Added import Giskard and fixed the pip install

docs/integrations/mlflow/mlflow-llm-example.ipynb

@@ -70,7 +70,7 @@
    },
    "outputs": [],
    "source": [
-    "%pip install langchain-openai openai pypdf faiss-cpu tiktoken pyngrok -q"
+    "%pip install langchain langchain-openai openai \"pypdf<=3.17.0\" faiss-cpu tiktoken pyngrok -q"
    ]
   },
   {
@@ -91,6 +91,7 @@
    "outputs": [],
    "source": [
     "import mlflow\n",
+    "import giskard\n",
     "\n",
     "mlflow.models.list_evaluators() # ['default', 'giskard']"
    ]

docs/integrations/mlflow/mlflow-tabular-example.ipynb

@@ -2,6 +2,9 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false
+   },
    "source": [
     "# MLFlow Example - Tabular\n",
     "## Detecting tabular ML models vulnerabilities in MLflow with Giskard\n",
@@ -11,17 +14,18 @@
     "|----------|------------------------------------------------------------------------|-----------------|\n",
     "| `model1` | A simple sklearn `LogisticRegression` model trained only for 5 epochs. | Titanic dataset |\n",
     "| `model2` | A simple sklearn `LogisticRegression` model trained for 100 epochs.    | Titanic dataset |"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "metadata": {
+    "collapsed": false
+   },
    "outputs": [],
    "source": [
     "import mlflow\n",
+    "import giskard\n",
     "\n",
     "from giskard import demo\n",
     "model1, df = demo.titanic(max_iter=5)\n",
@@ -33,13 +37,13 @@
     "    with mlflow.start_run(run_name=model_name) as run:\n",
     "        model_uri = mlflow.sklearn.log_model(model, model_name, pyfunc_predict_fn=\"predict_proba\").model_uri\n",
     "        mlflow.evaluate(model=model_uri, model_type=\"classifier\", data=df, targets=\"Survived\", evaluators=\"giskard\", evaluator_config={\"model_config\":   {\"classification_labels\": [\"no\", \"yes\"]}})"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
+   "metadata": {
+    "collapsed": false
+   },
    "source": [
     "After completing the previous steps, you can run mlflow ui from the directory where the mlruns folder is located, which will enable you to visualize the results. By accessing http://127.0.0.1:5000, you will be presented with the interface. There, you will find the two LLMs logged as separate runs for comparison and analysis.\n",
     "<img src=\"../../assets/integrations/mlflow/tabular/table_view.png\">\n",
@@ -52,17 +56,14 @@
     "\n",
     "A scan summary: After each model evaluation, a scan-summary.json file is created, enabling a comparison of vulnerabilities and metrics for each model in the Artifact view.\n",
     "<img src=\"../../assets/integrations/mlflow/tabular/scan-summary.png\">"
-   ],
-   "metadata": {
-    "collapsed": false
-   }
+   ]
   },
   {
    "cell_type": "markdown",
-   "source": [],
    "metadata": {
     "collapsed": false
-   }
+   },
+   "source": []
   }
  ],
  "metadata": {