fix(router.py): enable additional params to be passe din

litellm/router.py

@@ -61,6 +61,8 @@ class Router:
 
         data = deployment["litellm_params"]
         data["messages"] = messages
+        for key, value in kwargs.items():
+            data[key] = value
         # call via litellm.completion() 
         return litellm.completion(**data)
     
@@ -78,6 +80,8 @@ class Router:
 
         data = deployment["litellm_params"]
         data["prompt"] = prompt
+        for key, value in kwargs.items():
+            data[key] = value
         # call via litellm.completion() 
         return litellm.text_completion(**data)        
 
@@ -203,7 +207,10 @@ class Router:
         # get value 
         cached_value = self.cache.get_cache(key)
         # update value 
-        cached_value = cached_value + increment_value
+        try:
+            cached_value = cached_value + increment_value
+        except: 
+            cached_value = increment_value
         # save updated value
         self.cache.add_cache(result=cached_value, cache_key=key)
     

litellm/tests/test_router.py

@@ -7,55 +7,103 @@ import pytest
 sys.path.insert(
     0, os.path.abspath("../..")
 )  # Adds the parent directory to the system path
+import litellm
 from litellm import Router
 from concurrent.futures import ThreadPoolExecutor
 from dotenv import load_dotenv
 
 load_dotenv()
 
-model_list = [{ # list of model deployments 
-	"model_name": "gpt-3.5-turbo", # openai model name 
-	"litellm_params": { # params for litellm completion/embedding call 
-		"model": "azure/chatgpt-v-2", 
-		"api_key": os.getenv("AZURE_API_KEY"),
-		"api_version": os.getenv("AZURE_API_VERSION"),
-		"api_base": os.getenv("AZURE_API_BASE")
-	},
-	"tpm": 240000,
-	"rpm": 1800
-}, {
-    "model_name": "gpt-3.5-turbo", # openai model name 
-	"litellm_params": { # params for litellm completion/embedding call 
-		"model": "azure/chatgpt-functioncalling", 
-		"api_key": os.getenv("AZURE_API_KEY"),
-		"api_version": os.getenv("AZURE_API_VERSION"),
-		"api_base": os.getenv("AZURE_API_BASE")
-	},
-	"tpm": 240000,
-	"rpm": 1800
-}, {
-    "model_name": "gpt-3.5-turbo", # openai model name 
-	"litellm_params": { # params for litellm completion/embedding call 
-		"model": "gpt-3.5-turbo", 
-		"api_key": os.getenv("OPENAI_API_KEY"),
-	},
-	"tpm": 1000000,
-	"rpm": 9000
-}]
+def test_multiple_deployments(): 
+	model_list = [{ # list of model deployments 
+		"model_name": "gpt-3.5-turbo", # openai model name 
+		"litellm_params": { # params for litellm completion/embedding call 
+			"model": "azure/chatgpt-v-2", 
+			"api_key": os.getenv("AZURE_API_KEY"),
+			"api_version": os.getenv("AZURE_API_VERSION"),
+			"api_base": os.getenv("AZURE_API_BASE")
+		},
+		"tpm": 240000,
+		"rpm": 1800
+	}, {
+		"model_name": "gpt-3.5-turbo", # openai model name 
+		"litellm_params": { # params for litellm completion/embedding call 
+			"model": "azure/chatgpt-functioncalling", 
+			"api_key": os.getenv("AZURE_API_KEY"),
+			"api_version": os.getenv("AZURE_API_VERSION"),
+			"api_base": os.getenv("AZURE_API_BASE")
+		},
+		"tpm": 240000,
+		"rpm": 1800
+	}, {
+		"model_name": "gpt-3.5-turbo", # openai model name 
+		"litellm_params": { # params for litellm completion/embedding call 
+			"model": "gpt-3.5-turbo", 
+			"api_key": os.getenv("OPENAI_API_KEY"),
+		},
+		"tpm": 1000000,
+		"rpm": 9000
+	}]
 
-router = Router(model_list=model_list, redis_host=os.getenv("REDIS_HOST"), redis_password=os.getenv("REDIS_PASSWORD"), redis_port=int(os.getenv("REDIS_PORT"))) # type: ignore
+	router = Router(model_list=model_list, redis_host=os.getenv("REDIS_HOST"), redis_password=os.getenv("REDIS_PASSWORD"), redis_port=int(os.getenv("REDIS_PORT"))) # type: ignore
 
-completions = [] 
-with ThreadPoolExecutor(max_workers=100) as executor:
-	kwargs = {
-		"model": "gpt-3.5-turbo",
-		"messages": [{"role": "user", "content": "Hey, how's it going?"}]
-	}
-	for _ in range(20):
-		future = executor.submit(router.completion, **kwargs) # type: ignore
-		completions.append(future)
+	completions = [] 
+	with ThreadPoolExecutor(max_workers=100) as executor:
+		kwargs = {
+			"model": "gpt-3.5-turbo",
+			"messages": [{"role": "user", "content": "Hey, how's it going?"}]
+		}
+		for _ in range(20):
+			future = executor.submit(router.completion, **kwargs) # type: ignore
+			completions.append(future)
 
-# Retrieve the results from the futures
-results = [future.result() for future in completions]
+	# Retrieve the results from the futures
+	results = [future.result() for future in completions]
 
-print(results)
+	print(results)
+
+### FUNCTION CALLING 
+
+def test_function_calling(): 
+	litellm.set_verbose =True
+	model_list = [
+		{
+				"model_name": "gpt-3.5-turbo-0613",
+				"litellm_params": {
+					"model": "gpt-3.5-turbo-0613",
+					"api_key": "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",
+				},
+				"tpm": 100000,
+				"rpm": 10000,
+			},
+	]
+
+	messages = [
+		{"role": "user", "content": "What is the weather like in Boston?"}
+	]
+	functions = [
+		{
+		"name": "get_current_weather",
+		"description": "Get the current weather in a given location",
+		"parameters": {
+			"type": "object",
+			"properties": {
+			"location": {
+				"type": "string",
+				"description": "The city and state, e.g. San Francisco, CA"
+			},
+			"unit": {
+				"type": "string",
+				"enum": ["celsius", "fahrenheit"]
+			}
+			},
+			"required": ["location"]
+		}
+		}
+	]
+
+	router = Router(model_list=model_list)
+	response = router.completion(model="gpt-3.5-turbo-0613", messages=messages, functions=functions)
+	print(response)
+
+test_function_calling()