Merge pull request #117 from Azure/sept2024

Updating package versions

.env.example

@@ -1,5 +1,5 @@
-OPENAI_API_VERSION = "2023-09-01-preview"
-OPENAI_EMBEDDING_API_VERSION = "2023-05-15"
+OPENAI_API_VERSION = "2024-07-01-preview"
+OPENAI_EMBEDDING_API_VERSION = "2024-07-01-preview"
 
 AZURE_OPENAI_API_KEY = "<YOUR AZURE OPENAI API KEY - If using Azure AD auth, this can be left empty>"
 AZURE_OPENAI_ENDPOINT = "<YOUR AZURE OPENAI ENDPOINT>"

.gitignore

@@ -414,4 +414,4 @@ solutions/AzureOpenAIUtil/
 
 # Qdrant
 .lock
-labs/03-orchestration/03-Qdrant/qdrantstorage/**
+labs/03-orchestration/03-VectorStore/qdrantstorage/**

labs/02-integrating-ai/00-PythonModules/pythonmodules.ipynb

@@ -55,7 +55,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.14"
   },
   "orig_nbformat": 4
  },

labs/02-integrating-ai/01-AzureOpenAIAPI/azureopenaiapi.ipynb

@@ -7,11 +7,7 @@
    "source": [
     "# 01 - Working with the Azure OpenAI API directly\n",
     "\n",
-    "In this lab, we will perform a couple of simple calls to the Azure OpenAI API.\n",
-    "- The first call will allow us to find out which Model Deployments are available for the Azure OpenAI API.\n",
-    "- The second call will send a prompt to the Azure OpenAI API.\n",
-    "\n",
-    "This will also prove that everything is setup correctly and working for the rest of the labs.\n",
+    "In this lab, we will perform a simple call to the Azure OpenAI API. This will prove that everything is setup correctly and working for the rest of the labs.\n",
     "\n",
     "## Setup\n",
     "\n",
@@ -194,7 +190,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.12.5"
+   "version": "3.10.14"
   },
   "orig_nbformat": 4
  },

labs/02-integrating-ai/02-OpenAIPackages/openai.ipynb

@@ -34,7 +34,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Next, we'll start to bring in the values from our `.env` file."
+    "Next, we'll bring in the values from our `.env` file."
    ]
   },
   {
@@ -57,7 +57,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We'll create a new `AzureOpenAI` object and pass in the API key and version and the endpoint URL to be used."
+    "We'll create a new `AzureOpenAI` object and pass in the API key, API version and the endpoint URL to be used."
    ]
   },
   {
@@ -168,7 +168,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.14"
   },
   "orig_nbformat": 4
  },

labs/02-integrating-ai/03-Langchain/langchain.ipynb

@@ -272,7 +272,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.14"
   },
   "orig_nbformat": 4
  },

labs/02-integrating-ai/04-SemanticKernel/semantickernel.ipynb

@@ -32,7 +32,7 @@
    },
    "outputs": [],
    "source": [
-    "#r \"nuget: dotenv.net, 3.1.2\"\n",
+    "#r \"nuget: dotenv.net, 3.2.0\"\n",
     "\n",
     "using dotenv.net;\n",
     "\n",
@@ -76,7 +76,7 @@
    },
    "outputs": [],
    "source": [
-    "#r \"nuget: Microsoft.SemanticKernel, 1.10.0\""
+    "#r \"nuget: Microsoft.SemanticKernel, 1.19.0\""
    ]
   },
   {
@@ -91,7 +91,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "metadata": {
     "dotnet_interactive": {
      "language": "csharp"
@@ -125,6 +125,12 @@
    "cell_type": "code",
    "execution_count": null,
    "metadata": {
+    "dotnet_interactive": {
+     "language": "csharp"
+    },
+    "polyglot_notebook": {
+     "kernelName": "csharp"
+    },
     "vscode": {
      "languageId": "polyglot-notebook"
     }
@@ -144,7 +150,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "metadata": {
     "dotnet_interactive": {
      "language": "csharp"
@@ -213,7 +219,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 7,
    "metadata": {
     "dotnet_interactive": {
      "language": "csharp"
@@ -286,10 +292,26 @@
   }
  ],
  "metadata": {
+  "kernelspec": {
+   "display_name": ".NET (C#)",
+   "language": "C#",
+   "name": ".net-csharp"
+  },
   "language_info": {
    "name": "python"
   },
-  "orig_nbformat": 4
+  "orig_nbformat": 4,
+  "polyglot_notebook": {
+   "kernelInfo": {
+    "defaultKernelName": "csharp",
+    "items": [
+     {
+      "aliases": [],
+      "name": "csharp"
+     }
+    ]
+   }
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 2

labs/03-orchestration/01-Tokens/tokens.ipynb

@@ -62,9 +62,9 @@
     "\n",
     "| Encoding name | Azure OpenAI Service models |\n",
     "| ------------- | -------------- |\n",
-    "| gpt2 (or r50k_base) | Most GPT-3 models |\n",
+    "| cl100k_base | gpt-4, gpt-3.5-turbo, text-embedding-ada-002, text-embedding-3-small, text-embedding-3-large |\n",
     "| p50k_base | Code models, text-davinci-002, text-davinci-003 |\n",
-    "| cl100k_base | text-embedding-ada-002 |\n",
+    "| r50k_base (or gpt2) | Most GPT-3 models |\n",
     "\n",
     "You can use `tiktoken` as follows to tokenize a string and see what the output looks like."
    ]
@@ -77,7 +77,7 @@
    "source": [
     "import tiktoken\n",
     "\n",
-    "encoding = tiktoken.get_encoding(\"p50k_base\")\n",
+    "encoding = tiktoken.get_encoding(\"cl100k_base\")\n",
     "encoding.encode(\"Hello world, this is fun!\")"
    ]
   },
@@ -141,7 +141,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "def get_num_tokens_from_string(string: str, encoding_name: str='p50k_base') -> int:\n",
+    "def get_num_tokens_from_string(string: str, encoding_name: str='cl100k_base') -> int:\n",
     "    \"\"\"Returns the number of tokens in a text by a given encoding.\"\"\"\n",
     "    encoding = tiktoken.get_encoding(encoding_name)\n",
     "    return len(encoding.encode(string))\n",
@@ -183,7 +183,7 @@
     "content = open(movie_data, \"r\", encoding=\"utf-8\").read()\n",
     "\n",
     "# Use tiktoken to tokenize the content and get a count of tokens used.\n",
-    "encoding = tiktoken.get_encoding(\"p50k_base\")\n",
+    "encoding = tiktoken.get_encoding(\"cl100k_base\")\n",
     "print (f\"Token count: {len(encoding.encode(content))}\")"
    ]
   },
@@ -199,7 +199,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -245,7 +245,7 @@
    "source": [
     "You can see we've output the first few lines of the prompt and we've printed the overall size (in characters) of the prompt. Now, let's see what happens if we submit that query to the AI.\n",
     "\n",
-    "**NOTE:** Don't be surprised to see an error message!"
+    "**NOTE:** This exercise is intended to fail, but it does depend on the model you're using. Some newer models have a higher token limit than others. If you're using a model with a high token limit, you might want to increase the size of the `movies.csv` file to make this fail, or you could try using a different model."
    ]
   },
   {
@@ -322,7 +322,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.9"
+   "version": "3.10.14"
   },
   "orig_nbformat": 4
  },