From 8b8e5890e32061b8b8f4c003f095a781b0b84b76 Mon Sep 17 00:00:00 2001
From: ishaan-jaff <ishaanjaffer0324@gmail.com>
Date: Tue, 21 Nov 2023 17:20:24 -0800
Subject: [PATCH] (docs) routing

---
 docs/my-website/docs/routing.md | 78 ++++++++++++++++++++++++++-------
 1 file changed, 63 insertions(+), 15 deletions(-)

diff --git a/docs/my-website/docs/routing.md b/docs/my-website/docs/routing.md
index 4c5928cccb..1441016a62 100644
--- a/docs/my-website/docs/routing.md
+++ b/docs/my-website/docs/routing.md
@@ -250,37 +250,85 @@ Queue your LLM API requests to ensure you're under your rate limits
 - Step 1: Create a `/queue/reques` request
 - Step 2: Poll your request, to check if it's completed
 
-### Step 1: Queue a `/chat/completion` request
 
+## Step 1 Add a config to the proxy, generate a temp key 
 ```python
 import requests
-# args to litellm.completion()
-data = {
-    'model': 'gpt-3.5-turbo',
-    'messages': [
-        {'role': 'system', 'content': f'You are a helpful assistant. What llm are you?'},
-    ],
+import time
+config = {
+
 }
-response = requests.post("http://0.0.0.0:8000/queue/request", json=data)
-response = response.json()
-polling_url = response["url"]
+
+response = requests.post(
+    url = "http://0.0.0.0:8000/key/generate",
+    json={
+        "config": config,
+        "duration": "30d" # default to 30d, set it to 30m if you want a temp key
+    },
+    headers={
+        "Authorization": "Bearer sk-hosted-litellm"
+    }
+)
+
+print("\nresponse from generating key", response.json())
+
+generated_key = response.json()["key"]
+print("\ngenerated key for proxy", generated_key)
 ```
 
-### Step 2: Poll your `/chat/completion` request
+# Step 2: Queue a request to the proxy, using your generated_key
 ```python
- while True:
+job_response = requests.post(
+    url = "http://0.0.0.0:8000/queue/request",
+    json={
+            'model': 'gpt-3.5-turbo',
+            'messages': [
+                {'role': 'system', 'content': f'You are a helpful assistant. What is your name'},
+            ],
+    },
+    headers={
+        "Authorization": f"Bearer {generated_key}"
+    }
+)
+
+job_response = job_response.json()
+job_id  = job_response["id"]
+polling_url = job_response["url"]
+polling_url = f"http://0.0.0.0:8000{polling_url}"
+print("\nCreated Job, Polling Url", polling_url)
+```
+
+# Step 3: Poll the request
+```python
+while True:
     try:
-        polling_url = f"http://0.0.0.0:8000{polling_url}"
-        polling_response = requests.get(polling_url)
+        print("\nPolling URL", polling_url)
+        polling_response = requests.get(
+                url=polling_url, 
+                headers={
+                    "Authorization": f"Bearer {generated_key}"
+                }
+            )
         polling_response = polling_response.json()
-        print("\n RESPONSE FROM POLLING JOB", polling_response)
+        print("\nResponse from polling url", polling_response)
         status = polling_response["status"]
         if status == "finished":
             llm_response = polling_response["result"]
+            print("LLM Response")
             print(llm_response)
+            break
+        time.sleep(0.5)
+    except Exception as e:
+        print("got exception in polling", e)
+        break
+
 ```
 
 
+
+        
+
+
 <!-- ## litellm.completion() 
 
 If you're calling litellm.completion(), here's the different reliability options you can enable.