v0.29.2

Fixed

• Workflow threads not being properly cleaned up after completion.
• Crash when ToolActions were missing output due to an ActionsSubtask exception.

v0.29.1

Changed

• Remove BaseTextArtifact, revert CsvRowArtifact to subclass TextArtifact.

Fixed

• Missing extra for drivers-text-to-speech-elevenlabs.

v0.29.0

Added

• Native function calling support to OpenAiChatPromptDriver, AzureOpenAiChatPromptDriver, AnthropicPromptDriver, AmazonBedrockPromptDriver, GooglePromptDriver, OllamaPromptDriver, and CoherePromptDriver.
• OllamaEmbeddingDriver for generating embeddings with Ollama.
• GriptapeCloudKnowledgeBaseVectorStoreDriver to query Griptape Cloud Knowledge Bases.
• GriptapeCloudEventListenerDriver.api_key defaults to the value in the GT_CLOUD_API_KEY environment variable.
• BaseObservabilityDriver as the base class for all Observability Drivers.
• DummyObservabilityDriver as a no-op Observability Driver.
• OpenTelemetryObservabilityDriver for sending observability data to an open telemetry collector or vendor.
• GriptapeCloudObservabilityDriver for sending observability data to Griptape Cloud.
• DatadogObservabilityDriver for sending observability data to a Datadog Agent.
• Observability context manager for enabling observability and configuring which Observability Driver to use.
• @observable decorator for selecting which functions/methods to provide observability for.
• GenericArtifact for storing any data.
• BaseTextArtifact for text-based Artifacts to subclass.
• HuggingFacePipelineImageGenerationDriver for generating images locally with HuggingFace pipelines.
• BaseImageGenerationPipelineDriver as the base class for drivers interfacing with HuggingFace image generation pipelines.
• StableDiffusion3ImageGenerationPipelineDriver for local text-to-image generation using a Stable Diffusion 3 pipeline.
• StableDiffusion3Img2ImgImageGenerationPipelineDriver for local image-to-image generation using a Stable Diffusion 3 pipeline.
• StableDiffusion3ControlNetImageGenerationPipelineDriver for local ControlNet image generation using a Stable Diffusion 3 pipeline.

Changed

• BREAKING: BaseVectorStoreDriver.upsert_text_artifacts optional arguments are now keyword-only arguments.
• BREAKING: BaseVectorStoreDriver.upsert_text_artifact optional arguments are now keyword-only arguments.
• BREAKING: BaseVectorStoreDriver.upsert_text optional arguments are now keyword-only arguments.
• BREAKING: BaseVectorStoreDriver.does_entry_exist optional arguments are now keyword-only arguments.
• BREAKING: BaseVectorStoreDriver.load_artifacts optional arguments are now keyword-only arguments.
• BREAKING: BaseVectorStoreDriver.upsert_vector optional arguments are now keyword-only arguments.
• BREAKING: BaseVectorStoreDriver.query optional arguments are now keyword-only arguments.
• BREAKING: EventListener.publish_event's flush argument is now a keyword-only argument.
• BREAKING: BaseEventListenerDriver.publish_event's flush argument is now a keyword-only argument.
• BREAKING: Renamed DummyException to DummyError for pep8 naming compliance.
• BREAKING: Migrate to sqlalchemy 2.0.
• BREAKING: Make sqlalchemy an optional dependency.
• BREAKING: Renamed drivers-sql-redshift to drivers-sql-amazon-redshift
• BREAKING: Renamed drivers-prompt-huggingface extra to drivers-prompt-huggingface-hub.
• BREAKING: Renamed drivers-vector-postgresql extra to drivers-vector-pgvector.
• BREAKING: Update marqo dependency to ^3.7.0.
• BREAKING: Removed drivers-sql-postgresql extra. Use drivers-sql extra and install necessary drivers (i.e. psycopg2) separately.
• Removed unnecessary sqlalchemy-redshift dependency in drivers-sql-amazon-redshift extra.
• Removed unnecessary transformers dependency in drivers-prompt-huggingface extra.
• Removed unnecessary huggingface-hub dependency in drivers-prompt-huggingface-pipeline extra.
• CsvRowArtifact now inherits from BaseTextArtifact.
• TextArtifact now inherits from BaseTextArtifact.

Fixed

• Parameter count for QdrantVectorStoreDriver.query now optional as per documentation.
• Path issues on Windows with LocalFileManagerDriver and AmazonS3FileManagerDriver.

v0.28.2

Fixed

• Conversation Memory being incorrectly inserted into the PromptTask.prompt_stack when no system content is present.

v0.28.1

Fixed

• Sending empty system content in PromptTask.
• Throttling issues with DuckDuckGoWebSearchDriver.

v0.28.0

Added

• RagEngine is an abstraction for implementing modular RAG pipelines.
  • RagContext is a container object for passing around RAG context.
  • RAG stages:
    • QueryRagStage for parsing and expanding queries.
    • RetrievalRagStage for retrieving content.
    • ResponseRagStage for augmenting and generating outputs.
  • RAG modules:
    • Retrieval:
      • VectorStoreRetrievalRagModule for retrieving text chunks from vector stores.
      • TextLoaderRetrievalRagModule for retrieving data with text loaders in real time.
      • TextChunksRerankRagModule for re-ranking retrieved results.
    • Response:
      • MetadataBeforeResponseRagModule for appending metadata.
      • RulesetsBeforeResponseRagModule for appending rulesets.
      • PromptResponseRagModule for generating responses based on retrieved text chunks.
      • TextChunksResponseRagModule for responding with retrieved text chunks.
      • FootnotePromptResponseRagModule for responding with automatic footnotes from text chunk references.
• RagClient tool for exposing RagEngines to LLM agents.
• RagTask task for including RagEngines in any structure.
• Rerank drivers:
  • CohereRerankDriver for using the Cohere rerank API.
• utils.execute_futures_list() for executing a list of futures.
• LocalVectorStoreDriver.persist_file for persisting vectors and chunks in a text file.
• Entry.to_artifact() for easy vector store entry conversions into Griptape artifacts.
• BaseVectorStoreDriver.does_entry_exist() to check if an entry exists in the vector store.
• GoogleWebSearchDriver to web search with the Google Customsearch API.
• DuckDuckGoWebSearchDriver to web search with the DuckDuckGo search SDK.
• ProxyWebScraperDriver to web scrape using proxies.
• Parameter session on AmazonBedrockStructureConfig.
• Parameter meta on TextArtifact.
• VectorStoreClient improvements:
  • VectorStoreClient.query_params dict for custom query params.
  • VectorStoreClient.process_query_output_fn for custom query output processing logic.
• Parameter fail_fast to Structure.
• BooleanArtifact for handling boolean values.
• typos to dev dependencies to catch typos in code/docs.
• Message for storing messages in a PromptStack. Messages consist of a role, content, and usage.
• DeltaMessage for storing partial messages in a PromptStack. Multiple DeltaMessage can be combined to form a Message.
• TextMessageContent for storing textual content in a Message.
• ImageMessageContent for storing image content in a Message.
• Support for adding TextArtifacts, ImageArtifacts, and ListArtifacts to PromptStack.
• Support for image inputs to OpenAiChatPromptDriver, AzureOpenAiChatPromptDriver, AmazonBedrockPromptDriver, AnthropicPromptDriver, and GooglePromptDriver.
• Input/output token usage metrics to all Prompt Drivers.
• FinishPromptEvent.input_token_count and FinishPromptEvent.output_token_count.
• Support for storing Artifacts as inputs/outputs in Conversation Memory Runs.
• Agent.input for passing Artifacts as input.
• Support for PromptTasks to take TextArtifacts, ImageArtifacts, and ListArtifacts as input.
• Parameters sort_key and sort_key_value on AmazonDynamoDbConversationMemoryDriver for tables with sort keys.
• Reference for supporting artifact citations in loaders and RAG engine modules.

Changed

• BREAKING: Moved/renamed griptape.utils.PromptStack to griptape.common.PromptStack.
• BREAKING: Renamed PromptStack.inputs to PromptStack.messages.
• BREAKING: Moved PromptStack.USER_ROLE, PromptStack.ASSISTANT_ROLE, and PromptStack.SYSTEM_ROLE to Message.
• BREAKING: Updated return type of PromptDriver.try_run from TextArtifact to Message.
• BREAKING: Updated return type of PromptDriver.try_stream from Iterator[TextArtifact] to Iterator[DeltaMessage].
• BREAKING: Removed BasePromptEvent.token_count in favor of FinishPromptEvent.input_token_count and FinishPromptEvent.output_token_count.
• BREAKING: Removed StartPromptEvent.prompt. Use StartPromptEvent.prompt_stack instead.
• BREAKING: Removed Agent.input_template in favor of Agent.input.
• BREAKING: BasePromptDriver.run now returns a Message instead of a TextArtifact. For compatibility, Message.value contains the Message's Artifact value
• BREAKING: BaseVectorStoreDriver.upsert_text_artifact() and BaseVectorStoreDriver.upsert_text() use artifact/string values to generate vector_id if it wasn't implicitly passed. This change ensures that we don't generate embeddings for the same content every time.
• BREAKING: Removed VectorQueryEngine in favor of RagEngine.
• BREAKING: Removed TextQueryTask in favor of RagTask.
• BREAKING: TextArtifactStorage now requires vector_store_driver and rag_engine in place of vector_query_engine.
• BREAKING: Moved load_artifacts() from BaseQueryEngine to BaseVectorStoreDriver.
• BREAKING: Merged BaseVectorStoreDriver.QueryResult into BaseVectorStoreDriver.Entry.
• BREAKING: Replaced query_engine with vector_store_driver in VectorStoreClient.
• BREAKING: removed parameters google_api_lang, google_api_key, google_api_search_id, google_api_country on WebSearch in favor of web_search_driver.
• BREAKING: removed VectorStoreClient.top_n and VectorStoreClient.namespace in favor of VectorStoreClient.query_params.
• BREAKING: All futures_executor fields renamed to futures_executor_fn and now accept callables instead of futures; wrapped all future submit calls with the with block to address future executor shutdown issues.
• GriptapeCloudKnowledgeBaseClient migrated to /search api.
• Default Prompt Driver model in GoogleStructureConfig to gemini-1.5-pro.

Fixed

• CoherePromptDriver to properly handle empty history.
• StructureVisualizer.to_url() by wrapping task IDs in single quotes.

v0.27.2

What's Changed

• Tool Task Hotfix by @collindutter in #883
• Feature/claude sonnet by @collindutter in #884
• Version bump v0.27.1 by @collindutter in #887
• [hotfix] Don't add ToolkitTask stop sequence if already present by @andrewfrench in #906
• [hotfix] Fix token calculation in VectorQueryEngine by @andrewfrench in #911
• Version bump v0.27.2 by @andrewfrench in #912

Full Changelog: 0.27.0...0.27.2

v0.27.0

Added

• BaseTask.add_child() to add a child task to a parent task.
• BaseTask.add_children() to add multiple child tasks to a parent task.
• BaseTask.add_parent() to add a parent task to a child task.
• BaseTask.add_parents() to add multiple parent tasks to a child task.
• Structure.resolve_relationships() to resolve asymmetrically defined parent/child relationships. In other words, if a parent declares a child, but the child does not declare the parent, the parent will automatically be added as a parent of the child when running this method. The method is invoked automatically by Structure.before_run().
• CohereEmbeddingDriver for using Cohere's embeddings API.
• CohereStructureConfig for providing Structures with quick Cohere configuration.
• AmazonSageMakerJumpstartPromptDriver.inference_component_name for setting the InferenceComponentName parameter when invoking an endpoint.
• AmazonSageMakerJumpstartEmbeddingDriver.inference_component_name for setting the InferenceComponentName parameter when invoking an endpoint.
• AmazonSageMakerJumpstartEmbeddingDriver.custom_attributes for setting custom attributes when invoking an endpoint.
• ToolkitTask.response_stop_sequence for overriding the default Chain of Thought stop sequence.
• griptape.utils.StructureVisualizer for visualizing Workflow structures with Mermaid.js
• BaseTask.parents_outputs to get the textual output of all parent tasks.
• BaseTask.parents_output_text to get a concatenated string of all parent tasks' outputs.
• parents_output_text to Workflow context.
• OllamaPromptModelDriver for using models with Ollama.
• Parameter output on Structure as a convenience for output_task.output

Changed

• BREAKING: Workflow no longer modifies task relationships when adding tasks via tasks init param, add_tasks() or add_task(). Previously, adding a task would automatically add the previously added task as its parent. Existing code that relies on this behavior will need to be updated to explicitly add parent/child relationships using the API offered by BaseTask.
• BREAKING: Removed AmazonBedrockPromptDriver.prompt_model_driver as it is no longer needed with the AmazonBedrockPromptDriver Converse API implementation.
• BREAKING: Removed BedrockClaudePromptModelDriver.
• BREAKING: Removed BedrockJurassicPromptModelDriver.
• BREAKING: Removed BedrockLlamaPromptModelDriver.
• BREAKING: Removed BedrockTitanPromptModelDriver.
• BREAKING: Removed BedrockClaudeTokenizer, use SimpleTokenizer instead.
• BREAKING: Removed BedrockJurassicTokenizer, use SimpleTokenizer instead.
• BREAKING: Removed BedrockLlamaTokenizer, use SimpleTokenizer instead.
• BREAKING: Removed BedrockTitanTokenizer, use SimpleTokenizer instead.
• BREAKING: Removed OpenAiChatCompletionPromptDriver as it uses the legacy OpenAi Completions API.
• BREAKING: Removed BasePromptDriver.count_tokens().
• BREAKING: Removed BasePromptDriver.max_output_tokens().
• BREAKING: Moved/renamed PromptStack.add_to_conversation_memory to BaseConversationMemory.add_to_prompt_stack.
• BREAKING: Moved griptape.constants.RESPONSE_STOP_SEQUENCE to ToolkitTask.
• BREAKING: Renamed AmazonSagemakerPromptDriver to AmazonSageMakerJumpstartPromptDriver.
• BREAKING: Removed SagemakerFalconPromptModelDriver, use AmazonSageMakerJumpstartPromptDriver instead.
• BREAKING: Removed SagemakerLlamaPromptModelDriver, use AmazonSageMakerJumpstartPromptDriver instead.
• BREAKING: Renamed AmazonSagemakerEmbeddingDriver to AmazonSageMakerJumpstartEmbeddingDriver.
• BREAKING: Removed SagemakerHuggingfaceEmbeddingModelDriver, use AmazonSageMakerJumpstartEmbeddingDriver instead.
• BREAKING: Removed SagemakerTensorflowHubEmbeddingModelDriver, use AmazonSageMakerJumpstartEmbeddingDriver instead.
• BREAKING: AmazonSageMakerJumpstartPromptDriver.model parameter, which gets passed to SageMakerRuntime.Client.invoke_endpoint as EndpointName, is now renamed to AmazonSageMakerPromptDriver.endpoint.
• BREAKING: Removed parameter template_generator on PromptSummaryEngine and added parameters system_template_generator and user_template_generator.
• BREAKING: Removed template engines/summary/prompt_summary.j2 and added templates engines/summary/system.j2 and engines/summary/user.j2.
• ToolkitTask.RESPONSE_STOP_SEQUENCE is now only added when using ToolkitTask.
• Updated Prompt Drivers to use BasePromptDriver.max_tokens instead of using BasePromptDriver.max_output_tokens().
• Improved error message when GriptapeCloudKnowledgeBaseClient does not have a description set.
• Updated AmazonBedrockPromptDriver to use Converse API.
• Structure.before_run() now automatically resolves asymmetrically defined parent/child relationships using the new Structure.resolve_relationships().
• Updated HuggingFaceHubPromptDriver to use transformers's apply_chat_template.
• Updated HuggingFacePipelinePromptDriver to use chat features of transformers.TextGenerationPipeline.
• Updated CoherePromptDriver to use Cohere's latest SDK.
• Moved Task reset logic for all Structures to Structure.before_run.
• Updated default prompt templates for PromptSummaryEngine.
• Updated template templates/tasks/tool_task/system.j2.

Fixed

• Workflow.insert_task() no longer inserts duplicate tasks when given multiple parent tasks.
• Performance issue in OpenAiChatPromptDriver when extracting unused rate-limiting headers.
• Streaming not working when using deprecated Structure.stream field.
• Raw Tool output being lost when being executed by ActionsSubtask.
• Re-order Workflow tasks on every task execution wave.
• Web Loader to catch Exceptions and properly return an ErrorArtifact.
• Conversation Memory entry only added if output_task.output is not None on all Structures
• TextArtifacts contained in ListArtifact returned by WebSearch.search to properly formatted stringified JSON.
• Structure run args not being set immediately.
• Input and output logging in BaseAudioInputTasks and BaseAudioGenerationTasks
• Validation of max_tokens < 0 on BaseChunker

v0.26.0

Added

• AzureOpenAiStructureConfig for providing Structures with all Azure OpenAI Driver configuration.
• AzureOpenAiVisionImageQueryDriver to support queries on images using Azure's OpenAI Vision models.
• AudioLoader for loading audio content into an AudioArtifact.
• AudioTranscriptionTask and AudioTranscriptionClient for transcribing audio content in Structures.
• OpenAiAudioTranscriptionDriver for integration with OpenAI's speech-to-text models, including Whisper.
• Parameter env to BaseStructureRunDriver to set environment variables for a Structure Run.
• PusherEventListenerDriver to enable sending of framework events over a Pusher WebSocket.

Changed

• BREAKING: Removed StructureConfig.global_drivers. Pass Drivers directly to the Structure Config instead.
• BREAKING: Removed StructureConfig.task_memory in favor of configuring directly on the Structure.
• BREAKING: Updated OpenAI-based image query drivers to remove Vision from the name.
• BREAKING: off_prompt now defaults to False on all Tools, making Task Memory something that must be explicitly opted into.
• BREAKING: AmazonSageMakerPromptDriver.model parameter, which gets passed to SageMakerRuntime.Client.invoke_endpoint as EndpointName, is now renamed to AmazonSageMakerPromptDriver.endpoint.
• BREAKING: AmazonSageMakerPromptDriver.model parameter is now optional being passed to SageMakerRuntime.Client.invoke_endpoint as InferenceComponentName (instead of EndpointName).
• BREAKING: SageMakerLlamaPromptModelDriver modified to exclusively support the Llama 3 Instruct model deployed via SageMaker JumpStart. (Support for Llama 2 models has been removed.)
• Simplified custom Task Memory configurations by making several TextArtifactStorage Engines optional.
• Default the value of azure_deployment on all Azure Drivers to the model the Driver is using.
• Field azure_ad_token on all Azure Drivers is no longer serializable.
• Default standard OpenAI and Azure OpenAI image query model to gpt-4o.
• Error message to be more helpful when importing optional dependencies.

v0.25.1

Fixed

• Honor namespace in RedisVectorStoreDriver.query().
• Correctly set the meta, score, and vector fields of query result returned from RedisVectorStoreDriver.query().
• Standardize behavior between omitted and empty actions list when initializing ActionsSubtask.

Added

• Optional event batching on Event Listener Drivers.
• id field to all events.

Changed

• Default behavior of Event Listener Drivers to batch events.
• Default behavior of OpenAiStructureConfig to utilize gpt-4o for prompt_driver.