updated some wording and typos. Also updated to not hard-code model name (#45)

* updated some wording and typos. Also updated to not hard-code model name

* nbfmt and fixed chat notebook reference to text

---------

Co-authored-by: Mark Daoust <[email protected]>

Author: soosung80

site/en/examples/chat_calculator.ipynb

@@ -11,7 +11,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "metadata": {
         "cellView": "form",
         "id": "tuOe1ymfHZPu"
@@ -65,25 +65,43 @@
         "id": "D64fjiFDke_P"
       },
       "source": [
-        "In some cases you might want to stop the generation.\n",
+        "For some use cases, you may want to stop the generation from a model to insert specific results. For example, language models may have trouble with complicated arithmetic problems like word problems.\n",
+        "This tutorial shows an example of using an external tool with the `palm.chat` method to output the correct answer to a word problem.\n",
         "\n",
-        "For example, models like this may have trouble with harder arithmetic, like this version of the problem:"
+        "This particular example uses the [`numexpr`](https://github.com/pydata/numexpr) tool to perform the arithmetic but you can use this same procedure to integrate other tools specific to your use case. The following is an outline of the steps:\n",
+        "\n",
+        "1. Determine a `start` and `end` tag to demarcate the text to send the tool.\n",
+        "1. Create a prompt instructing the model how to use the tags in its response.\n",
+        "1. From the model response, take the text between the `start` and `end` tags as input to the tool.\n",
+        "1. Drop everything after the `end` tag.\n",
+        "1. Run the tool and add it's output as your reply.\n",
+        "1. The model will take into account the tools's output in its reply."
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 24,
+      "execution_count": null,
       "metadata": {
         "id": "v8d0FtO2KJ3O"
       },
-      "outputs": [],
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m122.2/122.2 kB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m113.3/113.3 kB\u001b[0m \u001b[31m5.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
+            "\u001b[?25h"
+          ]
+        }
+      ],
       "source": [
         "pip install -q google.generativeai"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 26,
+      "execution_count": null,
       "metadata": {
         "id": "TxbqsnIWRheU"
       },
@@ -94,7 +112,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 27,
+      "execution_count": null,
       "metadata": {
         "id": "BH9oQzP2SD4L"
       },
@@ -113,7 +131,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 28,
+      "execution_count": null,
       "metadata": {
         "id": "VQK6KRDpKD8g"
       },
@@ -125,7 +143,20 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 101,
+      "execution_count": null,
+      "metadata": {
+        "id": "UGy1ghOp0ibu"
+      },
+      "outputs": [],
+      "source": [
+        "models = [m for m in palm.list_models() if 'generateMessage' in m.supported_generation_methods]\n",
+        "model = models[0].name\n",
+        "print(model)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
       "metadata": {
         "id": "1TIekNZ1rrOd"
       },
@@ -144,7 +175,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 81,
+      "execution_count": null,
       "metadata": {
         "id": "IRoDEoU1Bq_6"
       },
@@ -177,8 +208,8 @@
       ],
       "source": [
         "response = retry_chat(\n",
-        "    model=\"models/chat-bison-001\",\n",
-        "    context=\"You are an expert at solving word problems.\"\n",
+        "    model=model,\n",
+        "    context=\"You are an expert at solving word problems.\",\n",
         "    messages=question,\n",
         ")\n",
         "\n",
@@ -191,15 +222,15 @@
         "id": "zG4bukqCIQ4f"
       },
       "source": [
-        "Just like that, it's usually incorrect.\n",
+        "The prompt as is usually generates incorrect results.\n",
         "It generally gets the steps right but the arithmetic wrong.\n",
         "\n",
         "The answer should be:"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 82,
+      "execution_count": null,
       "metadata": {
         "id": "9Jw0L9OoCAHZ"
       },
@@ -226,12 +257,12 @@
         "id": "91LETezvs6LU"
       },
       "source": [
-        "So give the model access to a calculator. You can do that by adding something like this to the prompt:"
+        "In this next attempt, give the model instructions on how to access the calculator. You can do that by specifying a `start` and `end` tag the model can use to indicate where a calculation is needed. Add something like the following to the prompt:"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": 102,
+      "execution_count": null,
       "metadata": {
         "id": "kjrZYUE7N5N6"
       },
@@ -271,7 +302,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 84,
+      "execution_count": null,
       "metadata": {
         "id": "lbLNQfHVK0bO"
       },
@@ -304,7 +335,7 @@
       ],
       "source": [
         "chat = retry_chat(\n",
-        "    model=\"models/chat-bison-001\",\n",
+        "    model=model,\n",
         "    messages=calc_prompt,\n",
         ")\n",
         "\n",
@@ -322,7 +353,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 85,
+      "execution_count": null,
       "metadata": {
         "id": "K9Y0Z-Lome0P"
       },
@@ -352,7 +383,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 93,
+      "execution_count": null,
       "metadata": {
         "id": "sGDNIvkkQjw8"
       },
@@ -384,7 +415,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 94,
+      "execution_count": null,
       "metadata": {
         "id": "BC7TfMIu-9Ci"
       },
@@ -419,15 +450,15 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 98,
+      "execution_count": null,
       "metadata": {
         "id": "PFXRsjvNMUyv"
       },
       "outputs": [],
       "source": [
         "def solve():\n",
         "  chat = retry_chat(\n",
-        "      model=\"models/chat-bison-001\",\n",
+        "      model=model,\n",
         "      context=\"You are an expert at solving word probles.\",\n",
         "      messages=calc_prompt,\n",
         "  )\n",
@@ -456,7 +487,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 103,
+      "execution_count": null,
       "metadata": {
         "id": "Syf10WrLmopr"
       },
@@ -522,7 +553,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 104,
+      "execution_count": null,
       "metadata": {
         "id": "jM-TRySbOz3k"
       },
@@ -713,7 +744,7 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 105,
+      "execution_count": null,
       "metadata": {
         "id": "5vaOADwUWgQd"
       },