Update app.py

app.py

@@ -33,7 +33,6 @@ print(f"CLOUDFLARE_AUTH_TOKEN: {API_TOKEN[:5]}..." if API_TOKEN else "Not set")
 MODELS = [
     "mistralai/Mistral-7B-Instruct-v0.3",
     "mistralai/Mixtral-8x7B-Instruct-v0.1",
-    "meta-llama/Meta-Llama-3.1-8B-Instruct",
     "@cf/meta/llama-3.1-8b-instruct"
 ]
 
@@ -349,20 +348,26 @@ def get_response_from_pdf(query, model, num_calls=3, temperature=0.2):
 {context_str}
 Write a detailed and complete response that answers the following user question: '{query}'"""
 
-    client = InferenceClient(model, token=huggingface_token)
-    
-    response = ""
-    for i in range(num_calls):
-        for message in client.chat_completion(
-            messages=[{"role": "user", "content": prompt}],
-            max_tokens=1000,
-            temperature=temperature,
-            stream=True,
-        ):
-            if message.choices and message.choices[0].delta and message.choices[0].delta.content:
-                chunk = message.choices[0].delta.content
-                response += chunk
-                yield response  # Yield partial response
+    if model == "@cf/meta/llama-3.1-8b-instruct":
+        # Use Cloudflare API
+        for response in get_response_from_cloudflare(prompt, num_calls, temperature):
+            yield response
+    else:
+        # Use Hugging Face API
+        client = InferenceClient(model, token=huggingface_token)
+        
+        response = ""
+        for i in range(num_calls):
+            for message in client.chat_completion(
+                messages=[{"role": "user", "content": prompt}],
+                max_tokens=1000,
+                temperature=temperature,
+                stream=True,
+            ):
+                if message.choices and message.choices[0].delta and message.choices[0].delta.content:
+                    chunk = message.choices[0].delta.content
+                    response += chunk
+                    yield response  # Yield partial response
 
 def vote(data: gr.LikeData):
     if data.liked: