update more notebooks

Author: aaravnavani

docs/examples/secrets_detection.ipynb

@@ -6,7 +6,7 @@
    "source": [
     "## Check whether an LLM-generated code response contains secrets\n",
     "\n",
-    "### Using the `DetectSecrets` validator\n",
+    "### Using the `SecretsPresent` validator\n",
     "\n",
     "This is a simple walkthrough of how to use the `DetectSecrets` validator to check whether an LLM-generated code response contains secrets. It utilizes the `detect-secrets` library, which is a Python library that scans code files for secrets. The library is available on GitHub at [this link](https://github.com/Yelp/detect-secrets).\n"
    ]
@@ -31,9 +31,18 @@
     "! pip install detect-secrets -q"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We also need to install the ```SecretsPresent``` validator from Guardrails Hub: \n",
+    "\n",
+    "```guardrails hub install hub://guardrails/secrets_present```"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [
     {
@@ -47,9 +56,10 @@
    ],
    "source": [
     "# Import the guardrails package\n",
-    "# and the DetectSecrets validator\n",
+    "# and import the SecretsPresent validator\n",
+    "# from Guardrails Hub\n",
     "import guardrails as gd\n",
-    "from guardrails.validators import DetectSecrets\n",
+    "from guardrails.hub import SecretsPresent\n",
     "from rich import print"
    ]
   },
@@ -64,7 +74,7 @@
     "# if the validator detects secrets\n",
     "\n",
     "guard = gd.Guard.from_string(\n",
-    "    validators=[DetectSecrets(on_fail=\"fix\")],\n",
+    "    validators=[SecretsPresent(on_fail=\"fix\")],\n",
     "    description=\"testmeout\",\n",
     ")"
    ]
@@ -207,7 +217,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "#### In this way, you can use the `DetectSecrets` validator to check whether an LLM-generated code response contains secrets. With Guardrails as wrapper, you can be assured that the secrets in the code will be detected and masked and not be exposed.\n"
+    "#### In this way, you can use the `SecretsPresent` validator to check whether an LLM-generated code response contains secrets. With Guardrails as wrapper, you can be assured that the secrets in the code will be detected and masked and not be exposed.\n"
    ]
   }
  ],

docs/examples/select_choice_based_on_action.ipynb

@@ -20,6 +20,11 @@
     "\n",
     "We want the LLM to play an RP game where it can choose to either `fight` or `flight`. If it chooses to `fight`, the LLM should choose a `weapon` and an `enemy`. If the player chooses `flight`, the LLM should choose a `direction` and a `distance`.\n",
     "\n",
+    "## Step 0: Install the ```ValidChoices``` validator from Guardrails Hub \n",
+    "\n",
+    "We first have to install the ```ValidChices``` validator from Guardrails Hub: \n",
+    "\n",
+    "```guardrails hub install hub://guardrails/valid_choices```\n",
     "\n",
     "## Step 1: Generating `RAIL` Spec\n",
     "\n",
@@ -83,7 +88,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from guardrails.validators import ValidChoices\n",
+    "from guardrails.hub import ValidChoices\n",
     "from pydantic import BaseModel, Field\n",
     "from typing import Literal, Union\n",
     "\n",

docs/examples/syntax_error_free_sql.ipynb

@@ -41,6 +41,15 @@
     "! pip install sqlvalidator"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We also need to install the ```ValidSQL``` validator from Guardrails Hub: \n",
+    "\n",
+    "```guardrails hub install hub://guardrails/valid_sql```"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -117,7 +126,7 @@
     }
    ],
    "source": [
-    "from guardrails.validators import BugFreeSQL\n",
+    "from guardrails.hub import ValidSQL\n",
     "from pydantic import BaseModel, Field\n",
     "\n",
     "prompt = \"\"\"\n",
@@ -130,7 +139,7 @@
     "\"\"\"\n",
     "\n",
     "class ValidSql(BaseModel):\n",
-    "    generated_sql: str = Field(description=\"Generate SQL for the given natural language instruction.\", validators=[BugFreeSQL(on_fail=\"reask\")])"
+    "    generated_sql: str = Field(description=\"Generate SQL for the given natural language instruction.\", validators=[ValidSQL(on_fail=\"reask\")])"
    ]
   },
   {

docs/examples/text_summarization_quality.ipynb

@@ -38,6 +38,15 @@
     "!pip install numpy"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "We also need to install the ```SimilarToDocument``` validator from Guardrails Hub: \n",
+    "\n",
+    "```guardrails hub install hub://guardrails/similar_to_document```"
+   ]
+  },
   {
    "attachments": {},
    "cell_type": "markdown",
@@ -123,7 +132,7 @@
    "outputs": [],
    "source": [
     "from pydantic import BaseModel, Field\n",
-    "from guardrails.validators import SimilarToDocument\n",
+    "from guardrails.hub import SimilarToDocument\n",
     "\n",
     "prompt = \"\"\"\n",
     "Summarize the following document:\n",

docs/examples/toxic_language.ipynb

@@ -8,19 +8,24 @@
     "\n",
     "### Using the `ToxicLanguage` validator\n",
     "\n",
-    "This is a simple walkthrough of the `ToxicLanguage` validator. This validator checks whether an LLM-generated response contains toxic language. It uses the pre-trained multi-label model from HuggingFace -`unitary/unbiased-toxic-roberta` to check whether the generated text is toxic. It supports both full-text-level and sentence-level validation.\n"
+    "This is a simple walkthrough of the `ToxicLanguage` validator. This validator checks whether an LLM-generated response contains toxic language. It uses the pre-trained multi-label model from HuggingFace -`unitary/unbiased-toxic-roberta` to check whether the generated text is toxic. It supports both full-text-level and sentence-level validation.\n",
+    "\n",
+    "We first need to install the ```ToxicLanguage``` validator from Guardrails Hub: \n",
+    "\n",
+    "```guardrails hub install hub://guardrails/toxic_language```"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "# Import the guardrails package\n",
     "# and the ToxicLanguage validator\n",
+    "# from Guardrails Hub\n",
     "import guardrails as gd\n",
-    "from guardrails.validators import ToxicLanguage\n",
+    "from guardrails.hub import ToxicLanguage\n",
     "from rich import print"
    ]
   },