griptape

🔧 Improvements

• Lock openai at ^0.28 to prevent installation issues until https://github.com/griptape-ai/griptape/issues/420 is implemented.

🚨 Breaking Changes

• Updated Structure.add_event_listener to take an EventListener directly.

🔧 Improvements

• Fixed freeze when using the Stream utility multiple times.
• Fixed boto3 session not being passed from AmazonBedrockEmbeddingDriver to BedrockTitanTokenizer.
• Added Structure.remove_event_listener.

🔧 Improvements

• Fixed requests scope in pyproject.toml.
• Updated Makefile.

🔧 Improvements

• Moved requests from Tool requirements.txt to hard dependency in pyproject.toml.

🚨 Breaking Changes

• Removed BufferConversationMemory.
• Simplified Event Listener format.
• Restrict Python support to >=3.9,<3.12. 3.12 support is coming, but is currently blocked by several downstream libraries.
• Removed Tokenizer's encode and decode methods.
• Removed TextToolMemory and BlobToolMemory.

🆕 New Features

• Combined TextToolMemory and BlobToolMemory under ToolMemory.
• Added Conversation Memory buffering via max_runs parameter.
• Added Conversation Memory pruning to prevent long running conversations from exceeding prompt token limit.
• Added prompt streaming to Prompt Drivers that can support it.
• Added EmailLoader.
• Added support for more file extensions in FileManager Tool.
• Added share_file activity to GoogleDriveClient Tool.
• Added serialization and deserialization for all Events.

🔧 Improvements

• Added BaseVectorStoreDriver.QueryResult.id.
• Fixed SummaryConversationMemory bugs.
• Refactored EmailClient to use EmailLoader.
• Refactored Embedding Drivers to use Chunkers for improvements on embedding large text.
• Added parsing of OpenAi rate limit headers for future use.
• Added __len__ magic methods for Artifacts (thanks @Bubble-Interface!).
• Fixed boto3 session not being passed from BedrockTitanEmbeddingDriver into BedrockTitanTokenizer.

📖 Docs

• Updated docs for new Event Listener format.
• Added page for Extraction Engines.
• Added sections for additional Task types.
• Added page for OpenWeatherClient Tool.
• Added example for PgVectorStoreDriver
• Updated page for Conversation Memory buffering changes.

🔧 Improvements

• Updated snowflake-connector-python dependency that was causing issues in Python 3.11.

🔧 Improvements

• Fixed prompt driver propagation to tool memory defaults in Structures.
• Removed engine defaults in TextToolMemory.
• Improved test coverage.

🆕 New Features

• Added new embedding driver for Amazon Bedrock: BedrockTitanEmbeddingDriver.
• Added new prompt driver for Amazon Bedrock: AmazonBedrockPromptDriver.
• Added new Amazon Bedrock prompt models: BedrockClaudePromptModelDriver, and BedrockJurassicPromptModelDriver, BedrockTitanPromptModelDriver.
• Added new Amazon Bedrock tokenizers: BedrockClaudeTokenizer, BedrockJurassicTokenizer, and BedrockTitanTokenizer.
• Added ignored_exception_types to ExponentialBackoffMixin to ignore certain failures and not retry.
• Added extraction engines for extracting data into JSON objects and CSV rows: JsonExtractionEngine and CsvExtractionEngine.
• Added ExtractionTask to integrate extraction engines into workflows and pipelines.
• Added the GoogleDriveClient tool to access and search files in Google Drive.
• Added the GoogleDocsClient tool to access and edit Google Docs documents.
• Added PgVectorVectorStoreDriver to store and retrieve embeddings in Postgres.

🔧 Improvements

• Added InvalidRequestError to ignored_exception_types in OpenAI drivers.
• Updated all relevant tools to use Griptape loaders.
• Abstracted TextToolMemory and ToolOutputProcessor activities into TextMemoryActivitiesMixin.
• Updated the Calculator tool to use numexpr to improve security.
• Improved base prompts.
• Updated GoogleCalendarClient and GoogleGmailClient to support the owner_email property.
• Fixed OpenAI GPT-4 throttling issues in prompt drivers.

🔧 Improvements

• v0.17.0 didn't include the task and structure-level rules PR, even though the release notes mentioned it. v0.17.1 now includes that PR.

🚨 Breaking Changes

• Removed schema_template_args in all tools. The tool instance can now be accessed directly via {{ _self }} in Jinja activity description templates.

🆕 New Features

• Added FileLoader to load arbitrary files into artifacts.
• Added DataFrameLoader to load Pandas DataFrames into artifacts.
• Added task-level Rulesets for more precise LLM steering inside structures.
• Added the ability to optionally specify Rules in place of structure and task-level Rulesets. This is useful when the user only needs one set of rules per task/structure.
• Added the ability to let the LLM load content directly (not just from memory) into FileManager and AwsS3Client tools.
• Added the ability to map custom loaders based on loaded file extensions in FileManager.
• Added enable_activities() and disable_activities() to ActivityMixin to quickly enable or disable all activities.

🔧 Improvements

• Added BaseMultiModelPromptDriver to better abstract driver methods relevant to handling LLM hosting platforms such as Amazon SageMaker and Hugging Face.
• Added a default Structure.embedding_driver that automatically propagates down to relevant default dependencies.
• Added the ability to specify output file encoding in FileManager.
• Improved action matching in ActionSubtask to handle cases where the LLM wraps action output into markdown or prepends it with extra text.

🔧 Improvements

• Update transformers version in pyproject.toml.
• Update all dependencies in poetry.lock.

🔧 Improvements

• Fixed an issue where some tasks didn't output logs.
• Added task type to the log output.

🆕 New Features

• Added AmazonSageMakerPromptDriver to easily connect open source SageMaker-hosted LLMs.
• Introduced prompt model drivers that abstract input, output, and tokenization for hosted models. In this release we added support for:
  • Llama models with SageMakerLlamaPromptModelDriver.
  • Falcon models with SageMakerFalconPromptModelDriver.
• Added `OpenSearchVectorDriver to integrate OpenSearch vector store and querying capabilities.
• AddedAmazonOpenSearchVectorDriver to support hosted OpenSearch.
• Added TextSummaryTask for quick text summarization in Griptape structures.
• Added ToolTask that allows developers to integrate any tools as a task without having to use chain-of-thought.
• Added TextQueryTask for text querying in Griptape structures.
• Added CsvLoader for loading and pre-processing CSV files.

🔧 Improvements

• Merged the core namespace into utils and moved all mixins into a separate mixins namespace.
• Multiple bug fixes.

🔧 Improvements

• Fixed VectorQueryEngine bugs and made search results more consistent.

🔧 Improvements

• Updated CoT memory prompt for greater consistency and reliability.

🔧 Improvements

• Fixed docker dependency issue.

🚨 Breaking Changes

• griptape-tools was merged into griptape. You can remove griptape-tools from your dependencies.
• PromptTask.prompt_template was renamed to PromptTask.input_template.
• KnowledgeBaseClient tool was renamed to VectorStoreClient.
• OpenAiPromptDriver was split into OpenAiChatPromptDriver and OpenAiCompletionPromptDriver.
• input was renamed to parent_output in agent and pipeline contexts.
• inputs was renamed to parent_outputs in workflow contexts.

🆕 New Features

• Added PromptStack to manage prompt task inputs. Integrated PromptStack into prompt drivers.
• Consolidated prompt templates into generator functions, which makes it easier for developers to override task and engine prompts.
• Added the GoogleCalendar tool.
• Added the GoogleGmail tool.
• Added the ProxycurlClient tool.
• Added MongoDbAtlasVectorStoreDriver.
• Added RedisVectorStoreDriver

🔧 Improvements

• Fixed AzureOpenAiEmbeddingDriver connectivity issues.
• Added validation for tasks to all structures.