From c4a595d3527fc59cc714e8115ea3bb14e937e5a4 Mon Sep 17 00:00:00 2001
From: ishaan-jaff <ishaanjaffer0324@gmail.com>
Date: Wed, 4 Oct 2023 14:38:00 -0700
Subject: [PATCH] add batch completion rate limits docs

---
 docs/my-website/docs/completion/batching.md | 31 +++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

diff --git a/docs/my-website/docs/completion/batching.md b/docs/my-website/docs/completion/batching.md
index 334e8b1156..6d56608604 100644
--- a/docs/my-website/docs/completion/batching.md
+++ b/docs/my-website/docs/completion/batching.md
@@ -1,9 +1,36 @@
-# Batching Completion() Calls 
+# Batching Completion(), Handling Rate Limits
 LiteLLM allows you to:
-* Send many completion calls to 1 model
+* Send many completion calls to 1 model [while handling rate limits]
 * Send 1 completion call to many models: Return Fastest Response
 * Send 1 completion call to many models: Return All Responses
 
+## Handling Rate Limits with batch completion
+## Batch Completion with only 1 model
+### Usage 
+```python
+import asyncio
+from litellm import batch_completion_rate_limits
+
+# kwargs to litellm.completion
+jobs = [
+    {"model": "gpt-4", "messages": [{"content": "Please provide a summary of the latest scientific discoveries."*500, "role": "user"}]},
+    {"model": "gpt-4", "messages": [{"content": "Please provide a summary of the latest scientific discoveries."*800, "role": "user"}]},
+    {"model": "gpt-4", "messages": [{"content": "Please provide a summary of the latest scientific discoveries."*900, "role": "user"}]},
+    {"model": "gpt-4", "messages": [{"content": "Please provide a summary of the latest scientific discoveries."*900, "role": "user"}]},
+    {"model": "gpt-4", "messages": [{"content": "Please provide a summary of the latest scientific discoveries."*900, "role": "user"}]}
+]
+
+asyncio.run(
+        batch_completion_rate_limits(
+            jobs = jobs,
+            api_key=os.environ['OPENAI_API_KEY'], # pass your api key for your selected model
+            max_requests_per_minute=60,
+            max_tokens_per_minute=40000
+        )
+)
+
+```
+
 ## Send multiple completion calls to 1 model
 
 In the batch_completion method, you provide a list of `messages` where each sub-list of messages is passed to `litellm.completion()`, allowing you to process multiple prompts efficiently in a single API call.