Merge branch 'main' into release/v0.24.0

docs/griptape-framework/data/loaders.md

@@ -56,7 +56,6 @@ CsvLoader().load("tests/assets/cities.csv")
 
 CsvLoader().load_collection(["tests/assets/cities.csv", "tests/assets/addresses.csv"])
 ```
-```
 
 
 ## Dataframe Loader

docs/griptape-framework/drivers/embedding-drivers.md

@@ -144,7 +144,6 @@ embeddings = driver.embed_string("Hello world!")
 print(embeddings[:3])
 ```
 
-
 ### VoyageAI Embeddings
 The [VoyageAiEmbeddingDriver](../../reference/griptape/drivers/embedding/voyageai_embedding_driver.md) uses the [VoyageAI Embeddings API](https://www.voyageai.com/).
 
@@ -192,3 +191,4 @@ agent = Agent(
 
 agent.run("based on https://www.griptape.ai/, tell me what Griptape is")
 ```
+

docs/griptape-framework/drivers/image-query-drivers.md

@@ -62,7 +62,7 @@ print(result)
 ## OpenAiVisionImageQueryDriver
 
 !!! info
-    To tune `max_tokens`, 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.
+    This Driver defaults to using the `gpt-4-vision-preview` model. As other multimodal models are released, they can be specified using the `model` field. 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.
 
 The [OpenAiVisionImageQueryDriver](../../reference/griptape/drivers/image_query/openai_vision_image_query_driver.md) is used to query images using the OpenAI Vision API. Here is an example of how to use it: