fix replicate docs

cookbook/Evaluating_LLMs.ipynb

@@ -25,7 +25,7 @@
       },
       "outputs": [],
       "source": [
-        "!pip install litellm==0.1.404 python-dotenv"
+        "!pip install litellm python-dotenv"
       ]
     },
     {

cookbook/liteLLM_Replicate_Demo.ipynb

@@ -1,21 +1,11 @@
 {
-  "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": "YV6L5fNv7Kep"
+      },
       "source": [
         "# Call Replicate LLMs using chatGPT Input/Output Format\n",
         "This tutorial covers using the following Replicate Models with liteLLM\n",
@@ -28,10 +18,7 @@
         "\n",
         "\n",
         "\n"
-      ],
+      ]
-      "metadata": {
-        "id": "YV6L5fNv7Kep"
-      }
     },
     {
       "cell_type": "code",
@@ -46,53 +33,44 @@
       ]
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
+      "metadata": {
+        "id": "mpHTbTqQ8fey"
+      },
       "source": [
         "Imports & Set ENV variables\n",
         "Get your Replicate Key: https://replicate.com/account/api-tokens"
-      ],
+      ]
-      "metadata": {
-        "id": "mpHTbTqQ8fey"
-      }
     },
     {
       "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "kDbgfcU8O-dW"
+      },
+      "outputs": [],
       "source": [
         "from litellm import completion\n",
         "import os\n",
         "os.environ['REPLICATE_API_TOKEN'] = ' ' # @param\n",
         "user_message = \"Hello, whats the weather in San Francisco??\"\n",
         "messages = [{ \"content\": user_message,\"role\": \"user\"}]"
-      ],
+      ]
-      "metadata": {
-        "id": "kDbgfcU8O-dW"
-      },
-      "execution_count": 2,
-      "outputs": []
     },
     {
+      "attachments": {},
       "cell_type": "markdown",
-      "source": [
-        "## Call Replicate Models using completion(model, messages) - chatGPT format"
-      ],
       "metadata": {
         "id": "1KmkOdzLSOmJ"
-      }
+      },
+      "source": [
+        "## Call Replicate Models using completion(model, messages) - chatGPT format"
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": 3,
-        "stability_ai = \"stability-ai/stablelm-tuned-alpha-7b:c49dae362cbaecd2ceabb5bd34fdb68413c4ff775111fea065d259d577757beb\"\n",
-        "llama_2 = \"replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1\"\n",
-        "llama_2_7b = \"a16z-infra/llama-2-7b-chat:4f0b260b6a13eb53a6b1891f089d57c08f41003ae79458be5011303d81a394dc\"\n",
-        "dolly_v2 = \"replicate/dolly-v2-12b:ef0e1aefc61f8e096ebe4db6b2bacc297daf2ef6899f0f7e001ec445893500e5\"\n",
-        "vicuna = \"replicate/vicuna-13b:6282abe6a492de4145d7bb601023762212f9ddbbe78278bd6771c8b3b2f2a13b\"\n",
-        "models = [stability_ai, llama_2, llama_2_7b, dolly_v2, vicuna]\n",
-        "for model in models:\n",
-        "  response = completion(model=model, messages=messages, replicate=True)\n",
-        "  print(f\"Response from {model} \\n]\\n\")\n",
-        "  print(response)"
-      ],
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -100,11 +78,10 @@
         "id": "XJ4nh4SnRzHP",
         "outputId": "986c0544-bb40-4915-f00f-498b0e518307"
       },
-      "execution_count": 3,
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "replicate is not installed. Installing...\n",
             "Response from stability-ai/stablelm-tuned-alpha-7b:c49dae362cbaecd2ceabb5bd34fdb68413c4ff775111fea065d259d577757beb \n",
@@ -129,17 +106,22 @@
             "{'choices': [{'finish_reason': 'stop', 'index': 0, 'message': {'role': 'assistant', 'content': ''}}], 'created': 1691611752.8998356, 'model': 'replicate/vicuna-13b:6282abe6a492de4145d7bb601023762212f9ddbbe78278bd6771c8b3b2f2a13b', 'usage': {'prompt_tokens': 9, 'completion_tokens': 0, 'total_tokens': 9}}\n"
           ]
         }
+      ],
+      "source": [
+        "llama_2 = \"replicate/llama-2-70b-chat:2c1608e18606fad2812020dc541930f2d0495ce32eee50074220b87300bc16e1\"\n",
+        "llama_2_7b = \"a16z-infra/llama-2-7b-chat:4f0b260b6a13eb53a6b1891f089d57c08f41003ae79458be5011303d81a394dc\"\n",
+        "dolly_v2 = \"replicate/dolly-v2-12b:ef0e1aefc61f8e096ebe4db6b2bacc297daf2ef6899f0f7e001ec445893500e5\"\n",
+        "vicuna = \"replicate/vicuna-13b:6282abe6a492de4145d7bb601023762212f9ddbbe78278bd6771c8b3b2f2a13b\"\n",
+        "models = [llama_2, llama_2_7b, dolly_v2, vicuna]\n",
+        "for model in models:\n",
+        "  response = completion(model=model, messages=messages)\n",
+        "  print(f\"Response from {model} \\n]\\n\")\n",
+        "  print(response)"
       ]
     },
     {
       "cell_type": "code",
-      "source": [
+      "execution_count": 4,
-        "# @title Stream Responses from Replicate - Outputs in the same format used by chatGPT streaming\n",
-        "response = completion(model=stability_ai, messages=messages, replicate=True, stream=True)\n",
-        "\n",
-        "for chunk in response:\n",
-        "  print(chunk['choices'][0]['delta'])"
-      ],
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
@@ -147,11 +129,10 @@
         "id": "zlTVLB-7PTV_",
         "outputId": "5182275b-3108-46fa-a2cf-745fac4ad110"
       },
-      "execution_count": 4,
       "outputs": [
         {
-          "output_type": "stream",
           "name": "stdout",
+          "output_type": "stream",
           "text": [
             "Hi\n",
             " there!\n",
@@ -221,16 +202,37 @@
             " breezes.<|USER|>\n"
           ]
         }
+      ],
+      "source": [
+        "# @title Stream Responses from Replicate - Outputs in the same format used by chatGPT streaming\n",
+        "response = completion(model=llama_2, messages=messages, stream=True)\n",
+        "\n",
+        "for chunk in response:\n",
+        "  print(chunk['choices'][0]['delta'])"
       ]
     },
     {
       "cell_type": "code",
-      "source": [],
+      "execution_count": null,
       "metadata": {
         "id": "t7WMRuL-8NrO"
       },
-      "execution_count": null,
+      "outputs": [],
-      "outputs": []
+      "source": []
     }
-  ]
+  ],
-}
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}