docs(routing.md): adding router to docs

docs/my-website/docs/routing.md

@@ -0,0 +1,50 @@
+# Load-Balance Router
+
+Use this if you're trying to load-balance across multiple deployments. 
+
+
+```python
+pip install litellm
+```
+
+```python
+from litellm import Router
+
+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)
+
+# openai.ChatCompletion.create replacement
+response = router.completion(model="gpt-3.5-turbo", 
+				messages=[{"role": "user", "content": "Hey, how's it going?"}]
+
+print(response)
+```

docs/my-website/sidebars.js

@@ -83,7 +83,7 @@ const sidebars = {
     },
     "proxy_server",
     "budget_manager",
-    "rate_limit_manager",
+    "routing",
     "set_keys",
     "completion/token_usage",
     {