fix(main.py): fixing print_verbose

litellm/llms/huggingface_restapi.py

@@ -141,6 +141,7 @@ def completion(
     litellm_params=None,
     logger_fn=None,
 ):
+    try:
         headers = validate_environment(api_key, headers)
         task = get_hf_task_for_model(model)
         print_verbose(f"{model}, {task}")
@@ -285,7 +286,7 @@ def completion(
                     completion_response = response.json()
                 except:
                     raise HuggingfaceError(
-                    message=response.text, status_code=response.status_code
+                        message=f"Original Response received: {response.text}; Stacktrace: {traceback.format_exc()}", status_code=response.status_code
                     )
             print_verbose(f"response: {completion_response}")
             if isinstance(completion_response, dict) and "error" in completion_response:
@@ -362,6 +363,11 @@ def completion(
             model_response.usage.total_tokens = prompt_tokens + completion_tokens
             model_response._hidden_params["original_response"] = completion_response
             return model_response
+    except HuggingfaceError as e: 
+        raise e
+    except Exception as e: 
+        import traceback
+        raise HuggingfaceError(status_code=500, message=traceback.format_exc())
 
 
 def embedding(

litellm/main.py

@@ -1961,8 +1961,7 @@ def moderation(input: str, api_key: Optional[str]=None):
 ## Set verbose to true -> ```litellm.set_verbose = True```
 def print_verbose(print_statement):
     if litellm.set_verbose:
-        import logging
+        print(print_statement) # noqa
-        logging.info(f"LiteLLM: {print_statement}")
 
 def config_completion(**kwargs):
     if litellm.config_path != None:

litellm/proxy/proxy_cli.py

@@ -52,6 +52,7 @@ def is_port_in_use(port):
 @click.command()
 @click.option('--host', default='0.0.0.0', help='Host for the server to listen on.')
 @click.option('--port', default=8000, help='Port to bind the server to.')
+@click.option('--num_workers', default=1, help='Number of uvicorn workers to spin up')
 @click.option('--api_base', default=None, help='API base URL.')
 @click.option('--api_version', default="2023-07-01-preview", help='For azure - pass in the api version.')
 @click.option('--model', '-m', default=None, help='The model name to pass to litellm expects') 
@@ -74,17 +75,17 @@ def is_port_in_use(port):
 @click.option('--test', flag_value=True, help='proxy chat completions url to make a test request to')
 @click.option('--local', is_flag=True, default=False, help='for local debugging')
 @click.option('--cost', is_flag=True, default=False, help='for viewing cost logs')
-def run_server(host, port, api_base, api_version, model, alias, add_key, headers, save, debug, temperature, max_tokens, request_timeout, drop_params, create_proxy, add_function_to_prompt, config, file, max_budget, telemetry, logs, test, local, cost):
+def run_server(host, port, api_base, api_version, model, alias, add_key, headers, save, debug, temperature, max_tokens, request_timeout, drop_params, create_proxy, add_function_to_prompt, config, file, max_budget, telemetry, logs, test, local, cost, num_workers):
     global feature_telemetry
     args = locals()
     if local:
-        from proxy_server import app, initialize, print_cost_logs, usage_telemetry, add_keys_to_config
+        from proxy_server import app, save_worker_config, print_cost_logs, usage_telemetry, add_keys_to_config
         debug = True
     else:
         try:
-            from .proxy_server import app, initialize, print_cost_logs, usage_telemetry, add_keys_to_config
+            from .proxy_server import app, save_worker_config, print_cost_logs, usage_telemetry, add_keys_to_config
         except ImportError as e: 
-            from proxy_server import app, initialize, print_cost_logs, usage_telemetry, add_keys_to_config
+            from proxy_server import app, save_worker_config, print_cost_logs, usage_telemetry, add_keys_to_config
     feature_telemetry = usage_telemetry
     if create_proxy == True: 
         repo_url = 'https://github.com/BerriAI/litellm'
@@ -163,7 +164,7 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
     else:
         if headers:
             headers = json.loads(headers)
-        initialize(model=model, alias=alias, api_base=api_base, api_version=api_version, debug=debug, temperature=temperature, max_tokens=max_tokens, request_timeout=request_timeout, max_budget=max_budget, telemetry=telemetry, drop_params=drop_params, add_function_to_prompt=add_function_to_prompt, headers=headers, save=save, config=config)
+        save_worker_config(model=model, alias=alias, api_base=api_base, api_version=api_version, debug=debug, temperature=temperature, max_tokens=max_tokens, request_timeout=request_timeout, max_budget=max_budget, telemetry=telemetry, drop_params=drop_params, add_function_to_prompt=add_function_to_prompt, headers=headers, save=save, config=config)
         try:
             import uvicorn
         except:
@@ -174,7 +175,7 @@ def run_server(host, port, api_base, api_version, model, alias, add_key, headers
         
         if port == 8000 and is_port_in_use(port):
             port = random.randint(1024, 49152)
-        uvicorn.run(app, host=host, port=port)
+        uvicorn.run("proxy_server:app", host=host, port=port, workers=num_workers)
 
 
 if __name__ == "__main__":

litellm/proxy/proxy_server.py

@@ -129,11 +129,12 @@ llm_router: Optional[litellm.Router] = None
 llm_model_list: Optional[list] = None
 server_settings: dict = {}
 log_file = "api_log.json"
-
+worker_config = None
 
 #### HELPER FUNCTIONS ####
 def print_verbose(print_statement):
     global user_debug
+    print(f"user debug value: {user_debug}")
     if user_debug:
         print(print_statement)
 
@@ -337,6 +338,9 @@ def load_config():
     except:
         pass
 
+def save_worker_config(**data): 
+    import json
+    os.environ["WORKER_CONFIG"] = json.dumps(data)
 
 def initialize(
     model,
@@ -532,6 +536,7 @@ def litellm_completion(*args, **kwargs):
                 for key, value in m["litellm_params"].items(): 
                     kwargs[key] = value
                 break
+    print(f"litellm set verbose pre-call: {litellm.set_verbose}")
     if call_type == "chat_completion":
         response = litellm.completion(*args, **kwargs)
     elif call_type == "text_completion":
@@ -540,6 +545,14 @@ def litellm_completion(*args, **kwargs):
         return StreamingResponse(data_generator(response), media_type='text/event-stream')
     return response
 
+
+@app.on_event("startup")
+def startup_event():
+    import json
+    worker_config = json.loads(os.getenv("WORKER_CONFIG"))
+    initialize(**worker_config)
+    print(f"\033[32mWorker Initialized\033[0m\n")
+
 #### API ENDPOINTS ####
 @router.get("/v1/models")
 @router.get("/models")  # if project requires model list

litellm/utils.py

@@ -285,8 +285,7 @@ class TextCompletionResponse(OpenAIObject):
 ############################################################
 def print_verbose(print_statement):
     if litellm.set_verbose:
-        import logging
+        print(print_statement) # noqa
-        logging.info(f"LiteLLM: {print_statement}")
 
 ####### LOGGING ###################
 from enum import Enum