docs: Use Kinetica Sql context API (#21993)

Update python notebook to use new Kinetica SQL context API.

docs/docs/integrations/chat/kinetica.ipynb

@@ -62,10 +62,10 @@
     "%pip install --upgrade --quiet langchain-core langchain-community\n",
     "\n",
     "# Install Kineitca DB connection package\n",
-    "%pip install --upgrade --quiet gpudb typeguard\n",
+    "%pip install --upgrade --quiet 'gpudb>=7.2.0.8' typeguard pandas tqdm\n",
     "\n",
     "# Install packages needed for this tutorial\n",
-    "%pip install --upgrade --quiet faker"
+    "%pip install --upgrade --quiet faker ipykernel "
    ]
   },
   {
@@ -114,7 +114,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -139,11 +139,11 @@
       "\n",
       "    birthdate  \n",
       "id             \n",
-      "0  1997-12-01  \n",
-      "1  1924-07-27  \n",
-      "2  1933-11-28  \n",
-      "3  1988-10-19  \n",
-      "4  1931-03-12  \n"
+      "0  1997-12-08  \n",
+      "1  1924-08-03  \n",
+      "2  1933-12-05  \n",
+      "3  1988-10-26  \n",
+      "4  1931-03-19  \n"
      ]
     }
    ],
@@ -222,39 +222,60 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CREATE OR REPLACE CONTEXT \"demo\".\"test_llm_ctx\" (\n",
+      "    TABLE = \"demo\".\"user_profiles\",\n",
+      "    COMMENT = 'Contains user profiles.'\n",
+      "),\n",
+      "(\n",
+      "    SAMPLES = ( \n",
+      "        'How many male users are there?' = 'select count(1) as num_users\n",
+      "    from demo.user_profiles\n",
+      "    where sex = ''M'';' )\n",
+      ")\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
        "1"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# create an LLM context for the table.\n",
-    "\n",
-    "sql = f\"\"\"\n",
-    "CREATE OR REPLACE CONTEXT {kinetica_ctx}\n",
-    "(\n",
-    "    TABLE = {table_name}\n",
-    "    COMMENT = 'Contains user profiles.'\n",
-    "),\n",
-    "(\n",
-    "    SAMPLES = (\n",
-    "    'How many male users are there?' = \n",
-    "    'select count(1) as num_users\n",
-    "    from {table_name}\n",
-    "    where sex = ''M'';')\n",
+    "from gpudb import GPUdbSamplesClause, GPUdbSqlContext, GPUdbTableClause\n",
+    "\n",
+    "table_ctx = GPUdbTableClause(table=table_name, comment=\"Contains user profiles.\")\n",
+    "\n",
+    "samples_ctx = GPUdbSamplesClause(\n",
+    "    samples=[\n",
+    "        (\n",
+    "            \"How many male users are there?\",\n",
+    "            f\"\"\"\n",
+    "            select count(1) as num_users\n",
+    "                from {table_name}\n",
+    "                where sex = 'M';\n",
+    "            \"\"\",\n",
+    "        )\n",
+    "    ]\n",
     ")\n",
-    "\"\"\"\n",
     "\n",
-    "count_affected = kinetica_llm.kdbc.execute(sql)\n",
+    "context_sql = GPUdbSqlContext(\n",
+    "    name=kinetica_ctx, tables=[table_ctx], samples=samples_ctx\n",
+    ").build_sql()\n",
+    "\n",
+    "print(context_sql)\n",
+    "count_affected = kinetica_llm.kdbc.execute(context_sql)\n",
     "count_affected"
    ]
   },
@@ -273,7 +294,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -334,7 +355,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -357,7 +378,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [
     {
@@ -404,7 +425,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.19"
+   "version": "3.9.19"
   }
  },
  "nbformat": 4,