From f2991203941095109707c47265090bcfb0588965 Mon Sep 17 00:00:00 2001
From: ishaan-jaff <ishaanjaffer0324@gmail.com>
Date: Wed, 29 Nov 2023 18:08:00 -0800
Subject: [PATCH] (docs) router

---
 docs/my-website/docs/routing.md | 31 +++++++++++++++++++------------
 1 file changed, 19 insertions(+), 12 deletions(-)

diff --git a/docs/my-website/docs/routing.md b/docs/my-website/docs/routing.md
index 03d95e9ef2..ddaea36885 100644
--- a/docs/my-website/docs/routing.md
+++ b/docs/my-website/docs/routing.md
@@ -69,17 +69,18 @@ print(response)
 - `router.text_completion()` - completion calls in the old OpenAI `/v1/completions` endpoint format
 
 ### Advanced
-#### Routing Strategies - Shuffle, Rate Limit Aware
+#### Routing Strategies - Weighted Pick, Rate Limit Aware
 
 Router provides 2 strategies for routing your calls across multiple deployments: 
 
 <Tabs>
-<TabItem value="simple-shuffle" label="Simple Shuffle">
+<TabItem value="simple-shuffle" label="Weighted Pick">
 
-**Default** Randomly picks a deployment to route a call too.
+**Default** Picks a deployment based on the provided **Requests per minute (rpm) or Tokens per minute (tpm)**
 
 ```python
 from litellm import Router 
+import asyncio
 
 model_list = [{ # list of model deployments 
 	"model_name": "gpt-3.5-turbo", # model alias 
@@ -87,7 +88,8 @@ model_list = [{ # list of model deployments
 		"model": "azure/chatgpt-v-2", # actual model name
 		"api_key": os.getenv("AZURE_API_KEY"),
 		"api_version": os.getenv("AZURE_API_VERSION"),
-		"api_base": os.getenv("AZURE_API_BASE")
+		"api_base": os.getenv("AZURE_API_BASE"),
+		"rpm": 900,			# requests per minute for this API
 	}
 }, {
     "model_name": "gpt-3.5-turbo", 
@@ -95,24 +97,29 @@ model_list = [{ # list of model deployments
 		"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")
+		"api_base": os.getenv("AZURE_API_BASE"),
+		"rpm": 10,
 	}
 }, {
     "model_name": "gpt-3.5-turbo", 
 	"litellm_params": { # params for litellm completion/embedding call 
 		"model": "gpt-3.5-turbo", 
 		"api_key": os.getenv("OPENAI_API_KEY"),
+		"rpm": 10,
 	}
 }]
 
-
+# init router
 router = Router(model_list=model_list, routing_strategy="simple-shuffle")
+async def router_acompletion():
+	response = await router.acompletion(
+		model="gpt-3.5-turbo", 
+		messages=[{"role": "user", "content": "Hey, how's it going?"}]
+	)
+	print(response)
+	return response
 
-
-response = await router.acompletion(model="gpt-3.5-turbo", 
-				messages=[{"role": "user", "content": "Hey, how's it going?"}])
-
-print(response)
+asyncio.run(router_acompletion())
 ```
 </TabItem>
 <TabItem value="usage-based" label="Rate-Limit Aware">
@@ -163,7 +170,7 @@ router = Router(model_list=model_list,
                 redis_host=os.environ["REDIS_HOST"], 
 				redis_password=os.environ["REDIS_PASSWORD"], 
 				redis_port=os.environ["REDIS_PORT"], 
-                routing_strategy="usage-based-routing")
+                routing_strategy="simple-shuffle")
 
 
 response = await router.acompletion(model="gpt-3.5-turbo",