From c4521f9e63327d5e3f91b80c6506172d3503979d Mon Sep 17 00:00:00 2001 From: SangamSwadiK <35230623+SangamSwadiK@users.noreply.github.com> Date: Sat, 2 Mar 2024 12:59:09 +0530 Subject: [PATCH 1/2] Fix link in getting started notebook --- docs/guardrails_ai/getting_started.ipynb | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/guardrails_ai/getting_started.ipynb b/docs/guardrails_ai/getting_started.ipynb index 2c9c46680..627dccd88 100644 --- a/docs/guardrails_ai/getting_started.ipynb +++ b/docs/guardrails_ai/getting_started.ipynb @@ -154,7 +154,7 @@ "source": [ "#### Specifying quality criteria\n", "\n", - "Next, we want to specify the quality criteria for the output to be valid and corrective actions to be taken if the output is invalid. We can do this by adding a `format` tag to each field in the output schema. Format tags can either be enforced by Guardrails, or they can only be suggetions to the LLM. You can see the list of validators enforced by Guardrails [here](../api_reference_markdown/validators.md). Additionally, you can create your own custom validators, see examples here [1](../examples/no_secrets_in_generated_text), [2](../examples/recipe_generation), [3](../examples/valid_chess_moves).\n", + "Next, we want to specify the quality criteria for the output to be valid and corrective actions to be taken if the output is invalid. We can do this by adding a `format` tag to each field in the output schema. Format tags can either be enforced by Guardrails, or they can only be suggetions to the LLM. You can see the list of validators enforced by Guardrails [here](../api_reference/validators.md). Additionally, you can create your own custom validators, see examples here [1](../examples/no_secrets_in_generated_text), [2](../examples/recipe_generation), [3](../examples/valid_chess_moves).\n", "\n", "As an example, for our use case we specify that the `affected_area` of `symptoms` should be one of the following: `['head', 'neck', 'chest']`. For this, we use the [`valid-choices` validator](https://www.guardrailsai.com/docs/api_reference_markdown/validators#validchoices).\n", "\n", From 02f819989619240ca7ee8cf196cbeb348a718221 Mon Sep 17 00:00:00 2001 From: Caleb Courier Date: Tue, 5 Mar 2024 08:57:28 -0600 Subject: [PATCH 2/2] fix other links --- docs/guardrails_ai/getting_started.ipynb | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/docs/guardrails_ai/getting_started.ipynb b/docs/guardrails_ai/getting_started.ipynb index 627dccd88..55e52be4c 100644 --- a/docs/guardrails_ai/getting_started.ipynb +++ b/docs/guardrails_ai/getting_started.ipynb @@ -154,9 +154,9 @@ "source": [ "#### Specifying quality criteria\n", "\n", - "Next, we want to specify the quality criteria for the output to be valid and corrective actions to be taken if the output is invalid. We can do this by adding a `format` tag to each field in the output schema. Format tags can either be enforced by Guardrails, or they can only be suggetions to the LLM. You can see the list of validators enforced by Guardrails [here](../api_reference/validators.md). Additionally, you can create your own custom validators, see examples here [1](../examples/no_secrets_in_generated_text), [2](../examples/recipe_generation), [3](../examples/valid_chess_moves).\n", + "Next, we want to specify the quality criteria for the output to be valid and corrective actions to be taken if the output is invalid. We can do this by adding a `format` tag to each field in the output schema. Format tags can either be enforced by Guardrails, or they can only be suggetions to the LLM. You can see the list of validators enforced by Guardrails [here](../hub/api_reference_markdown/validators.md). Additionally, you can create your own custom validators, see examples here [1](../examples/no_secrets_in_generated_text), [2](../examples/recipe_generation), [3](../examples/valid_chess_moves).\n", "\n", - "As an example, for our use case we specify that the `affected_area` of `symptoms` should be one of the following: `['head', 'neck', 'chest']`. For this, we use the [`valid-choices` validator](https://www.guardrailsai.com/docs/api_reference_markdown/validators#validchoices).\n", + "As an example, for our use case we specify that the `affected_area` of `symptoms` should be one of the following: `['head', 'neck', 'chest']`. For this, we use the [`valid-choices` validator](https://www.guardrailsai.com/docs/hub/api_reference_markdown/validators#validchoices).\n", "\n", "\n", "#### Specifying corrective actions\n", @@ -165,7 +165,7 @@ "\n", "For example, we can specify that if the `affected_area` of a symptom is not one of the valid choices, we should re-prompt the LLM to correct its output.\n", "\n", - "We do this by adding the `on-fail-valid-choices='reask'` attribute to the `affected_area` field. To see the full list of corrective actions, see [here](https://www.guardrailsai.com/docs/concepts/output#%EF%B8%8F-specifying-corrective-actions).\n", + "We do this by adding the `on-fail-valid-choices='reask'` attribute to the `affected_area` field. To see the full list of corrective actions, see [here](https://www.guardrailsai.com/docs/hub/concepts/on_fail_policies).\n", "\n", "\n", "Finally, our updated output schema looks like:" @@ -1977,7 +1977,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.9.17" + "version": "3.11.7" }, "orig_nbformat": 4, "vscode": {