Merge pull request #232 from Azure-Samples/workshop_details

adding updates to workshop

docs/workshop/LAB-SETUP.ipynb

@@ -62,7 +62,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "! echo Y | GITHUB_TOKEN=\"\" gh auth login --hostname github.com --git-protocol https --web"
+    "! echo Y | GITHUB_TOKEN=\"\" gh auth login --hostname github.com --git-protocol https --web --scopes workflow "
    ]
   },
   {
@@ -206,11 +206,7 @@
    "metadata": {},
    "source": [
     "6. Run the postprovision script by running the cell below\n",
-    "\n",
-    "> ⏰ **TIP to save time**: \n",
-    "> - This script will take about 6-10mins to run. \n",
-    "> - You do not need to wait until the script completes to start reading through the first notebook.\n",
-    "> - Head to [workshop-1-intro.ipynb](workshop-1-intro.ipynb) once you've run the cell below and get started!"
+    "    - This script will take about 3 mins to run. "
    ]
   },
   {

docs/workshop/researcher/researcher-0.prompty

@@ -12,7 +12,7 @@ model:
     azure_deployment: gpt-35-turbo
     api_version: 2023-07-01-preview
 sample:
-  instructions: Can you generate queries to find the latest camping trends and what folks are doing in the winter? Use 'en-US' as the market code. 
+  instructions: Can you generate queries to find the latest winter camping trends? Use 'en-US' as the market code. 
 ---
 system:
 # Researcher Agent

docs/workshop/workshop-1-intro.ipynb

@@ -112,17 +112,12 @@
     "</div>\n",
     "\n",
     "\n",
-    "> - [**Step 1:** Build a multi-lingual query generator](#step-1-build-a-multi-lingual-query-generator)\n",
-    "> - [**Step 2:** Understanding LLM function calling with Prompty](#step-2-understanding-llm-function-calling-with-prompty)\n",
-    "> - [**Step 3:** Build the tools and execute the research](#step-3-build-the-functions-and-execute-the-research)\n",
+    "> - **Step 1:** Build a multi-lingual query generator\n",
+    "> - **Step 2:** Understanding LLM function calling with Prompty\n",
+    "> - **Step 3:** Build the tools and execute the research\n",
     "\n",
     "<br>\n",
     "\n",
-    "> **🚧 IMPORTANT**: **Before you start with step 1**:\n",
-    "> - Check to see if the last script from the [LAB-SETUP.ipynb](./LAB-SETUP.ipynb) notebook has completed succesefully. \n",
-    "> - If it has click the **🔄 Restart** button at the top of the notebook. \n",
-    "> - If it has not, wait a few minutes until it has to continue as this will provide the dependencies you need\n",
-    "\n",
     "Let's start with step 1. \n",
     "\n",
     "### **Step 1: Build a multi-lingual query generator**\n",
@@ -224,7 +219,7 @@
    "metadata": {},
    "source": [
     "In the result from running the Prompty file we saw that the **find_information** function was selected. \n",
-    "- From it's description in the [functions.json](./researcher/functions.json) file can you understand why it was chosen? \n",
+    "- From its description in the [functions.json](./researcher/functions.json) file can you understand why it was chosen? \n",
     "- Observe that it finds general information on the web. \n",
     "- The LLM used the **instruction** we gave it and the **descriptions** it saw in *functions.json* to pick which function to call.  \n",
     "- It also figured out which parameter values should be passed to the function. \n",
@@ -357,7 +352,8 @@
     "---\n",
     "<img src=\"coding.png\" alt=\"todo icon\" width=\"45\" height=\"45\"> **Run the code:**\n",
     "\n",
-    "> **TODO:** Run the cell below to run the full researcher agent!"
+    "> **TODO:** Run the cell below to run the full researcher agent! \n",
+    "> - Try different instructions and see which results you get and which function is called. "
    ]
   },
   {

docs/workshop/workshop-2-tracing.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## 2. Utilizing Prompty tracing for debugging and observabilty\n",
+    "## 2. Utilizing Prompty tracing for debugging and observability\n",
     "\n",
     "When running Applications driven by LLMs, sometimes things don't go as expected! \n",
     "<br>It's important to have a way to debug your LLM workflow so you can see where things are working. \n",
@@ -113,7 +113,7 @@
     "> **Observations 👀:**\n",
     ">   - This page shows you information that prompty has sent to or recieved from the LLM. \n",
     ">   - In this specific case look at the *Completion Tokens* amount. \n",
-    ">   - This shows only 200 tokens, which is not enough for us to generate a twitter thread. \n",
+    ">   - This shows less than a 1000 tokens, which is not enough for us to generate a twitter thread. \n",
     "\n",
     "<br> \n",
     "\n",