Update app.py

app.py

@@ -1,8 +1,7 @@
-#refer llama recipes for more info https://github.com/huggingface/huggingface-llama-recipes/blob/main/inference-api.ipynb
-#huggingface-llama-recipes : https://github.com/huggingface/huggingface-llama-recipes/tree/main
 import gradio as gr
-from openai import OpenAI
+from openai import OpenAI, APIError
 import os
+import tenacity
 
 ACCESS_TOKEN = os.getenv("HF_TOKEN")
 
@@ -11,6 +10,7 @@ client = OpenAI(
     api_key=ACCESS_TOKEN,
 )
 
+@tenacity.retry(wait=tenacity.wait_exponential(multiplier=1, min=4, max=10))
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -19,31 +19,49 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    try:
+        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]})
+        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})
+        messages.append({"role": "user", "content": message})
 
-    response = ""
-    
-    for message in  client.chat.completions.create(
-        model="NousResearch/Hermes-3-Llama-3.1-8B",
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-        messages=messages,
-    ):
-        token = message.choices[0].delta.content
-        
-        response += token
-        yield response
+        response = ""
         
+        for message in  client.chat.completions.create(
+            model="NousResearch/Hermes-3-Llama-3.1-8B",
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+            messages=messages,
+        ):
+            token = message.choices[0].delta.content
+            
+            response += token
+            yield response
+    except APIError as e:
+        error_details = e.body
+        error_type = error_details.get("type")
+        error_code = error_details.get("code")
+        error_param = error_details.get("param")
+        error_message = error_details.get("message")
+
+        if error_type:
+            error_str = f"{error_type}: {error_message} (code: {error_code}, param: {error_param})"
+        else:
+            error_str = "An error occurred during streaming"
+
+        print(f"Error: {error_str}")
+        yield error_str
+    except Exception as e:
+        print(f"Error: {e}")
+        yield "Error occurred. Please try again."
+
 chatbot = gr.Chatbot(height=600)
 
 demo = gr.ChatInterface(