made some changes in route handling

app.py

@@ -464,20 +464,34 @@ async def api_generate(request: Request):
             'stream': True,
         }
 
-        xaimodels = ["grok-3-mini", "grok-2-1212", "grok-3", "grok-3-fast", "grok-3-mini-fast"]
+        # Define model lists for each provider
+        xai_models = ["grok-3-mini", "grok-2-1212", "grok-3", "grok-3-fast", "grok-3-mini-fast"]
+        together_models = ['meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8', 'meta-llama/Llama-4-Scout-17B-16E-Instruct', 'deepseek-ai/DeepSeek-R1', 'deepseek-ai/DeepSeek-V3', 'Qwen/Qwen2.5-VL-72B-Instruct', 'google/gemma-2-27b-it']
+        groq_models = ['qwen-qwq-32b', 'gemma2-9b-it', 'meta-llama/llama-4-maverick-17b-128e-instruct', 'meta-llama/llama-4-scout-17b-16e-instruct']
+        vercel_groq_models = ['meta-llama/llama-4-scout-17b-16e-instruct', 'llama-3.1-8b-instant', 'llama-3.3-70b-versatile', 'deepseek-r1-distill-llama-70b']
+
+        # Create a list of available generators for the requested model
+        available_generators = []
+
+        if model in xai_models:
+            available_generators.append(vercelXaigenerate)
+        if model in together_models:
+            available_generators.append(generate)
+        if model in groq_models:
+            available_generators.append(groqgenerate)
+        if model in vercel_groq_models:
+            available_generators.append(vercelGroqgenerate)
+
+        if not available_generators:
+            return {"error": "No suitable generator found for the specified model"}
+
+        # Randomly select one generator if multiple are available
+        selected_generator = random.choice(available_generators)
+        log_request("/v1/generate", selected_generator.__name__)
+        return StreamingResponse(selected_generator(json_data), media_type='text/event-stream')
 
-        if model in xaimodels:
-            return StreamingResponse(vercelXaigenerate(json_data), media_type='text/event-stream')
-        else:
-            try:
-                return StreamingResponse(vercelGroqgenerate(json_data), media_type='text/event-stream')
-            except Exception as e:
-                try:
-                    return StreamingResponse(generate(json_data), media_type='text/event-stream')    
-                except Exception as e:
-                    return StreamingResponse(groqgenerate(json_data), media_type='text/event-stream')
     except Exception as e:
-        return {"error": str(e)}    
+        return {"error": f"Generation failed: {str(e)}"}
     
 @app.post("/v1/generate-images")
 async def generate_images(request: Request):

test.py

@@ -7,9 +7,9 @@ messages = [
     {"role": "user", "content": "who are you and give me a breif description of who you are"}
 ]
 
-model = "Llama-4-Maverick-17B-128E-Instruct-FP8"
+model = "meta-llama/llama-4-scout-17b-16e-instruct"
 
-url = "https://maouu-chipling-api.hf.space/v1/generate"
+url = "http://127.0.0.1:8000/v1/generate"
 payload = {
     "messages": messages,
     "model": model
@@ -19,8 +19,8 @@ response = requests.post(url, json=payload, stream=True)
 
 if response.status_code == 200:
     for line in response.iter_lines():
-        print(line)
         if line:
+            print(line)
             decoded_line = line.decode('utf-8')
             if decoded_line.startswith('data: '):
                 try: