Update app.py

app.py

@@ -17,14 +17,10 @@ logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(
 
 # Environment variables and configurations
 huggingface_token = os.environ.get("HUGGINGFACE_TOKEN")
-ACCOUNT_ID = os.environ.get("CLOUDFARE_ACCOUNT_ID")
-API_TOKEN = os.environ.get("CLOUDFLARE_AUTH_TOKEN")
-API_BASE_URL = "https://api.cloudflare.com/client/v4/accounts/a17f03e0f049ccae0c15cdcf3b9737ce/ai/run/"
 
 MODELS = [
     "mistralai/Mistral-7B-Instruct-v0.3",
     "mistralai/Mixtral-8x7B-Instruct-v0.1",
-    "@cf/meta/llama-3.1-8b-instruct",
     "mistralai/Mistral-Nemo-Instruct-2407",
     "meta-llama/Meta-Llama-3.1-8B-Instruct",
     "meta-llama/Meta-Llama-3.1-70B-Instruct"
@@ -112,76 +108,21 @@ def get_response_with_search(query, model, num_calls=3, temperature=0.2):
 Write a detailed and complete research document that fulfills the following user request: '{query}'
 After writing the document, please provide a list of sources used in your response."""
 
-    if model == "@cf/meta/llama-3.1-8b-instruct":
-        # Use Cloudflare API
-        for response in get_response_from_cloudflare(prompt="", context=context, query=query, num_calls=num_calls, temperature=temperature):
-            yield response, ""  # Yield streaming response without sources
-    else:
-        # Use Hugging Face API
-        client = InferenceClient(model, token=huggingface_token)
-        
-        main_content = ""
-        for i in range(num_calls):
-            for message in client.chat_completion(
-                messages=[{"role": "user", "content": prompt}],
-                max_tokens=10000,
-                temperature=temperature,
-                stream=True,
-            ):
-                if message.choices and message.choices[0].delta and message.choices[0].delta.content:
-                    chunk = message.choices[0].delta.content
-                    main_content += chunk
-                    yield main_content, ""  # Yield partial main content without sources
-
-def get_response_from_cloudflare(prompt, context, query, num_calls=3, temperature=0.2):
-    headers = {
-        "Authorization": f"Bearer {API_TOKEN}",
-        "Content-Type": "application/json"
-    }
-    model = "@cf/meta/llama-3.1-8b-instruct"
-
-    instruction = f"""Using the following context:
-{context}
-Write a detailed and complete research document that fulfills the following user request: '{query}'
-After writing the document, please provide a list of sources used in your response."""
-
-    inputs = [
-        {"role": "system", "content": instruction},
-        {"role": "user", "content": query}
-    ]
-
-    payload = {
-        "messages": inputs,
-        "stream": True,
-        "temperature": temperature,
-        "max_tokens": 32000
-    }
-
-    full_response = ""
-    for i in range(num_calls):
-        try:
-            with requests.post(f"{API_BASE_URL}{model}", headers=headers, json=payload, stream=True) as response:
-                if response.status_code == 200:
-                    for line in response.iter_lines():
-                        if line:
-                            try:
-                                json_response = json.loads(line.decode('utf-8').split('data: ')[1])
-                                if 'response' in json_response:
-                                    chunk = json_response['response']
-                                    full_response += chunk
-                                    yield full_response
-                            except (json.JSONDecodeError, IndexError) as e:
-                                logging.error(f"Error parsing streaming response: {str(e)}")
-                                continue
-                else:
-                    logging.error(f"HTTP Error: {response.status_code}, Response: {response.text}")
-                    yield f"I apologize, but I encountered an HTTP error: {response.status_code}. Please try again later."
-        except Exception as e:
-            logging.error(f"Error in generating response from Cloudflare: {str(e)}")
-            yield f"I apologize, but an error occurred: {str(e)}. Please try again later."
+    # Use Hugging Face API
+    client = InferenceClient(model, token=huggingface_token)
     
-    if not full_response:
-        yield "I apologize, but I couldn't generate a response at this time. Please try again later."
+    main_content = ""
+    for i in range(num_calls):
+        for message in client.chat_completion(
+            messages=[{"role": "user", "content": prompt}],
+            max_tokens=10000,
+            temperature=temperature,
+            stream=True,
+        ):
+            if message.choices and message.choices[0].delta and message.choices[0].delta.content:
+                chunk = message.choices[0].delta.content
+                main_content += chunk
+                yield main_content, ""  # Yield partial main content without sources
 
 def vote(data: gr.LikeData):
     if data.liked:
@@ -205,7 +146,7 @@ def initial_conversation():
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Dropdown(choices=MODELS, label="Select Model", value=MODELS[3]),
+        gr.Dropdown(choices=MODELS, label="Select Model", value=MODELS[2]),
         gr.Slider(minimum=0.1, maximum=1.0, value=0.2, step=0.1, label="Temperature"),
         gr.Slider(minimum=1, maximum=5, value=1, step=1, label="Number of API Calls"),
     ],