From 18ce230e0d9c1b6f3522d0c1a21373049bfccf48 Mon Sep 17 00:00:00 2001 From: Aarav Navani <38411399+aaravnavani@users.noreply.github.com> Date: Fri, 15 Mar 2024 19:50:29 -0700 Subject: [PATCH] Fix broken links in docs (#640) * fix broken links * guardrails hub * fix example links * add valid-choices validator * add list of corrective actions * fix logs * fix comments * fix lint * fix existing change --------- Co-authored-by: Aarav Navani <38411399+oofmeister27@users.noreply.github.com> --- docs/examples/extracting_entities.ipynb | 2 +- docs/examples/guardrails_with_chat_models.ipynb | 2 +- docs/examples/no_secrets_in_generated_text.ipynb | 4 ++-- docs/examples/recipe_generation.ipynb | 2 +- docs/examples/syntax_error_free_sql.ipynb | 2 +- docs/examples/text_summarization_quality.ipynb | 2 +- docs/examples/translation_to_specific_language.ipynb | 2 +- docs/examples/translation_with_quality_check.ipynb | 2 +- docs/examples/valid_chess_moves.ipynb | 2 +- docs/guardrails_ai/getting_started.ipynb | 6 +++--- docs/how_to_guides/logs.md | 4 +--- docs/index.md | 2 +- 12 files changed, 15 insertions(+), 17 deletions(-) diff --git a/docs/examples/extracting_entities.ipynb b/docs/examples/extracting_entities.ipynb index 72eecddbb..30537fbbb 100644 --- a/docs/examples/extracting_entities.ipynb +++ b/docs/examples/extracting_entities.ipynb @@ -77,7 +77,7 @@ "source": [ "## Step 1: Create the RAIL Spec\n", "\n", - "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/concepts/output.md). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", + "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/docs/how_to_guides/rail). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", "\n", "Here, we request:\n", "\n", diff --git a/docs/examples/guardrails_with_chat_models.ipynb b/docs/examples/guardrails_with_chat_models.ipynb index ea47425a5..2769b8545 100644 --- a/docs/examples/guardrails_with_chat_models.ipynb +++ b/docs/examples/guardrails_with_chat_models.ipynb @@ -14,7 +14,7 @@ "\n", "## Objective\n", "\n", - "We retry the [entity extraction example](./extracting_entities/pydantic) using a chat model.\n", + "We retry the [entity extraction example](./extracting_entities.ipynb) using a chat model.\n", "\n", "## Step 0: Download PDF and load it as string\n", "\n", diff --git a/docs/examples/no_secrets_in_generated_text.ipynb b/docs/examples/no_secrets_in_generated_text.ipynb index 65a97b56d..f90372c0e 100644 --- a/docs/examples/no_secrets_in_generated_text.ipynb +++ b/docs/examples/no_secrets_in_generated_text.ipynb @@ -26,11 +26,11 @@ "source": [ "## Step 1: Create the RAIL Spec\n", "\n", - "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/concepts/output.md). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", + "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/docs/how_to_guides/rail). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", "\n", "In this RAIL spec, we:\n", "\n", - "1. Create a custom Validator that checks if a string has any secrets. This is a simple example, but you can use this to create more complex Validators. For more information on creating custom Validators, see the [Validators documentation](/concepts/validators.md).\n", + "1. Create a custom Validator that checks if a string has any secrets. This is a simple example, but you can use this to create more complex Validators. For more information on creating custom Validators, see the [Validators documentation](/docs/hub/how_to_guides/custom_validator).\n", "2. Create a `output` schema that returns an object with a `api_help` key." ] }, diff --git a/docs/examples/recipe_generation.ipynb b/docs/examples/recipe_generation.ipynb index 8d26dba7b..7996df62e 100644 --- a/docs/examples/recipe_generation.ipynb +++ b/docs/examples/recipe_generation.ipynb @@ -34,7 +34,7 @@ "source": [ "## Step 1: Create the RAIL Spec\n", "\n", - "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/concepts/output.md). We will also show the same RAIL spec in a code-first format using a Pydantic model." + "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/docs/how_to_guides/rail). We will also show the same RAIL spec in a code-first format using a Pydantic model." ] }, { diff --git a/docs/examples/syntax_error_free_sql.ipynb b/docs/examples/syntax_error_free_sql.ipynb index d8fa5a5c2..1137ba750 100644 --- a/docs/examples/syntax_error_free_sql.ipynb +++ b/docs/examples/syntax_error_free_sql.ipynb @@ -48,7 +48,7 @@ "source": [ "## Step 1: Create the RAIL Spec\n", "\n", - "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/concepts/output.md). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", + "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/docs/how_to_guides/rail). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", "\n", "In this RAIL spec, we:\n", "\n", diff --git a/docs/examples/text_summarization_quality.ipynb b/docs/examples/text_summarization_quality.ipynb index 39417f631..5104663fe 100644 --- a/docs/examples/text_summarization_quality.ipynb +++ b/docs/examples/text_summarization_quality.ipynb @@ -45,7 +45,7 @@ "source": [ "## Step 1: Create the RAIL Spec\n", "\n", - "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/concepts/output.md). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", + "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/docs/how_to_guides/rail). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", "\n", "In this RAIL spec, we:\n", "\n", diff --git a/docs/examples/translation_to_specific_language.ipynb b/docs/examples/translation_to_specific_language.ipynb index f814fa1ee..92ac88f8c 100644 --- a/docs/examples/translation_to_specific_language.ipynb +++ b/docs/examples/translation_to_specific_language.ipynb @@ -54,7 +54,7 @@ "source": [ "## Step 1: Create the RAIL Spec\n", "\n", - "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/concepts/output.md). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", + "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/docs/how_to_guides/rail). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", "\n", "In this RAIL spec, we:\n", "\n", diff --git a/docs/examples/translation_with_quality_check.ipynb b/docs/examples/translation_with_quality_check.ipynb index d38206224..e2abdf2f6 100644 --- a/docs/examples/translation_with_quality_check.ipynb +++ b/docs/examples/translation_with_quality_check.ipynb @@ -45,7 +45,7 @@ "source": [ "## Step 1: Create the RAIL Spec / Pydantic model\n", "\n", - "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](../concepts/output.md). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", + "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/docs/how_to_guides/rail). We will also show the same RAIL spec in a code-first format using a Pydantic model.\n", "\n", "In this RAIL spec, we:\n", "\n", diff --git a/docs/examples/valid_chess_moves.ipynb b/docs/examples/valid_chess_moves.ipynb index 134bd1baa..46b5a5c44 100644 --- a/docs/examples/valid_chess_moves.ipynb +++ b/docs/examples/valid_chess_moves.ipynb @@ -54,7 +54,7 @@ "source": [ "## Step 1: Create the RAIL Spec\n", "\n", - "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/concepts/output.md). We will also show the same RAIL spec in a code-first format using a Pydantic model." + "Ordinarily, we would create an RAIL spec in a separate file. For the purposes of this example, we will create the spec in this notebook as a string following the RAIL syntax. For more information on RAIL, see the [RAIL documentation](/docs/how_to_guides/rail). We will also show the same RAIL spec in a code-first format using a Pydantic model." ] }, { diff --git a/docs/guardrails_ai/getting_started.ipynb b/docs/guardrails_ai/getting_started.ipynb index 55e52be4c..4cf1c9cba 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](../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", + "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](https://hub.guardrailsai.com/validator/guardrails/valid_choices). Additionally, you can create your own custom validators, see examples here [1](../examples/no_secrets_in_generated_text.ipynb), [2](../examples/recipe_generation.ipynb), [3](../examples/valid_chess_moves.ipynb).\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/hub/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://hub.guardrailsai.com/validator/guardrails/valid_choice).\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/hub/concepts/on_fail_policies).\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](/docs/hub/concepts/on_fail_policies).\n", "\n", "\n", "Finally, our updated output schema looks like:" diff --git a/docs/how_to_guides/logs.md b/docs/how_to_guides/logs.md index 87eb647bc..567e555eb 100644 --- a/docs/how_to_guides/logs.md +++ b/docs/how_to_guides/logs.md @@ -4,8 +4,6 @@ All `Guard` calls are logged internally, and can be accessed via the guard histo ## Accessing logs via `Guard.history` -`history` is an attribute of the `Guard` class. It implements a standard `Stack` interface with a few extra helper methods and properties. For more information on our `Stack` implementation see the [Helper Classes](/docs/api_reference_markdown/helper_classes) page. - Each entry in the history stack is a `Call` log which will contain information specific to a particular `Guard.__call__` or `Guard.parse` call in the order that they were executed within the current session. For example, if you have a guard: @@ -119,7 +117,7 @@ llm responses } ``` -For more information on `Call`, see the [History & Logs](/api_reference/history_and_logs/#guardrails.classes.history.Call) page. +For more information on `Call`, see the [History & Logs](/docs/api_reference_markdown/history_and_logs) page. ## 🇻🇦 Accessing logs from individual steps In addition to the cumulative values available directly on the `Call` log, it also contains a `Stack` of `Iteration`'s. Each `Iteration` represent the logs from within a step in the guardrails process. This includes the call to the LLM, as well as parsing and validating the LLM's response. diff --git a/docs/index.md b/docs/index.md index 1b3081060..5b7d9af9d 100644 --- a/docs/index.md +++ b/docs/index.md @@ -16,7 +16,7 @@ Guardrails AI is the leading open-source framework to define and enforce assuran Guardrails provides an object definition called a `Rail` for enforcing a specification on an LLM output, and a lightweight wrapper called a `Guard` around LLM API calls to implement this spec. -1. `rail` (**R**eliable **AI** markup **L**anguage) files for specifying structure and type information, validators and corrective actions over LLM outputs. The concept of a Rail has evolved from markup - Rails can be defined in either Pydantic or RAIL for structured outputs, or directly in Python for string outputs. +1. `rail` (**R**eliable **AI** markup **L**anguage) files for specifying structure and type information, validators and corrective actions over LLM outputs. The concept of a Rail has evolved from markup - Rails can be defined in either Pydantic or RAIL for structured outputs, or directly in Python for string outputs. 2. `Guard` wraps around LLM API calls to structure, validate and correct the outputs. ```mermaid