From 6dabeabcbc19d9c18be81ae70a6c2e5f3d5a41cd Mon Sep 17 00:00:00 2001
From: ishaan-jaff <ishaanjaffer0324@gmail.com>
Date: Wed, 20 Sep 2023 08:01:44 -0700
Subject: [PATCH] docs

---
 docs/my-website/docs/completion/batching.md | 101 +++++++++++++++++++-
 1 file changed, 97 insertions(+), 4 deletions(-)

diff --git a/docs/my-website/docs/completion/batching.md b/docs/my-website/docs/completion/batching.md
index 5c278aebe2..334e8b1156 100644
--- a/docs/my-website/docs/completion/batching.md
+++ b/docs/my-website/docs/completion/batching.md
@@ -1,7 +1,8 @@
 # Batching Completion() Calls 
 LiteLLM allows you to:
-* Send multiple completion calls to 1 model
-* Send 1 completion call to N models
+* Send many completion calls to 1 model
+* Send 1 completion call to many models: Return Fastest Response
+* Send 1 completion call to many models: Return All Responses
 
 ## Send multiple completion calls to 1 model
 
@@ -39,7 +40,7 @@ responses = batch_completion(
 )
 ```
 
-## Send 1 completion call to N models
+## Send 1 completion call to many models: Return Fastest Response
 This makes parallel calls to the specified `models` and returns the first response 
 
 Use this to reduce latency
@@ -86,4 +87,96 @@ Returns the first response
     "total_tokens": 20
   }
 }
-```
\ No newline at end of file
+```
+
+## Send 1 completion call to many models: Return All Responses
+This makes parallel calls to the specified models and returns all responses
+
+Use this to process requests concurrently and get responses from multiple models.
+
+### Example Code
+```python
+import litellm
+import os
+from litellm import batch_completion_models_all_responses
+
+os.environ['ANTHROPIC_API_KEY'] = ""
+os.environ['OPENAI_API_KEY'] = ""
+os.environ['COHERE_API_KEY'] = ""
+
+responses = batch_completion_models_all_responses(
+    models=["gpt-3.5-turbo", "claude-instant-1.2", "command-nightly"], 
+    messages=[{"role": "user", "content": "Hey, how's it going"}]
+)
+print(responses)
+
+```
+
+### Output
+
+```json
+[<ModelResponse chat.completion id=chatcmpl-e673ec8e-4e8f-4c9e-bf26-bf9fa7ee52b9 at 0x103a62160> JSON: {
+  "object": "chat.completion",
+  "choices": [
+    {
+      "finish_reason": "stop_sequence",
+      "index": 0,
+      "message": {
+        "content": " It's going well, thank you for asking! How about you?",
+        "role": "assistant",
+        "logprobs": null
+      }
+    }
+  ],
+  "id": "chatcmpl-e673ec8e-4e8f-4c9e-bf26-bf9fa7ee52b9",
+  "created": 1695222060.917964,
+  "model": "claude-instant-1.2",
+  "usage": {
+    "prompt_tokens": 14,
+    "completion_tokens": 9,
+    "total_tokens": 23
+  }
+}, <ModelResponse chat.completion id=chatcmpl-ab6c5bd3-b5d9-4711-9697-e28d9fb8a53c at 0x103a62b60> JSON: {
+  "object": "chat.completion",
+  "choices": [
+    {
+      "finish_reason": "stop",
+      "index": 0,
+      "message": {
+        "content": " It's going well, thank you for asking! How about you?",
+        "role": "assistant",
+        "logprobs": null
+      }
+    }
+  ],
+  "id": "chatcmpl-ab6c5bd3-b5d9-4711-9697-e28d9fb8a53c",
+  "created": 1695222061.0445492,
+  "model": "command-nightly",
+  "usage": {
+    "prompt_tokens": 6,
+    "completion_tokens": 14,
+    "total_tokens": 20
+  }
+}, <OpenAIObject chat.completion id=chatcmpl-80szFnKHzCxObW0RqCMw1hWW1Icrq at 0x102dd6430> JSON: {
+  "id": "chatcmpl-80szFnKHzCxObW0RqCMw1hWW1Icrq",
+  "object": "chat.completion",
+  "created": 1695222061,
+  "model": "gpt-3.5-turbo-0613",
+  "choices": [
+    {
+      "index": 0,
+      "message": {
+        "role": "assistant",
+        "content": "Hello! I'm an AI language model, so I don't have feelings, but I'm here to assist you with any questions or tasks you might have. How can I help you today?"
+      },
+      "finish_reason": "stop"
+    }
+  ],
+  "usage": {
+    "prompt_tokens": 13,
+    "completion_tokens": 39,
+    "total_tokens": 52
+  }
+}]
+
+```