Added
- Every subtask in `ToolkitTask` can now execute multiple actions in parallel.
- Added `BaseActionSubtaskEvent.subtask_actions`.
- Support for `text-embedding-3-small` and `text-embedding-3-large` models.
- `GooglePromptDriver` and `GoogleTokenizer` for use with `gemini-pro`.
- `GoogleEmbeddingDriver` for use with `embedding-001`.
- `GoogleStructureConfig` for providing Structures with Google Prompt and Embedding Driver configuration.
- Support for `claude-3-opus`, `claude-3-sonnet`, and `claude-3-haiku` in `AnthropicPromptDriver`.
- Support for `anthropic.claude-3-sonnet-20240229-v1:0` and `anthropic.claude-3-haiku-20240307-v1:0` in `BedrockClaudePromptModelDriver`.
- `top_k` and `top_p` parameters in `AnthropicPromptDriver`.
- Added `AnthropicImageQueryDriver` for Claude-3 multi-modal models
- Added `AmazonBedrockImageQueryDriver` along with `BedrockClaudeImageQueryDriverModel` for Claude-3 in Bedrock support
- `BaseWebScraperDriver` allowing multiple web scraping implementations.
- `TrafilaturaWebScraperDriver` for scraping text from web pages using trafilatura.
- `MarkdownifyWebScraperDriver` for scraping text from web pages using playwright and converting to markdown using markdownify.
- `VoyageAiEmbeddingDriver` for use with VoyageAi's embedding models.
- `AnthropicStructureConfig` for providing Structures with Anthropic Prompt and VoyageAi Embedding Driver configuration.
- `QdrantVectorStoreDriver` to integrate with Qdrant vector databases.
Fixed
- Improved system prompt in `ToolTask` to support more use cases.
Changed
- **BREAKING**: `ActionSubtask` was renamed to `ActionsSubtask`.
- **BREAKING**: Removed `subtask_action_name`, `subtask_action_path`, and `subtask_action_input` in `BaseActionSubtaskEvent`.
- **BREAKING**: `OpenAiVisionImageQueryDriver` field `model` no longer defaults to `gpt-4-vision-preview` and must be specified
- Default model of `OpenAiEmbeddingDriver` to `text-embedding-3-small`.
- Default model of `OpenAiStructureConfig` to `text-embedding-3-small`.
- `BaseTextLoader` to accept a `BaseChunker`.
- Default model of `AmazonBedrockStructureConfig` to `anthropic.claude-3-sonnet-20240229-v1:0`.
- `AnthropicPromptDriver` and `BedrockClaudePromptModelDriver` to use Anthropic's Messages API.
- `OpenAiVisionImageQueryDriver` now has a required field `max_tokens` that defaults to 256
- `GriptapeCloudStructureRunDriver` now outputs a `BaseArtifact` instead of a `TextArtifact`