fix docs hierarchy

cookbook/TogetherAI_liteLLM.ipynb

@@ -1,72 +1,56 @@
 {
-  "nbformat": 4,
-  "nbformat_minor": 0,
-  "metadata": {
-    "colab": {
-      "provenance": []
-    },
-    "kernelspec": {
-      "name": "python3",
-      "display_name": "Python 3"
-    },
-    "language_info": {
-      "name": "python"
-    }
-  },
   "cells": [
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "WemkFEdDAnJL"
+      },
       "source": [
         "## liteLLM Together AI Tutorial\n",
         "https://together.ai/\n"
-      ],
-      "metadata": {
-        "id": "WemkFEdDAnJL"
-      }
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
-        "!pip install litellm==0.1.371"
-      ],
+      "execution_count": null,
       "metadata": {
         "id": "pc6IO4V99O25"
       },
-      "execution_count": null,
-      "outputs": []
+      "outputs": [],
+      "source": [
+        "!pip install litellm==0.1.371"
+      ]
     },
     {
       "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {
+        "id": "TMI3739_9q97"
+      },
+      "outputs": [],
       "source": [
         "import os\n",
         "from litellm import completion\n",
         "os.environ[\"TOGETHER_AI_TOKEN\"] = \"\" #@param\n",
         "user_message = \"Hello, whats the weather in San Francisco??\"\n",
         "messages = [{ \"content\": user_message,\"role\": \"user\"}]"
-      ],
-      "metadata": {
-        "id": "TMI3739_9q97"
-      },
-      "execution_count": 5,
-      "outputs": []
+      ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "bEqJ2HHjBJqq"
+      },
       "source": [
         "## Calling togethercomputer/llama-2-70b-chat\n",
         "https://api.together.xyz/playground/chat?model=togethercomputer%2Fllama-2-70b-chat"
-      ],
-      "metadata": {
-        "id": "bEqJ2HHjBJqq"
-      }
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
-        "model_name = \"togethercomputer/llama-2-70b-chat\"\n",
-        "response = completion(model=model_name, messages=messages, together_ai=True)\n",
-        "print(response)"
-      ],
+      "execution_count": 6,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -74,34 +58,34 @@
         "id": "Jrrt8puj523f",
         "outputId": "5a5b5beb-cda3-413e-8e83-4423d392cb44"
       },
-      "execution_count": 6,
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "{'choices': [{'finish_reason': 'stop', 'index': 0, 'message': {'role': 'assistant', 'content': \"\\n\\nI'm not able to provide real-time weather information. However, I can suggest\"}}], 'created': 1691629657.9288375, 'model': 'togethercomputer/llama-2-70b-chat', 'usage': {'prompt_tokens': 9, 'completion_tokens': 17, 'total_tokens': 26}}\n"
           ]
         }
+      ],
+      "source": [
+        "model_name = \"togethercomputer/llama-2-70b-chat\"\n",
+        "response = completion(model=model_name, messages=messages, custom_llm_provider=\"together_ai\")\n",
+        "print(response)"
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "## With Streaming"
-      ],
       "metadata": {
         "id": "sfWtgf-mBQcM"
-      }
+      },
+      "source": [
+        "## With Streaming"
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
-        "response = completion(model=model_name, messages=messages, together_ai=True, stream=True)\n",
-        "print(response)\n",
-        "for chunk in response:\n",
-        "  print(chunk['choices'][0]['delta']) # same as openai format"
-      ],
+      "execution_count": 8,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -109,11 +93,10 @@
         "id": "wuBhlZtC6MH5",
         "outputId": "fcb82177-6494-4963-8e37-8716d3b9e616"
       },
-      "execution_count": 8,
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "<litellm.utils.CustomStreamWrapper object at 0x7ad005e93ee0>\n",
             "{'role': 'assistant', 'content': '\\\\n'}\n",
@@ -136,7 +119,27 @@
             "{'role': 'assistant', 'content': ' can'}\n"
           ]
         }
+      ],
+      "source": [
+        "response = completion(model=model_name, messages=messages, stream=True, custom_llm_provider=\"together_ai\")\n",
+        "print(response)\n",
+        "for chunk in response:\n",
+        "  print(chunk['choices'][0]['delta']) # same as openai format"
       ]
     }
-  ]
-}
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}