"Error in generating response from Hugging Face: {str(e)}")
-    
-    # Clean up the response
-    clean_response = re.sub(r'<s>\[INST\].*?\[/INST\]\s*', '', full_response, flags=re.DOTALL)
-    clean_response = clean_response.replace("Using the following context:", "").strip()
-    clean_response = clean_response.replace("Using the following context from the PDF documents:", "").strip()
-    
-    # Remove duplicate paragraphs and sentences
-    paragraphs = clean_response.split('\n\n')
-    unique_paragraphs = []
-    for paragraph in paragraphs:
-        if paragraph not in unique_paragraphs:
-            sentences = paragraph.split('. ')
-            unique_sentences = []
-            for sentence in sentences:
-                if sentence not in unique_sentences:
-                    unique_sentences.append(sentence)
-            unique_paragraphs.append('. '.join(unique_sentences))
-    
-    final_response = '\n\n'.join(unique_paragraphs)
-    
-    print(f"Final clean response: {final_response[:100]}...")
-    return final_response
-
 def chatbot_interface(message, history, model, temperature, num_calls):
     if not message.strip():
         return "", history