From 1e8064979b7dc22d33ca7d2d174ca42eb6024625 Mon Sep 17 00:00:00 2001 From: Collin Dutter Date: Thu, 24 Oct 2024 16:21:15 -0700 Subject: [PATCH] Clean up docs --- README.md | 6 ++---- docs/griptape-framework/data/index.md | 8 +------- .../drivers/audio-transcription-drivers.md | 4 ---- .../drivers/image-generation-drivers.md | 10 +++++----- docs/griptape-framework/drivers/image-query-drivers.md | 2 +- .../drivers/text-to-speech-drivers.md | 2 +- docs/griptape-framework/structures/tasks.md | 8 ++++---- .../official-tools/audio-transcription-tool.md | 2 +- .../official-tools/text-to-speech-tool.md | 2 +- .../official-tools/variation-image-generation-tool.md | 2 +- griptape/tools/inpainting_image_generation/tool.py | 2 +- griptape/tools/outpainting_image_generation/tool.py | 2 +- griptape/tools/prompt_image_generation/tool.py | 2 +- griptape/tools/text_to_speech/tool.py | 2 +- griptape/tools/variation_image_generation/tool.py | 2 +- mkdocs.yml | 3 --- 16 files changed, 22 insertions(+), 37 deletions(-) diff --git a/README.md b/README.md index 854dc281fb..4010ed4056 100644 --- a/README.md +++ b/README.md @@ -50,10 +50,8 @@ Drivers facilitate interactions with external resources and services: Engines wrap Drivers and provide use-case-specific functionality: - 📊 **RAG Engine** is an abstraction for implementing modular Retrieval Augmented Generation (RAG) pipelines. -- 🛠️ **Extraction Engines** extract JSON or CSV data from unstructured text. -- 📝 **Summary Engines** generate summaries from textual content. -- 🖼️ **Image Generation Engines** generate images from textual descriptions. -- 🔎 **Image Query Engines** query images based on textual prompts. +- 🛠️ **Extraction Engine** extracts JSON or CSV data from unstructured text. +- 📝 **Summary Engine** generates summaries from textual content. ### 📦 Additional Components diff --git a/docs/griptape-framework/data/index.md b/docs/griptape-framework/data/index.md index 13bbba3c47..e4a63763d1 100644 --- a/docs/griptape-framework/data/index.md +++ b/docs/griptape-framework/data/index.md @@ -14,18 +14,12 @@ Griptape provides several abstractions for working with data. **Tokenizers** are used to tokenize and detokenize text in order to track LLM token limits. -[Audio Engines](../engines/audio-engines.md) are used for working with audio. +[RAG Engines](../engines/rag-engines.md) are used for implementing modular RAG pipelines. [Extraction Engines](../engines/extraction-engines.md) are used for extracting structured content. -[Image Query Engines](../engines/image-query-engines.md) are used for querying images with text. - -[Image Generation Engines](../engines/image-generation-engines.md) are used for generating images. - [Summary Engines](../engines/summary-engines.md) are used for summarizing text content. -[RAG Engines](../engines/rag-engines.md) are used for implementing modular RAG pipelines. - [Vector Store Drivers](../drivers/vector-store-drivers.md) are used to store and query vector databases. [Prompt Drivers](../drivers/prompt-drivers.md) are used to call LLM APIs. diff --git a/docs/griptape-framework/drivers/audio-transcription-drivers.md b/docs/griptape-framework/drivers/audio-transcription-drivers.md index 793084e08f..9a8e7b70b5 100644 --- a/docs/griptape-framework/drivers/audio-transcription-drivers.md +++ b/docs/griptape-framework/drivers/audio-transcription-drivers.md @@ -7,10 +7,6 @@ search: [Audio Transcription Drivers](../../reference/griptape/drivers/audio_transcription/index.md) extract text from spoken audio. -This driver acts as a critical bridge between audio transcription Engines and the underlying models, facilitating the construction and execution of API calls that transform speech into editable and searchable text. Utilized predominantly in applications that support the input of verbal communications, the Audio Transcription Driver effectively extracts and interprets speech, rendering it into a textual format that can be easily integrated into data systems and Workflows. - -This capability is essential for enhancing accessibility, improving content discoverability, and automating tasks that traditionally relied on manual transcription, thereby streamlining operations and enhancing efficiency across various industries. - ## Audio Transcription Drivers ### OpenAI diff --git a/docs/griptape-framework/drivers/image-generation-drivers.md b/docs/griptape-framework/drivers/image-generation-drivers.md index 549fb0c28e..92fc64b026 100644 --- a/docs/griptape-framework/drivers/image-generation-drivers.md +++ b/docs/griptape-framework/drivers/image-generation-drivers.md @@ -5,9 +5,9 @@ search: ## Overview -[Image Generation Drivers](../../reference/griptape/drivers/image_generation/index.md) are used by [image generation Engines](../engines/image-generation-engines.md) to build and execute API calls to image generation models. +[Image Generation Drivers](../../reference/griptape/drivers/image_generation/index.md) build and execute API calls to image generation models. -Provide a Driver when building an [Engine](../engines/image-generation-engines.md), then pass it to a [Tool](../tools/index.md) for use by an [Agent](../structures/agents.md): +Provide a Driver to a [Tool](../tools/index.md) for use by an [Agent](../structures/agents.md): ```python --8<-- "docs/griptape-framework/drivers/src/image_generation_drivers_1.py" @@ -23,7 +23,7 @@ The [Amazon Bedrock Image Generation Driver](../../reference/griptape/drivers/im The [Bedrock Stable Diffusion Model Driver](../../reference/griptape/drivers/image_generation_model/bedrock_stable_diffusion_image_generation_model_driver.md) provides support for Stable Diffusion models hosted by Amazon Bedrock. This Model Driver supports configurations specific to Stable Diffusion, like style presets, clip guidance presets, and sampler. -This Model Driver supports negative prompts. When provided (for example, when used with an [image generation Engine](../engines/image-generation-engines.md) configured with [Negative Rulesets](../engines/image-generation-engines.md#image-generation-engine-rulesets)), the image generation request will include negatively-weighted prompts describing features or characteristics to avoid in the resulting generation. +This Model Driver supports negative prompts. When provided, the image generation request will include negatively-weighted prompts describing features or characteristics to avoid in the resulting generation. ```python --8<-- "docs/griptape-framework/drivers/src/image_generation_drivers_2.py" @@ -33,7 +33,7 @@ This Model Driver supports negative prompts. When provided (for example, when us The [Bedrock Titan Image Generator Model Driver](../../reference/griptape/drivers/image_generation_model/bedrock_titan_image_generation_model_driver.md) provides support for Titan Image Generator models hosted by Amazon Bedrock. This Model Driver supports configurations specific to Titan Image Generator, like quality, seed, and cfg_scale. -This Model Driver supports negative prompts. When provided (for example, when used with an [image generation engine](../engines/image-generation-engines.md) configured with [Negative Rulesets](../engines/image-generation-engines.md#image-generation-engine-rulesets)), the image generation request will include negatively-weighted prompts describing features or characteristics to avoid in the resulting generation. +This Model Driver supports negative prompts. When provided, the image generation request will include negatively-weighted prompts describing features or characteristics to avoid in the resulting generation. ```python --8<-- "docs/griptape-framework/drivers/src/image_generation_drivers_3.py" @@ -53,7 +53,7 @@ The [Leonardo Image Generation Driver](../../reference/griptape/drivers/image_ge This Driver supports configurations like model selection, image size, specifying a generation seed, and generation steps. For details on supported configuration parameters, see [Leonardo.Ai's image generation documentation](https://docs.leonardo.ai/reference/creategeneration). -This Driver supports negative prompts. When provided (for example, when used with an [image generation engine](../engines/image-generation-engines.md) configured with [Negative Rulesets](../engines/image-generation-engines.md#image-generation-engine-rulesets)), the image generation request will include negatively-weighted prompts describing features or characteristics to avoid in the resulting generation. +This Driver supports negative prompts. When provided, the image generation request will include negatively-weighted prompts describing features or characteristics to avoid in the resulting generation. ```python --8<-- "docs/griptape-framework/drivers/src/image_generation_drivers_5.py" diff --git a/docs/griptape-framework/drivers/image-query-drivers.md b/docs/griptape-framework/drivers/image-query-drivers.md index e3dc9032f7..0f40d15fc0 100644 --- a/docs/griptape-framework/drivers/image-query-drivers.md +++ b/docs/griptape-framework/drivers/image-query-drivers.md @@ -5,7 +5,7 @@ search: ## Overview -Image Query Drivers are used by [Image Query Engines](../engines/image-query-engines.md) to execute natural language queries on the contents of images. You can specify the provider and model used to query the image by providing the Engine with a particular Image Query Driver. +Image Query Drivers execute natural language queries on the contents of images. You can specify the provider and model used to query the image by providing the Engine with a particular Image Query Driver. !!! info All Image Query Drivers default to a `max_tokens` of 256. It is recommended that you set this value to correspond to the desired response length. diff --git a/docs/griptape-framework/drivers/text-to-speech-drivers.md b/docs/griptape-framework/drivers/text-to-speech-drivers.md index 55e3437527..365aeffbe2 100644 --- a/docs/griptape-framework/drivers/text-to-speech-drivers.md +++ b/docs/griptape-framework/drivers/text-to-speech-drivers.md @@ -7,7 +7,7 @@ search: [Text to Speech Drivers](../../reference/griptape/drivers/text_to_speech/index.md) are used to build and execute API calls to audio generation models. -Provide a Driver when building an [Engine](../engines/audio-engines.md), then pass it to a [Tool](../tools/index.md) for use by an [Agent](../structures/agents.md): +Provide a Driver to a [Tool](../tools/index.md) for use by an [Agent](../structures/agents.md): ## Text to Speech Drivers diff --git a/docs/griptape-framework/structures/tasks.md b/docs/griptape-framework/structures/tasks.md index 85ed0a4324..f82f753657 100644 --- a/docs/griptape-framework/structures/tasks.md +++ b/docs/griptape-framework/structures/tasks.md @@ -304,7 +304,7 @@ This task takes a python function, and authors can elect to return a custom arti ## Image Generation Tasks -To generate an image, use one of the following [Image Generation Tasks](../../reference/griptape/tasks/index.md). All Image Generation Tasks accept an [Image Generation Engine](../engines/image-generation-engines.md) configured to use an [Image Generation Driver](../drivers/image-generation-drivers.md). +To generate an image, use one of the following [Image Generation Tasks](../../reference/griptape/tasks/index.md). All Image Generation Tasks accept an [Image Generation Driver](../drivers/image-generation-drivers.md). All successful Image Generation Tasks will always output an [Image Artifact](../data/artifacts.md#image). Each task can be configured to additionally write the generated image to disk by providing either the `output_file` or `output_dir` field. The `output_file` field supports file names in the current directory (`my_image.png`), relative directory prefixes (`images/my_image.png`), or absolute paths (`/usr/var/my_image.png`). By setting `output_dir`, the task will generate a file name and place the image in the requested directory. @@ -342,7 +342,7 @@ The [Outpainting Image Generation Task](../../reference/griptape/tasks/outpainti ## Image Query Task -The [Image Query Task](../../reference/griptape/tasks/image_query_task.md) performs a natural language query on one or more input images. This Task uses an [Image Query Engine](../engines/image-query-engines.md) configured with an [Image Query Driver](../drivers/image-query-drivers.md) to perform the query. The functionality provided by this Task depend on the capabilities of the model provided by the Driver. +The [Image Query Task](../../reference/griptape/tasks/image_query_task.md) performs a natural language query on one or more input images. This Task uses an [Image Query Driver](../drivers/image-query-drivers.md) to perform the query. The functionality provided by this Task depend on the capabilities of the model provided by the Driver. This Task accepts two inputs: a query (represented by either a string or a [Text Artifact](../data/artifacts.md#text)) and a list of [Image Artifacts](../data/artifacts.md#image) or a Callable returning these two values. @@ -361,7 +361,7 @@ This Task is useful for orchestrating multiple specialized Structures in a singl ## Text to Speech Task -This Task enables Structures to synthesize speech from text using [Text to Speech Engines](../../reference/griptape/engines/audio/text_to_speech_driver.md) and [Text to Speech Drivers](../../reference/griptape/drivers/text_to_speech/index.md). +This Task enables Structures to synthesize speech from text using [Text to Speech Drivers](../../reference/griptape/drivers/text_to_speech/index.md). ```python --8<-- "docs/griptape-framework/structures/src/tasks_17.py" @@ -369,7 +369,7 @@ This Task enables Structures to synthesize speech from text using [Text to Speec ## Audio Transcription Task -This Task enables Structures to transcribe speech from text using [Audio Transcription Engines](../../reference/griptape/engines/audio/audio_transcription_engine.md) and [Audio Transcription Drivers](../../reference/griptape/drivers/audio_transcription/index.md). +This Task enables Structures to transcribe speech from text using [Audio Transcription Drivers](../../reference/griptape/drivers/audio_transcription/index.md). ```python --8<-- "docs/griptape-framework/structures/src/tasks_18.py" diff --git a/docs/griptape-tools/official-tools/audio-transcription-tool.md b/docs/griptape-tools/official-tools/audio-transcription-tool.md index ad8eeaa9b9..e28bb4ebee 100644 --- a/docs/griptape-tools/official-tools/audio-transcription-tool.md +++ b/docs/griptape-tools/official-tools/audio-transcription-tool.md @@ -1,6 +1,6 @@ # Audio Transcription Tool -This Tool enables [Agents](../../griptape-framework/structures/agents.md) to transcribe speech from text using [Audio Transcription Engines](../../reference/griptape/engines/audio/audio_transcription_engine.md) and [Audio Transcription Drivers](../../reference/griptape/drivers/audio_transcription/index.md). +This Tool enables [Agents](../../griptape-framework/structures/agents.md) to transcribe speech from text using [Audio Transcription Drivers](../../reference/griptape/drivers/audio_transcription/base_audio_transcription_driver.md). ```python --8<-- "docs/griptape-tools/official-tools/src/audio_transcription_tool_1.py" diff --git a/docs/griptape-tools/official-tools/text-to-speech-tool.md b/docs/griptape-tools/official-tools/text-to-speech-tool.md index 07221a61ee..78ad032f95 100644 --- a/docs/griptape-tools/official-tools/text-to-speech-tool.md +++ b/docs/griptape-tools/official-tools/text-to-speech-tool.md @@ -1,6 +1,6 @@ # Text To Speech Tool -This Tool enables LLMs to synthesize speech from text using [Text to Speech Engines](../../reference/griptape/engines/audio/text_to_speech_driver.md) and [Text to Speech Drivers](../../reference/griptape/drivers/text_to_speech/index.md). +This Tool enables LLMs to synthesize speech from text using [Text to Speech Drivers](../../reference/griptape/drivers/text_to_speech/index.md). ```python --8<-- "docs/griptape-tools/official-tools/src/text_to_speech_tool_1.py" diff --git a/docs/griptape-tools/official-tools/variation-image-generation-tool.md b/docs/griptape-tools/official-tools/variation-image-generation-tool.md index 523dcf9f04..059415a51b 100644 --- a/docs/griptape-tools/official-tools/variation-image-generation-tool.md +++ b/docs/griptape-tools/official-tools/variation-image-generation-tool.md @@ -1,4 +1,4 @@ -# Variation Image Generation Engine Tool +# Variation Image Generation Tool This Tool allows LLMs to generate variations of an input image from a text prompt. The input image can be provided either by its file path or by its [Task Memory](../../griptape-framework/structures/task-memory.md) reference. diff --git a/griptape/tools/inpainting_image_generation/tool.py b/griptape/tools/inpainting_image_generation/tool.py index d8a942205b..64cf1cc638 100644 --- a/griptape/tools/inpainting_image_generation/tool.py +++ b/griptape/tools/inpainting_image_generation/tool.py @@ -20,7 +20,7 @@ class InpaintingImageGenerationTool(BaseImageGenerationTool): """A tool that can be used to generate prompted inpaintings of an image. Attributes: - engine: The inpainting image generation engine used to generate the image. + image_generation_driver: The image generation driver used to generate the image. output_dir: If provided, the generated image will be written to disk in output_dir. output_file: If provided, the generated image will be written to disk as output_file. """ diff --git a/griptape/tools/outpainting_image_generation/tool.py b/griptape/tools/outpainting_image_generation/tool.py index 2bd654d94b..e1510654c9 100644 --- a/griptape/tools/outpainting_image_generation/tool.py +++ b/griptape/tools/outpainting_image_generation/tool.py @@ -20,7 +20,7 @@ class OutpaintingImageGenerationTool(BaseImageGenerationTool): """A tool that can be used to generate prompted outpaintings of an image. Attributes: - engine: The outpainting image generation engine used to generate the image. + image_generation_driver: The image generation driver used to generate the image. output_dir: If provided, the generated image will be written to disk in output_dir. output_file: If provided, the generated image will be written to disk as output_file. """ diff --git a/griptape/tools/prompt_image_generation/tool.py b/griptape/tools/prompt_image_generation/tool.py index 3ed166481a..fad022bd7c 100644 --- a/griptape/tools/prompt_image_generation/tool.py +++ b/griptape/tools/prompt_image_generation/tool.py @@ -18,7 +18,7 @@ class PromptImageGenerationTool(BaseImageGenerationTool): """A tool that can be used to generate an image from a text prompt. Attributes: - engine: The prompt image generation engine used to generate the image. + image_generation_driver: The image generation driver used to generate the image. output_dir: If provided, the generated image will be written to disk in output_dir. output_file: If provided, the generated image will be written to disk as output_file. """ diff --git a/griptape/tools/text_to_speech/tool.py b/griptape/tools/text_to_speech/tool.py index 10f2798320..518679c35f 100644 --- a/griptape/tools/text_to_speech/tool.py +++ b/griptape/tools/text_to_speech/tool.py @@ -19,7 +19,7 @@ class TextToSpeechTool(ArtifactFileOutputMixin, BaseTool): """A tool that can be used to generate speech from input text. Attributes: - engine: The text to audio generation engine used to generate the speech audio. + text_to_speech_driver: The text to audio generation driver used to generate the speech audio. output_dir: If provided, the generated audio will be written to disk in output_dir. output_file: If provided, the generated audio will be written to disk as output_file. """ diff --git a/griptape/tools/variation_image_generation/tool.py b/griptape/tools/variation_image_generation/tool.py index 8194258646..5c4250965b 100644 --- a/griptape/tools/variation_image_generation/tool.py +++ b/griptape/tools/variation_image_generation/tool.py @@ -20,7 +20,7 @@ class VariationImageGenerationTool(BaseImageGenerationTool): """A tool that can be used to generate prompted variations of an image. Attributes: - engine: The variation image generation engine used to generate the image. + image_generation_driver: The image generation driver used to generate the image. output_dir: If provided, the generated image will be written to disk in output_dir. output_file: If provided, the generated image will be written to disk as output_file. """ diff --git a/mkdocs.yml b/mkdocs.yml index f43b9e1f76..c938bb4e59 100644 --- a/mkdocs.yml +++ b/mkdocs.yml @@ -112,11 +112,8 @@ nav: - Building Custom Tools: "griptape-tools/custom-tools/index.md" - Engines: - RAG Engines: "griptape-framework/engines/rag-engines.md" - - Image Query Engines: "griptape-framework/engines/image-query-engines.md" - Extraction Engines: "griptape-framework/engines/extraction-engines.md" - Summary Engines: "griptape-framework/engines/summary-engines.md" - - Image Generation Engines: "griptape-framework/engines/image-generation-engines.md" - - Audio Engines: "griptape-framework/engines/audio-engines.md" - Drivers: - Prompt Drivers: "griptape-framework/drivers/prompt-drivers.md" - Embedding Drivers: "griptape-framework/drivers/embedding-drivers.md"