griptape-ai · collindutter · Jun 19, 2024 · Jun 19, 2024 · Jun 19, 2024
diff --git a/docs/griptape-framework/drivers/audio-transcription-drivers.md b/docs/griptape-framework/drivers/audio-transcription-drivers.md
@@ -6,6 +6,8 @@ This driver acts as a critical bridge between audio transcription Engines and th
 
 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
 
 The [OpenAI Audio Transcription Driver](../../reference/griptape/drivers/audio_transcription/openai_audio_transcription_driver.md) utilizes OpenAI's sophisticated `whisper` model to accurately transcribe spoken audio into text. This model supports multiple languages, ensuring precise transcription across a wide range of dialects. 

diff --git a/docs/griptape-framework/drivers/conversation-memory-drivers.md b/docs/griptape-framework/drivers/conversation-memory-drivers.md
@@ -2,6 +2,8 @@
 
 You can persist and load memory by using Conversation Memory Drivers. You can build drivers for your own data stores by extending [BaseConversationMemoryDriver](../../reference/griptape/drivers/memory/conversation/base_conversation_memory_driver.md).
 
+## Conversation Memory Drivers
+
 ### Local
 
 The [LocalConversationMemoryDriver](../../reference/griptape/drivers/memory/conversation/local_conversation_memory_driver.md) allows you to persist Conversation Memory in a local JSON file.

diff --git a/docs/griptape-framework/drivers/image-generation-drivers.md b/docs/griptape-framework/drivers/image-generation-drivers.md
@@ -23,6 +23,8 @@ agent = Agent(tools=[
 agent.run("Generate a watercolor painting of a dog riding a skateboard")
 ```
 
+## Image Generation Drivers
+
 ### Amazon Bedrock
 
 The [Amazon Bedrock Image Generation Driver](../../reference/griptape/drivers/image_generation/amazon_bedrock_image_generation_driver.md) provides multi-model access to image generation models hosted by Amazon Bedrock. This Driver manages API calls to the Bedrock API, while the specific Model Drivers below format the API requests and parse the responses.

diff --git a/docs/griptape-framework/drivers/image-query-drivers.md b/docs/griptape-framework/drivers/image-query-drivers.md
@@ -1,11 +1,13 @@
-# Image Query Drivers
+## Overview
 
 Image Query Drivers are used by [Image Query Engines](../engines/query-engines.md#image) 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.
 
 !!! 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. 
 
-## Anthropic
+## Image Query Drivers
+
+### Anthropic
 
 !!! info
     To tune `max_tokens`, see [Anthropic's documentation on image tokens](https://docs.anthropic.com/claude/docs/vision#image-costs) for more information on how to relate token count to response length.
@@ -59,7 +61,7 @@ result = engine.run("Describe the weather in the image", [image_artifact1, image
 print(result)
 ```
 
-## OpenAI
+### OpenAI
 
 !!! info
     While the `max_tokens` field is optional, it is recommended to set this to a value that corresponds to the desired response length. Without an explicit value, the model will default to very short responses. See [OpenAI's documentation](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them) for more information on how to relate token count to response length.
@@ -86,7 +88,7 @@ with open("tests/resources/mountain.png", "rb") as f:
 engine.run("Describe the weather in the image", [image_artifact])
 ```
 
-## Azure OpenAI
+### Azure OpenAI
 
 !!! info
     In order to use the `gpt-4-vision-preview` model on Azure OpenAI, the `gpt-4` model must be deployed with the version set to `vision-preview`. More information can be found in the [Azure OpenAI documentation](https://learn.microsoft.com/en-us/azure/ai-services/openai/how-to/gpt-with-vision).
@@ -117,11 +119,11 @@ with open("tests/resources/mountain.png", "rb") as f:
 engine.run("Describe the weather in the image", [image_artifact])
 ```
 
-## Amazon Bedrock
+### Amazon Bedrock
 
 The [Amazon Bedrock Image Query Driver](../../reference/griptape/drivers/image_query/amazon_bedrock_image_query_driver.md) provides multi-model access to image query models hosted by Amazon Bedrock. This Driver manages API calls to the Bedrock API, while the specific Model Drivers below format the API requests and parse the responses.
 
-### Claude
+#### Claude
 
 The [BedrockClaudeImageQueryModelDriver](../../reference/griptape/drivers/image_query_model/bedrock_claude_image_query_model_driver.md) provides support for Claude models hosted by Bedrock.
 

diff --git a/docs/griptape-framework/drivers/sql-drivers.md b/docs/griptape-framework/drivers/sql-drivers.md
@@ -8,7 +8,9 @@ SQL drivers can be used to make SQL queries and load table schemas. They are use
 !!! info
     More database-specific SQL drivers are coming soon.
 
-## SQL
+## SQL Drivers
+
+### SQL
 
 This is a basic SQL loader based on [SQLAlchemy 1.x](https://docs.sqlalchemy.org/en/14/). Here is an example of how to use it:
 
@@ -22,7 +24,7 @@ driver = SqlDriver(
 driver.execute_query("select 'foo', 'bar';")
 ```
 
-## Amazon Redshift
+### Amazon Redshift
 
 !!! info
     This driver requires the `drivers-sql-redshift` [extra](../index.md#extras).
@@ -46,7 +48,7 @@ driver = AmazonRedshiftSqlDriver(
 driver.execute_query("select * from people;")
 ```
 
-## Snowflake
+### Snowflake
 
 !!! info
     This driver requires the `drivers-sql-snowflake` [extra](../index.md#extras).

diff --git a/docs/griptape-framework/drivers/structure-run-drivers.md b/docs/griptape-framework/drivers/structure-run-drivers.md
@@ -2,7 +2,9 @@
 Structure Run Drivers can be used to run Griptape Structures in a variety of runtime environments.
 When combined with the [Structure Run Task](../../griptape-framework/structures/tasks.md#structure-run-task) or [Structure Run Client](../../griptape-tools/official-tools/structure-run-client.md) you can create complex, multi-agent pipelines that span multiple runtime environments.
 
-## Local
+## Structure Run Drivers
+
+### Local
 
 The [LocalStructureRunDriver](../../reference/griptape/drivers/structure_run/local_structure_run_driver.md) is used to run Griptape Structures in the same runtime environment as the code that is running the Structure.
 
@@ -53,7 +55,7 @@ joke_coordinator = Pipeline(
 joke_coordinator.run("Tell me a joke")
 ```
 
-## Griptape Cloud
+### Griptape Cloud
 
 The [GriptapeCloudStructureRunDriver](../../reference/griptape/drivers/structure_run/griptape_cloud_structure_run_driver.md) is used to run Griptape Structures in the Griptape Cloud.
 

diff --git a/docs/griptape-framework/drivers/text-to-speech-drivers.md b/docs/griptape-framework/drivers/text-to-speech-drivers.md
@@ -4,6 +4,8 @@
 
 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):
 
+## Text to Speech Drivers
+
 ### Eleven Labs
 
 The [Eleven Labs Text to Speech Driver](../../reference/griptape/drivers/text_to_speech/elevenlabs_text_to_speech_driver.md) provides support for text-to-speech models hosted by Eleven Labs. This Driver supports configurations specific to Eleven Labs, like voice selection and output format.

diff --git a/docs/griptape-framework/drivers/vector-store-drivers.md b/docs/griptape-framework/drivers/vector-store-drivers.md
@@ -16,7 +16,9 @@ Each vector driver takes a [BaseEmbeddingDriver](../../reference/griptape/driver
 !!! info
     More vector drivers are coming soon.
 
-## Local
+## Vector Store Drivers
+
+### Local
 
 The [LocalVectorStoreDriver](../../reference/griptape/drivers/vector/local_vector_store_driver.md) can be used to load and query data from memory. Here is a complete example of how the driver can be used to load a webpage into the driver and query it later:
 
@@ -47,7 +49,7 @@ print("\n\n".join(values))
 
 ```
 
-## Pinecone
+### Pinecone
 
 !!! info
     This driver requires the `drivers-vector-pinecone` [extra](../index.md#extras).
@@ -103,7 +105,7 @@ result = vector_store_driver.query(
 )
 ```
 
-## Marqo
+### Marqo
 
 !!! info
     This driver requires the `drivers-vector-marqo` [extra](../index.md#extras).
@@ -157,7 +159,7 @@ result = vector_store.query(query="What is griptape?")
 print(result)
 ```
 
-## Mongodb Atlas
+### Mongodb Atlas
 
 !!! info
     This driver requires the `drivers-vector-mongodb` [extra](../index.md#extras).
@@ -225,7 +227,7 @@ The format for creating a vector index should look similar to the following:
 ```
 Replace `path_to_vector` with the expected field name where the vector content will be.
 
-## Azure MongoDB
+### Azure MongoDB
 
 !!! info
     This driver requires the `drivers-vector-mongodb` [extra](../index.md#extras).
@@ -274,7 +276,7 @@ result = vector_store.query(query="What is griptape?")
 print(result)
 ```
 
-## Redis
+### Redis
 
 !!! info
     This driver requires the `drivers-vector-redis` [extra](../index.md#extras).
@@ -319,7 +321,7 @@ The format for creating a vector index should be similar to the following:
 FT.CREATE idx:griptape ON hash PREFIX 1 "griptape:" SCHEMA namespace TAG vector VECTOR FLAT 6 TYPE FLOAT32 DIM 1536 DISTANCE_METRIC COSINE
 ```
 
-## OpenSearch
+### OpenSearch
 
 !!! info
     This driver requires the `drivers-vector-opensearch` [extra](../index.md#extras).
@@ -372,7 +374,7 @@ The body mappings for creating a vector index should look similar to the followi
 }
 ```
 
-## PGVector
+### PGVector
 
 !!! info
     This driver requires the `drivers-vector-postgresql` [extra](../index.md#extras).

diff --git a/docs/griptape-framework/drivers/web-scraper-drivers.md b/docs/griptape-framework/drivers/web-scraper-drivers.md
@@ -4,7 +4,9 @@ Web Scraper Drivers can be used to scrape text from the web. They are used by [W
 
 * `scrape_url()` scrapes text from a website and returns a [TextArtifact](../../reference/griptape/artifacts/text_artifact.md). The format of the scrapped text is determined by the Driver.
 
-## Markdownify
+## Web Scraper Drivers
+
+### Markdownify
 
 !!! info
     This driver requires the `drivers-web-scraper-markdownify` [extra](../index.md#extras) and the
@@ -64,7 +66,7 @@ agent = Agent(
 agent.run("List all email addresses on griptape.ai in a flat numbered markdown list.")
 ```
 
-## Trafilatura
+### Trafilatura
 
 !!! info
     This driver requires the `drivers-web-scraper-trafilatura` [extra](../index.md#extras).

diff --git a/docs/griptape-framework/engines/summary-engines.md b/docs/griptape-framework/engines/summary-engines.md
@@ -4,7 +4,7 @@ Summary engines are used to summarize text and collections of [TextArtifact](../
 
 ## Prompt
 
-Used to summarize texts with LLMs. You can set a custom [prompt_driver](../../reference/griptape/engines/summary/prompt_summary_engine.md#griptape.engines.summary.prompt_summary_engine.PromptSummaryEngine.prompt_driver), [template_generator](../../reference/griptape/engines/summary/prompt_summary_engine.md#griptape.engines.summary.prompt_summary_engine.PromptSummaryEngine.template_generator), and [chunker](../../reference/griptape/engines/summary/prompt_summary_engine.md#griptape.engines.summary.prompt_summary_engine.PromptSummaryEngine.chunker).
+Used to summarize texts with LLMs. You can set a custom [prompt_driver](../../reference/griptape/engines/summary/prompt_summary_engine.md#griptape.engines.summary.prompt_summary_engine.PromptSummaryEngine.prompt_driver), [system_template_generator](../../reference/griptape/engines/summary/prompt_summary_engine.md#griptape.engines.summary.prompt_summary_engine.PromptSummaryEngine.system_template_generator), [user_template_generator](../../reference/griptape/engines/summary/prompt_summary_engine.md#griptape.engines.summary.prompt_summary_engine.PromptSummaryEngine.user_template_generator), and [chunker](../../reference/griptape/engines/summary/prompt_summary_engine.md#griptape.engines.summary.prompt_summary_engine.PromptSummaryEngine.chunker).
 
 Use the [summarize_artifacts](../../reference/griptape/engines/summary/prompt_summary_engine.md#griptape.engines.summary.prompt_summary_engine.PromptSummaryEngine.summarize_artifacts) method to summarize a list of artifacts or [summarize_text](../../reference/griptape/engines/summary/base_summary_engine.md#griptape.engines.summary.base_summary_engine.BaseSummaryEngine.summarize_text) to summarize an arbitrary string.