* Update content_blocks initialization and add flow_id parameter to ErrorMessage
* feat: include vertex ID in class instantiation
Pass the vertex ID to the custom component during instantiation to facilitate event tracking or management capabilities.
* fix: update message streaming logic to handle None messages and refactor _stream_message parameters
* feat: include flow_id in ChatOutput initialization
Add flow_id to the ChatOutput class to improve the tracking of conversational flows, enhancing the context management within the chat system.
* fix: update chat message source display to use 'source' instead of 'display_name'
* feat: add flow_id to message initialization in ChatOutput class
* fix: handle JSON parsing with type checks for message properties
Refine JSON loading to ensure proper type handling for message properties and content blocks, enhancing stability and preventing potential errors with non-string inputs.
* refactor: update logging structure and message handling
Improve the output logs to support logging multiple entries and ensure robust message streaming with type checking. Adjust error handling parameters for consistency.
* feat: restrict event types in registration and sending
Enhance event management by explicitly defining allowed event types, improving code clarity and reducing potential errors. This ensures only valid event types are registered and sent, leading to more robust event handling.
* Update `logs` attribute to store lists of `Log` objects in `Vertex` class
* feat: introduce TypedDicts for ContentBlock and Properties, update default values in Message model
* fix: restrict event types in send_event method to improve data validation
* Set default values for 'id', 'display_name', and 'source' fields in Source schema
* [autofix.ci] apply automated fixes
* fix: update query to use equality check for error messages
* make lint
* update simple agent test
* test: enhance EventManager tests for event_id validation
* feat: add background, chat icon, and text color properties to component toolkit
* fix: update LogComponent name to display_name for consistency
* remove playground from new cards on main page
* refactor: Update Properties handling in MessageTable and remove unused PropertiesDict
* fix: Set default value for category in MessageBase model
* fix: Update properties default factory in MessageTable model to use model_dump
* Add _build_source method to ChatOutput and update test inputs to use Message objects
* Fix incorrect parameter names in _build_source method across multiple JSON files
* ✅ (freeze.spec.ts, playground.spec.ts, stop-building.spec.ts, linkComponent.spec.ts, sliderComponent.spec.ts, tableInputComponent.spec.ts, stop-button-playground.spec.ts, generalBugs-shard-7.spec.ts): enable tests that were previously skipped to ensure proper functionality and coverage. Remove outdated comments and update test descriptions for clarity.
* Refactor agent event processing to support message streaming and improve content handling
* Refactor ChatOutput to enhance message handling and streamline property assignment
* Fix session ID assignment in send_message method for better message handling
* Add OnTokenFunctionType protocol for enhanced token handling
* Add BorderTrail component for animated border effects
* Add ContentBlockDisplay component for enhanced content visualization and loading state
* Refactor TextShimmer to use motion.create for improved component animation
* Add ContentBlockDisplay to render chat content blocks in newChatMessage component
* Refactor `ChatOutput` class to use `MessageInput` instead of `MessageTextInput` for `input_value` across starter projects.
* Update edge class name from 'runned' to 'ran' in flow components and store
* Add 'on_build_start' and 'on_build_end' events to EventManager
* Add build status updates for 'build_start' and 'build_end' events in buildUtils.ts
* Integrate event management for output function in ComponentToolkit to track build start and end events
* Refactor event handling in ComponentToolkit to improve build event tracking
* Refactor messagesStore to update existing message if it already exists
* update properties to have state attribute
* format
* Refactor chatMessage component to display loading state for partial chat messages
* Refactor reactflowUtils to handle broken edges with missing display names
* fix agent text output
* [autofix.ci] apply automated fixes
* [autofix.ci] apply automated fixes (attempt 2/3)
* fix agent component initialization
* Enhance error message formatting to include detailed exception information
* Refactor agent component for improved performance and stability
* Refactor `LCAgentComponent` to streamline agent execution logic and remove redundant methods
* Add type casting for send_message function in agent.py
* Change return type of function to 'Message' in log schema
* Add `embedding_service` and `client` fields to JSON configurations and refactor ChatOutput class
- Introduced `embedding_service` field in `Vector Store RAG.json` and `Travel Planning Agents.json` to support Astra Vectorize and embedding model selection.
- Added `client` field to `OpenAIEmbeddingsComponent` in JSON configurations for enhanced client configuration.
- Refactored `ChatOutput` class across multiple JSON files to include a new `_build_source` method for constructing `Source` objects, improving code modularity and readability.
- Updated import paths for `OpenAIEmbeddings` to reflect changes in the module structure.
* Update attribute handling in Component class to merge inputs with existing attributes
* Update ChatInput and ChatOutput initialization to include session_id
* Refactor test_load_flow_from_json_object to be asynchronous
* Add asynchronous tests for agent event handling in test_agent_events.py
* Add event handling functions for agent tool and chain events
- Implement functions to handle various agent events such as `on_chain_start`, `on_chain_end`, `on_tool_start`, `on_tool_end`, and `on_tool_error`.
- Introduce helper functions to build content blocks for agent messages.
- Create mappings for chain and tool event handlers.
- Refactor `process_agent_events` to utilize the new event handling functions.
- Remove the old `process_agent_events` implementation from `agent.py` and import the new one from `events.py`.
* feat: update content structure and validation logic
Enhance content block to accept a list of contents instead of a single item, and implement validation to ensure proper format. Refactor tool-related content types for improved clarity and functionality.
* Handle ValidationError in error message generation and update import paths
* feat: enhance error event creation to include structured error content
* move validators and remove utils.py
* feat: add event handler tests for agent tool and chain events
* refactor: streamline tool content structure
Combine multiple tool-related types into a single, more flexible interface. This simplifies the content handling by allowing optional properties for output, error, and timestamp, enhancing overall code maintainability. Adjust the ContentBlock interface to accommodate an array of contents for improved flexibility.
* feat: refactor error handling in ChatMessage component to support dynamic content blocks
* feat: enhance ContentBlockDisplay to support Markdown rendering and dynamic content handling
* Refactor agent event handling to simplify content block management
* Enhance `ContentBlockDisplay` with separators and improved content rendering logic
* add inline block to prevent text overflow in reason
* Refactor code to enhance Markdown rendering and dynamic content handling in ChatMessage component
* [autofix.ci] apply automated fixes
* Add timestamp field to BaseContent class and remove from ToolContent class
* Update timestamp validation to include fractional seconds in BaseContent class
* Add duration calculation for agent and tool events in events.py
* Refactor ContentBlock to use Pydantic's Discriminator and Tag for content types
* Add field validators for content_blocks and properties in Message class
* Add field serializer for source in Properties class
* Add type hint for serialize_properties method in MessageTable class
* create duration component and refactor contents
* [autofix.ci] apply automated fixes
* Refactor duration calculation to use perf_counter for improved accuracy and update ContentBlockDict to use dict for contents
* Update properties field validator to use 'before' mode for improved validation
* Refactor MessageTable to use ContentBlock instead of ContentBlockDict and enhance validation and serialization for properties and content_blocks
* Refactor AgentComponent to streamline agent initialization by using the set method directly
* Refactor event handling functions to use synchronous definitions and improve performance with asyncio.to_thread
* Refactor PythonREPLToolComponent to raise ToolException on error instead of returning error message
* Refactor CalculatorToolComponent to enhance error handling by raising ToolException and improving expression evaluation feedback
* Fix TextShimmer width in ContentBlockDisplay for improved layout consistency
* Enhance ContentBlockDisplay to support external links and math rendering in Markdown
* Enhance error handling in Calculator and Python REPL tools by introducing `ToolException` and improving expression evaluation logic.
* Refactor agent message properties to remove unnecessary icons and update content block titles for clarity
* feat: enhance agent and tool content messaging
Add headers to agent and tool content messages for better clarity and user experience.
* Handle nested schema structure in ContentBlock initialization
* fix: update agent input text content return type and enhance error message formatting
* Add placeholder and default value for model selection in AstraVectorStoreComponent
* Refactor event handling functions to remove `send_message_method` parameter and streamline message processing logic.
* Add model configuration to ToolContent for alias population
* Refactor agent event tests to improve message handling and content block initialization
* test: Update test durations for performance metrics
Adjust the recorded execution times for various test cases to ensure accurate performance tracking and facilitate optimization efforts.
* Refactor test_load_flow_from_json_object to improve project loading logic
* Make `HeaderDict` fields optional and update `header` field in `BaseContent`
* Enhance `Message` and `ChatOutput` with additional attributes for testing
* Update test duration metrics in .test_durations file
* Refactor `ContentDisplay` component to support multiple content types and improve rendering logic
* feat: Enhance duration display with human-readable format
Integrate the pretty-ms library to convert duration display metrics into a more user-friendly format, improving the overall user experience. Update dependencies to ensure compatibility with the latest version and optimize for newer Node.js versions.
* feat: Add optional duration and header properties to BaseContent interface
* fix: Change duration type from float to int in BaseContent class
* Remove default value for 'start_time' in duration calculations
* Enhance `ContentBlockDisplay` with dynamic header and expand/collapse animation
- Added `state` prop to `ContentBlockDisplay` to dynamically set header icon and title based on content state.
- Implemented `renderContent` function to encapsulate content rendering logic with animation.
- Integrated `ForwardedIconComponent` for displaying header icons.
- Updated `newChatMessage.tsx` to pass `state` prop to `ContentBlockDisplay`.
* Add animation to header title using AnimatePresence and motion components
* Add support for processing zip files with multithreading in FileComponent
- Enhanced FileComponent to handle individual and zipped text files.
- Introduced multithreading option for parallel processing of files within zip archives.
- Updated supported file types to include zip files.
- Improved error handling and logging for file processing.
* Expand `Message` conversion to support `AsyncIterator` and `Iterator` types.
* Remove unused function _find_or_create_tool_content from events.py
* Add header information to tool content and streamline message sending in event processing
* Add send_message_method parameter to event handlers for message dispatching
- Updated event handler functions to include a new parameter, `send_message_method`, allowing for message dispatching within the handlers.
- Modified the logic in each handler to utilize the `send_message_method` for sending messages.
- Adjusted the main event processing logic to pass the `send_message_method` to the appropriate handlers.
* Refactor ContentBlockDisplay component to improve rendering performance and user experience
* Refactor `ContentBlockDisplay.tsx` to improve readability and update header title logic
* [autofix.ci] apply automated fixes
* Add 'start_time' to event data and update test functions to include send_message mock
* Refactor ContentBlockDisplay component to include total duration and improve user experience
* Refactor ContentBlockDisplay component to handle isLoading state for total duration calculation
* Refactor animatedNumbers component and add AnimatedNumberBasic component
- Refactor the animatedNumbers component to improve readability and update the header title logic.
- Add a new component called AnimatedNumberBasic that displays an animated number with a specific value.
* Refactor agent message creation to improve event processing efficiency
* Refactor session ID assignment in run_graph_internal for improved clarity
* [autofix.ci] apply automated fixes
* fix: update agent message properties handling for improved compatibility
* fix: enhance message property validation to support dictionary input
* Add session_id to agent message initialization in tests
- Updated test cases in `test_agent_events.py` to include `session_id` in the `Message` initialization.
- Adjusted calls to `process_agent_events` to pass the `agent_message` with `session_id`.
* feat: Enhance event handling with duration tracking
Add start_time parameter to event handling functions to ensure consistent duration calculations across different stages of agent processing. This improves accuracy in measuring event durations and enhances overall event management.
* Add optional humanized value to AnimatedNumber component and update DurationDisplay usage
* Refactor `ContentDisplay` and add separator to `ContentBlockDisplay` component
* Add header to text content in agent message events
* Add separator between each content block in ContentBlockDisplay component
* Refactor layout in ContentDisplay component for improved styling and positioning
* Refactor event handlers to return updated start_time and agent_message
- Modified event handler functions to return a tuple of `agent_message` and `start_time`.
- Updated `_calculate_duration` to handle `start_time` as an integer.
- Ensured `start_time` is reset using `perf_counter()` after each event handling.
- Adjusted tool and chain event handler calls to accommodate the new return type.
* Add start_time and duration checks to agent event handlers in tests
- Updated test cases for `handle_on_chain_start`, `handle_on_chain_end`, `handle_on_tool_start`, `handle_on_tool_end`, `handle_on_tool_error`, and `handle_on_chain_stream` to include `start_time` as a return value.
- Added assertions to verify that `start_time` is a float and `duration` is an integer where applicable.
* [autofix.ci] apply automated fixes
* update colors and spacing of time
* [autofix.ci] apply automated fixes
* Refactor DurationDisplay component to display duration in seconds
* Rename case from "message" to "add_message" in buildUtils.ts switch statement
* Add event registration for message removal in EventManager
* Add category handling for message events in Component class
* Add custom exception handling for agent message processing
* Handle exceptions in agent event processing with message deletion and event notification
* Add new LLM options and refactor AgentComponent for dynamic provider handling
- Introduced new language model options: Anthropic, Groq, and NVIDIA.
- Refactored `AgentComponent` to utilize `MODEL_PROVIDERS_DICT` for dynamic provider handling.
- Simplified input management by removing hardcoded provider inputs and using a dictionary-based approach.
- Enhanced `update_build_config` to support flexible provider configurations and custom options.
* Refactor buildUtils.ts and add message removal handling
* Update Source model to allow None values for id, display_name, and source fields
* Refactor event handler functions to return tuple of Message and float
* Refactor `ChatOutput` class to use `MessageInput` instead of `MessageTextInput` for `input_value` across starter projects.
* Add test for updating component outputs with dynamic code input
* feat: add ToolModeMixin to manage tool mode state
* feat: add parameterName to mutateTemplate for enhanced template mutation
* feat: add tool mode functionality to node toolbar
Implement a toggle for tool mode, allowing users to easily switch functionalities within the node toolbar. This enhancement improves user interaction by providing a dedicated mode for tool-related tasks.
* feat: integrate ToolModeMixin into MessageTextInput for enhanced functionality
* Update parameterId to "tool_mode" in nodeToolbarComponent
* feat: implement tool mode output handling in run_and_validate_update_outputs
* feat: add conditional rendering for tool mode button based on template fields
* fix: enhance null checks for tool mode button visibility and output validation
* feat: add isToolMode property to NodeInputFieldComponentType for enhanced functionality
* feat: add isToolMode prop to NodeInputField for conditional styling
* feat: implement sorting logic for tool mode fields in GenericNode component
* feat: add isToolMode prop to NodeOutputField for conditional styling
* feat: pass isToolMode prop to NodeOutputField for conditional styling
* feat: update disabled logic in NodeInputField to include isToolMode
* Add default placeholder to getPlaceholder function and constants file
* feat: Enable dynamic placeholders in input components
Add support for customizable placeholder text across various input components to enhance usability and improve user experience.
* feat: Add optional placeholder prop to InputProps type
* feat: Add placeholder prop to InputGlobalComponent and CustomParameterComponent
* feat: Set dynamic placeholder for NodeInputField based on tool mode
* feat: Update NodeOutputField styling for tool mode and pass isToolMode prop
* feat: Add isToolMode prop to OutputComponent for dynamic styling
* feat: Add TOOL_OUTPUT_DISPLAY_NAME constant for toolset display
* feat: Update tool output display name to use TOOL_OUTPUT_DISPLAY_NAME constant
* feat: Conditionally render Freeze Path button based on tool mode
* Add support for asynchronous output methods and tool mode validation in component tools
* feat: Validate required inputs for tool mode before executing output methods
* Refactor: Rename method to indicate private access in custom_component
- Changed `get_function_entrypoint_return_type` to `_get_function_entrypoint_return_type` in `custom_component.py` to reflect its intended private usage.
- Updated references to the renamed method in `utils.py` and `directory_reader.py` to maintain consistency.
* feat: Implement tool output mapping based on tool mode presence in inputs
* Refactor tests to use private method _get_function_entrypoint_return_type
* feat: Enable tool mode for input_value in LCAgentComponent
* Add test for updating component outputs with dynamic code input
* feat: add tool mode functionality to node toolbar
Implement a toggle for tool mode, allowing users to easily switch functionalities within the node toolbar. This enhancement improves user interaction by providing a dedicated mode for tool-related tasks.
* feat: add conditional rendering for tool mode button based on template fields
* feat: add isToolMode prop to NodeInputField for conditional styling
* feat: Set dynamic placeholder for NodeInputField based on tool mode
* feat: Add TOOL_OUTPUT_DISPLAY_NAME constant for toolset display
* feat: Conditionally render Freeze Path button based on tool mode
* Add tool mode support to LCAgentComponent
- Introduced new input fields: `agent_name`, `agent_description`, and `add_tools_to_description` to support tool mode.
- Implemented methods `get_tool_name`, `get_tool_description`, `_build_tools_description`, and `to_toolkit` for handling tool-related functionalities.
- Enhanced `MessageTextInput` with additional information for better user guidance.
- Updated agent message sender name to use `agent_name` if available.
* Fix return statement placement in event handling logic
* Add tool mode enhancements and error handling in component_tool
- Introduce optional parameters `tool_name`, `tool_description`, and `callbacks` to `get_tools` method.
- Implement error handling for tool creation with `handle_tool_error` and `callbacks`.
- Ensure single tool validation when `tool_name` or `tool_description` is provided.
- Add support for `BaseModel` result serialization using `model_dump`.
* Refactor agent response method and update output configuration
* Remove unused 'input_value' field from tool_calling.py configuration
* Refactor source property assignment to use _build_source method
* Enhance callable input check and add callbacks to toolkit conversion
* Add unit tests for message update functionality in backend
- Implement tests for updating single and multiple messages.
- Add tests for handling nonexistent messages during updates.
- Include tests for updating messages with timestamps, content blocks, and nested properties.
- Ensure proper serialization and storage of message properties.
* Add field serializer for 'output' using jsonable_encoder in content_types.py
* Add tool mode fields and refactor message response in starter projects
- Introduced new fields `add_tools_to_description`, `agent_description`, and `agent_name` for tool mode configuration in JSON starter projects.
- Refactored `message_response` method to utilize `_build_source` for constructing message source properties.
- Updated method references from `get_response` to `message_response` for consistency.
- Adjusted input field descriptions and added missing metadata attributes.
* Implement no-op send_message function and patching decorator for component tools
* Refactor output handling in component tool to support Message and Data types
* Simplify exception handling by removing redundant exception re-raise
* Enhance tool assignment logic to preserve existing name and description if not provided
* feat: Enhance agent name and description handling
Refactor the agent component to dynamically include tool names in the default agent name and description. This improves clarity for users by providing more context about the agent's capabilities and ensures consistent representation of tools in the interface.
* refactor: Update agent description and name info to include default values and dynamic tool integration
* Add custom encoders for serialization and refactor schema modules
- Introduce `CUSTOM_ENCODERS` in `encoders.py` to handle serialization of `Callable` and `datetime` objects.
- Refactor `BaseContent` to use `model_serializer` for model serialization with custom encoders.
- Remove redundant `encode_callable` function and `CUSTOM_ENCODERS` definition from `artifact.py`.
- Update imports and clean up unused imports in schema modules.
* Remove 'agent_name' field and update 'get_tool_name' method in agent.py
* Enhance `serialize_model` method with `wrap` mode and improved error handling
* Add 'tool_mode' attribute to frontend node class
* Add unit tests for ContentBlock initialization and content handling
* Add unit tests for content types serialization and creation
* Refactor tool mode initialization logic in NodeToolbarComponent
* Add tool mode functionality to node toolbar and flow store
* Add updateNodeInternals call for tool_mode case in nodeToolbarComponent
* Add condition to hide handle in tool mode in NodeInputField component
* Add shortcut for activating Tool Mode and integrate into node toolbar
* Add tool_mode parameter to MessageTextInput and update attributes mapping
* Remove 'agent_name' field from Agent Flow configuration file
* Update agent message to use display_name instead of agent_name
* Add validation for required tools in agent execution and component setup
* Make 'tools' field required in AgentComponent configuration
* test: add unit tests for run_and_validate_update_outputs functionality
Implement comprehensive tests for the `run_and_validate_update_outputs` method across various scenarios, including enabling/disabling tool mode, handling invalid output structures, and supporting custom update logic. Validate that outputs are correctly updated and ensure appropriate error handling for invalid cases.
* test: update component toolkit tests to use CalculatorToolComponent
* Enhance input schema creation logic for tool mode components
* Include input expression in error responses for calculator tool
* Enhance `visit_Attribute` to check for required inputs in `tree_visitor.py`
* fix: add checks for graph attribute before accessing session and flow IDs in Component methods
* fix: set default value to None for id field in PlaygroundEvent model
* fix: remove unused add_toolkit_output flag from FeatureFlags model
* Refactor JSON configurations to remove unnecessary required inputs across starter projects
* Add tool mode validation and improve error handling
- Updated import statement for ContentBlock to fix import path.
- Modified `send_message_noop` to require a `Message` parameter and added type ignore for method assignment.
- Enhanced error message in tool mode validation to handle `None` input names.
- Changed return type of `send_error_message` to `Message` for consistency.
- Provided default value for `get_tool_name` to handle missing display names.
* Add pytest fixture to test_component_message_sending test
---------
Co-authored-by: anovazzi1 <otavio2204@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: cristhianzl <cristhian.lousa@gmail.com>
* Add `required_inputs` field to `Output` model in `base.py`
* Refactor ComponentTool to ComponentToolkit and enhance tool creation logic
- Replaced `ComponentTool` with `ComponentToolkit` to better encapsulate component-related tools.
- Introduced `build_description` and `_build_output_function` helper functions for dynamic tool creation.
- Updated tool initialization to handle multiple outputs and required inputs using `StructuredTool`.
- Improved schema creation for tool arguments based on component inputs.
* Refactor `to_tool` method to `to_toolkit` to use `ComponentToolkit` instead of `ComponentTool`
* Refactor `ComponentTool` to `ComponentToolkit` in unit tests
- Updated import statements to reflect the new `ComponentToolkit` class.
- Modified test logic to use `ComponentToolkit` for retrieving tools.
- Adjusted assertions to match the new structure and output format.
- Ensured compatibility with `Message` schema for output validation.
* Refactor `test_component_to_tool` to validate `ComponentToolkit` and tool properties
* Refactor `build_description` to include input types in the output format
* Add method to set required inputs for outputs based on method analysis
- Introduced `_set_output_required_inputs` method to determine and set required inputs for each output by analyzing the method's source code.
- Added necessary imports (`ast` and `dedent`) to support the new functionality.
* Update test to assert full tool description in test_component_to_tool.py
* Add unit tests for verifying required inputs of various components
- Added tests to ensure that required inputs for outputs are present in the inputs of `ChatInput`, `ChatOutput`, `SequentialTaskComponent`, `ToolCallingAgentComponent`, and `OpenAIModelComponent`.
- Included helper functions to check if required inputs are in inputs and to assert that all outputs have different required inputs.
* Add RequiredInputsVisitor to identify required inputs in AST nodes
- Introduced RequiredInputsVisitor class to traverse AST nodes and collect required inputs.
- The visitor checks for 'self' attributes matching the provided inputs and adds them to the required_inputs set.
* Refactor required inputs extraction using `RequiredInputsVisitor`
* Add feature flags configuration for toolkit output in settings
* Add toolkit output handling based on feature flag in custom component utils
* Add method to append 'component_as_tool' output in custom component
* Add unit test for toolkit output feature flag in custom component
* Add utility functions for lazy loading and instantiating input types in langflow
- Introduced `get_InputTypesMap` for lazy loading of `InputTypesMap`.
- Added `instantiate_input` function to create instances of input types dynamically.
- Included type checking and error handling for invalid input types.
* Refactor input instantiation logic and update imports
- Removed `instantiate_input` function from `inputs.py` and moved it to `utils.py`.
- Updated imports in `base.py` to reflect the new location of `instantiate_input`.
- Added missing import for `Callable` in `base.py`.
* Refactor import statement to use `instantiate_input` from `langflow.inputs.utils` in test_inputs.py
* Add TOOL_OUTPUT_NAME constant to tools module
* Add type checking and TOOL_OUTPUT_NAME filter in ComponentToolkit
- Introduced `TYPE_CHECKING` for type hints to avoid circular imports.
- Added `TOOL_OUTPUT_NAME` constant to filter specific outputs in `ComponentToolkit`.
- Updated type annotations to use forward references.
* Refactor component toolkit import to avoid circular dependency and use constant for tool output name
* Refactor `ComponentToolkit` class to remove inheritance from `BaseToolkit` and add an initializer for `component`
* Add unit test for ComponentToolkit in test_component_to_tool
- Added `test_component_to_tool_has_no_component_as_tool` to verify that `ComponentToolkit` correctly initializes with a `ChatInput` component and returns the expected tools.
* Refactor toolkit output handling to `custom_component` module
* fix: mypy errors union-attr and arg-type
* Add 'OTHER' field type to schema in langflow/io/schema.py
* Add tool name formatting to ComponentToolkit to ensure valid characters
* Refactor toolkit output handling and add type hint for `to_toolkit` method
* Add `is_interface_component` attribute to vertex types and update import order
* Add tests for ToolCallingAgentComponent and ChatOutput with API key handling
- Updated `test_component_tool` to reflect new description format.
- Added `test_component_tool_with_api_key` to test `ToolCallingAgentComponent` with `ChatOutput` and OpenAI API key.
- Enabled `add_toolkit_output` feature flag for testing.
* Refactor `_find_matching_output_method` to accept `input_name` parameter for more precise input-output matching
* Replace ValueError with warning in build_description function
* use chat_output component directly in set
* [autofix.ci] apply automated fixes
* [autofix.ci] apply automated fixes
* [autofix.ci] apply automated fixes (attempt 3/3)
* Refactor: Reorder method calls in `__init__` for logical consistency
Moved `set_class_code` method call to ensure output types and required inputs are set before class code initialization.
* Update _format_tool_name to allow '.' in tool names
* Refactor `_format_tool_name` to remove non-alphanumeric characters
* Update test assertions for component tool name and output mapping
* Handle case where 'required_inputs' is empty in 'component_tool.py'
* Refactor import statements for better readability in `base.py`
* [autofix.ci] apply automated fixes
* Add noqa comment to suppress import warning and re-add Any import in base.py
---------
Co-authored-by: italojohnny <italojohnnydosanjos@gmail.com>
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
* refactor: Add _find_matching_output_method to Component class
* feat: allow components to be passed in set method
* fix: Add test for graph set method with valid component
* set value variable to the output callable
* refactor: Update test_component.py to use set_component method
This commit refactors the test_component.py file in the custom_component directory. The test_set_invalid_input() function has been renamed to test_set_component() to better reflect its purpose. Additionally, the test_set_component() function now sets the agent parameter using the set_component() method instead of raising a ValueError. This change improves the readability and maintainability of the code.
* refactor: Fix formatting issue in _build_error_string_from_matching_pairs
The _build_error_string_from_matching_pairs method in the Component class had a formatting issue when input types were empty. This commit fixes the issue by adding a check for empty input types and providing an empty list as a fallback. This improves the accuracy and readability of the error string generated by the method.
* fix(component.py): add validation to ensure output method is a string to prevent potential runtime errors
* refactor: update code references to use _code instead of code
* refactor: add backwards compatible attributes to Component class
* refactor: update Component constructor to pass config params with underscore
Refactored the `Component` class in `component.py` to handle inputs and outputs. Added a new method `map_outputs` to map a list of outputs to the component. Also updated the `__init__` method to properly initialize the inputs, outputs, and other attributes. This change improves the flexibility and extensibility of the `Component` class.
Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org>
* refactor: change attribute to use underscore
* refactor: update CustomComponent initialization parameters
Refactored the `instantiate_class` function in `loading.py` to update the initialization parameters for the `CustomComponent` class. Changed the parameter names from `user_id`, `parameters`, `vertex`, and `tracing_service` to `_user_id`, `_parameters`, `_vertex`, and `_tracing_service` respectively. This change ensures consistency and improves code readability.
Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org>
* refactor: update BaseComponent to accept UUID for _user_id
Updated the `BaseComponent` class in `base_component.py` to accept a `UUID` type for the `_user_id` attribute. This change improves the type safety and ensures consistency with the usage of `_user_id` throughout the codebase.
* refactor: import nanoid with type annotation
The `nanoid` import in `component.py` has been updated to include a type annotation `# type: ignore`. This change ensures that the type checker ignores any errors related to the `nanoid` import.
* fix(custom_component.py): convert _user_id to string before passing to functions to ensure compatibility with function signatures
* feat(component.py): add method to set output types based on method return type to improve type checking and validation in custom components
* refactor: extract method to get method return type in CustomComponent
* refactor(utils.py): refactor code to use _user_id instead of user_id for consistency and clarity
perf(utils.py): optimize code by reusing cc_instance instead of calling get_component_instance multiple times
* refactor(utils.py, base.py): change parameter name 'add_name' to 'keep_name' for clarity and consistency in codebase
* [autofix.ci] apply automated fixes
* refactor: update schema.py to include Edge related typres
The `schema.py` file in the `src/backend/base/langflow/graph/edge` directory has been updated to include the `TargetHandle` and `SourceHandle` models. These models define the structure and attributes of the target and source handles used in the edge data. This change improves the clarity and consistency of the codebase.
* refactor: update BaseInputMixin to handle invalid field types gracefully
The `BaseInputMixin` class in `input_mixin.py` has been updated to handle invalid field types gracefully. Instead of raising an exception, it now returns `FieldTypes.OTHER` for any invalid field type. This change improves the robustness and reliability of the codebase.
* refactor: update file_types field alias in FileMixin
The `file_types` field in the `FileMixin` class of `input_mixin.py` has been updated to use the `alias` parameter instead of `serialization_alias`. This change ensures consistency and improves the clarity of the codebase.
* refactor(inputs): update field_type declarations in various input classes to use SerializableFieldTypes enum for better type safety and clarity
* refactor(inputs): convert dict to Message object in _validate_value method
* refactor(inputs): convert dict to Message object in _validate_value method
* refactor(inputs): update model_config in BaseInputMixin to enable populating by name
The `model_config` attribute in the `BaseInputMixin` class of `input_mixin.py` has been updated to include the `populate_by_name=True` parameter. This change allows the model configuration to be populated by name, improving the flexibility and usability of the codebase.
* refactor: update _extract_return_type method in CustomComponent to accept Any type
The _extract_return_type method in CustomComponent has been updated to accept the Any type as the return_type parameter. This change improves the flexibility and compatibility of the method, allowing it to handle a wider range of return types.
* refactor(component): add get_input and get_output methods for easier access to input and output values
The `Component` class in `component.py` has been updated to include the `get_input` and `get_output` methods. These methods allow for easier retrieval of input and output values by name, improving the usability and readability of the codebase.
* refactor(vertex): add get_input and get_output methods for easier access to input and output values
* refactor(component): add set_output_value method for easier modification of output values
The `Component` class in `component.py` has been updated to include the `set_output_value` method. This method allows for easier modification of output values by name, improving the usability and flexibility of the codebase.
* feat: add run_until_complete and run_in_thread functions for handling asyncio tasks
The `async_helpers.py` file in the `src/backend/base/langflow/utils` directory has been added. This file includes the `run_until_complete` and `run_in_thread` functions, which provide a way to handle asyncio tasks in different scenarios. The `run_until_complete` function checks if an event loop is already running and either runs the coroutine in a separate event loop in a new thread or creates a new event loop and runs the coroutine. The `run_in_thread` function runs the coroutine in a separate thread and returns the result or raises an exception if one occurs. These functions improve the flexibility and usability of the codebase.
* refactor(component): add _edges attribute to Component class for managing edges
The `Component` class in `component.py` has been updated to include the `_edges` attribute. This attribute is a list of `EdgeData` objects and is used for managing edges in the component. This change improves the functionality and organization of the codebase.
* fix(component.py): fix conditional statement to check if self._vertex is not None before accessing its attributes
* refactor(component): add _get_fallback_input method for handling fallback input
The `Component` class in `component.py` has been updated to include the `_get_fallback_input` method. This method returns an `Input` object with the provided keyword arguments, which is used as a fallback input when needed. This change improves the flexibility and readability of the codebase.
* refactor(component): add TYPE_CHECKING import for Vertex in component.py
* refactor(component): add _map_parameters_on_frontend_node and _map_parameters_on_template and other methods
The `Component` class in `component.py` has been refactored to include the `_map_parameters_on_frontend_node` and `_map_parameters_on_template` methods. These methods are responsible for mapping the parameters of the component onto the frontend node and template, respectively. This change improves the organization and maintainability of the codebase.
* refactor(component): Add map_inputs and map_outputs methods for mapping inputs and outputs
The `Component` class in `component.py` has been updated to include the `map_inputs` and `map_outputs` methods. These methods allow for mapping the given inputs and outputs to the component, improving the functionality and organization of the codebase.
* refactor(component): Add Input, Output, and ComponentFrontendNode imports and run_until_complete function
This commit refactors the `component.py` file in the `src/backend/base/langflow/custom/custom_component` directory. It adds the `Input`, `Output`, and `ComponentFrontendNode` imports, as well as the `run_until_complete` function from the `async_helpers.py` file. These changes improve the functionality and organization of the codebase.
* refactor(component): Add map_inputs and map_outputs methods for mapping inputs and outputs
* refactor(component): Add _process_connection_or_parameter method for handling connections and parameters
The `Component` class in `component.py` has been updated to include the `_process_connection_or_parameter` method. This method is responsible for handling connections and parameters based on the provided key and value. It checks if the value is callable and connects it to the component, otherwise it sets the parameter or attribute. This change improves the functionality and organization of the codebase.
* refactor(frontend_node): Add set_field_value_in_template method for updating field values
The `FrontendNode` class in `base.py` has been updated to include the `set_field_value_in_template` method. This method allows for updating the value of a specific field in the template of the frontend node. It iterates through the fields and sets the value of the field with the provided name. This change improves the flexibility and functionality of the codebase.
* refactor(inputs): Add DefaultPromptField class for default prompt inputs
The `inputs.py` file in the `src/backend/base/langflow/inputs` directory has been refactored to include the `DefaultPromptField` class. This class represents a default prompt input with customizable properties such as name, display name, field type, advanced flag, multiline flag, input types, and value. This change improves the flexibility and functionality of the codebase.
* feat: Add Template.from_dict method for creating Template objects from dictionaries
This commit adds the `from_dict` class method to the `Template` class in `base.py`. This method allows for creating `Template` objects from dictionaries by converting the dictionary keys and values into the appropriate `Template` attributes. This change improves the flexibility and functionality of the codebase.
* refactor(frontend_node): Add from_dict method for creating FrontendNode objects from dictionaries
* refactor: update BaseComponent to use get_template_config method
Refactored the `BaseComponent` class in `base_component.py` to use the `get_template_config` method instead of duplicating the code. This change improves code readability and reduces redundancy.
* refactor(graph): Add EdgeData import and update add_nodes_and_edges method signature
The `Graph` class in `base.py` has been updated to include the `EdgeData` import and modify the signature of the `add_nodes_and_edges` method. The `add_nodes_and_edges` method now accepts a list of dictionaries representing `EdgeData` objects instead of a list of dictionaries with string keys and values. This change improves the type safety and clarity of the codebase.
* refactor(graph): Add first_layer property to Graph class
The `Graph` class in `base.py` has been updated to include the `first_layer` property. This property returns the first layer of the graph and throws a `ValueError` if the graph is not prepared. This change improves the functionality and organization of the codebase.
* refactor(graph): Update Graph class instantiation in base.py
The `Graph` class in `base.py` has been updated to use keyword arguments when instantiating the class. This change improves the readability and maintainability of the codebase.
* refactor(graph): Add prepare method to Graph class
The `Graph` class in `base.py` has been updated to include the `prepare` method. This method prepares the graph for execution by validating the stream, building edges, and sorting vertices. It also adds the first layer of vertices to the run manager and sets the run queue. This change improves the functionality and organization of the codebase.
* refactor(graph): Improve graph preparation in retrieve_vertices_order function
The `retrieve_vertices_order` function in `chat.py` has been updated to improve the graph preparation process. Instead of manually sorting vertices and adding them to the run manager, the function now calls the `prepare` method of the `Graph` class. This method validates the stream, builds edges, and sets the first layer of vertices. This change improves the functionality and organization of the codebase.
* refactor: Add GetCache and SetCache protocols for caching functionality
* refactor(graph): Add VertexBuildResult class for representing vertex build results
* refactor(chat.py, base.py): update build_vertex method in chat.py and base.py
* refactor(graph): Update Edge and ContractEdge constructors to use EdgeData type
The constructors of the `Edge` and `ContractEdge` classes in `base.py` have been updated to use the `EdgeData` type for the `edge` and `raw_edge` parameters, respectively. This change improves the type safety and clarity of the codebase.
* feat: add BaseModel class with model_config attribute
A new `BaseModel` class has been added to the `base_model.py` file. This class extends the `PydanticBaseModel` and includes a `model_config` attribute of type `ConfigDict`. This change improves the codebase by providing a base model with a configuration dictionary for models.
Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org>
* refactor: update langflow.graph.edge.schema.py
Refactor the `langflow.graph.edge.schema.py` file to include the `TargetHandle` and `SourceHandle` models. This change improves the clarity and consistency of the codebase.
Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org>
* refactor(base): Update target_param assignment in Edge class
The `target_param` assignment in the `Edge` class of `base.py` has been updated to use the `cast` function for type hinting. This change improves the type safety and clarity of the codebase.
* refactor(base): Add check for existing type in add_types method
* refactor: update build_custom_component_template to use add_name instead of keep_name
Refactor the `build_custom_component_template` function in `utils.py` to use the `add_name` parameter instead of the deprecated `keep_name` parameter. This change ensures consistency with the updated method signature and improves code clarity.
* feat(component.py): add method to set output types based on method return type to improve type checking and validation in custom components (#3115)
* feat(component.py): add method to set output types based on method return type to improve type checking and validation in custom components
* refactor: extract method to get method return type in CustomComponent
* refactor: update _extract_return_type method in CustomComponent to accept Any type
The _extract_return_type method in CustomComponent has been updated to accept the Any type as the return_type parameter. This change improves the flexibility and compatibility of the method, allowing it to handle a wider range of return types.
* refactor: add _template_config property to BaseComponent
Add a new `_template_config` property to the `BaseComponent` class in `base_component.py`. This property is used to store the template configuration for the custom component. If the `_template_config` property is empty, it is populated by calling the `build_template_config` method. This change improves the efficiency of accessing the template configuration and ensures that it is only built when needed.
* refactor: add type checking for Output types in add_types method
Improve type checking in the `add_types` method of the `Output` class in `base.py`. Check if the `type_` already exists in the `types` list before adding it. This change ensures that duplicate types are not added to the list.
* update starter projects
* refactor: optimize imports in base.py
Optimize imports in the `base.py` file by removing unused imports and organizing the remaining imports. This change improves code readability and reduces unnecessary clutter.
* fix(base.py): fix condition to check if self.types is not None before checking if type_ is in self.types
* refactor: update build_custom_component_template to use add_name instead of keep_name
* refactor(prompts): Update PromptComponent to support custom fields and template updates
The `PromptComponent` class in `Prompt.py` has been updated to support custom fields and template updates. The `_update_template` method has been added to update the prompt template with custom fields. The `post_code_processing` method has been modified to update the template and improve backwards compatibility. The `_get_fallback_input` method has been added to provide a default prompt field. These changes improve the functionality and flexibility of the codebase.
* refactor(base): Add DefaultPromptField to langflow.io
The `DefaultPromptField` class has been added to the `langflow.io` module. This class provides a default prompt field for the `TableInput` class. This change improves the functionality and flexibility of the codebase.
* refactor(prompts): Update PromptComponent to support custom fields and template updates
* refactor(base): Update langflow.template.field.prompt.py for backwards compatibility
* refactor(base): Update langflow.components.__init__.py to import the prompts module
This change adds the prompts module to the list of imports in the __init__.py file of the langflow.components package. This ensures that the prompts module is available for use in the codebase.
* refactor(base): Update langflow.template.field.prompt.py for backwards compatibility
* refactor(graph): Update VertexTypesDict to import vertex types lazily
The VertexTypesDict class in constants.py has been updated to import vertex types lazily. This change improves the performance of the codebase by deferring the import until it is actually needed.
* refactor(graph): Add missing attributes and lock to Graph class
The Graph class in base.py has been updated to add missing attributes and a lock. This change ensures that the necessary attributes are initialized and provides thread safety with the addition of a lock. It improves the functionality and reliability of the codebase.
* refactor(graph): Add method to set inputs in Graph class
The `_set_inputs` method has been added to the Graph class in base.py. This method allows for setting inputs for specific vertices based on input components, inputs, and input type. It improves the functionality and flexibility of the codebase.
* refactor(graph): Set inputs for specific vertices in Graph class
The `_set_inputs` method has been added to the Graph class in base.py. This method allows for setting inputs for specific vertices based on input components, inputs, and input type. It improves the functionality and flexibility of the codebase.
* refactor(graph): Update Graph class to set cache using flow_id
The `Graph` class in `base.py` has been updated to set the cache using the `flow_id` attribute. This change ensures that the cache is properly set when `cache` is enabled and `flow_id` is not None. It improves the functionality and reliability of the codebase.
* refactor(graph): Refactor Graph class to improve edge building
The `Graph` class in `base.py` has been refactored to improve the process of building edges. The `build_edge` method has been added to encapsulate the logic of creating a `ContractEdge` object from the given `EdgeData`. This change enhances the readability and maintainability of the codebase.
* refactor(graph): Update _create_vertex method parameter name for clarity
The `_create_vertex` method in the `Graph` class of `base.py` has been updated to change the parameter name from `vertex` to `frontend_data` for improved clarity. This change enhances the readability and maintainability of the codebase.
* refactor(graph): Update Graph class to return first layer in sort_interface_components_first
The `sort_interface_components_first` method in the `Graph` class of `base.py` has been updated to return just the first layer of vertices. This change improves the functionality of the codebase by providing a more focused and efficient sorting mechanism.
* refactor(graph): Update Graph class to use get_vertex method for building vertices
The _build_vertices method in the Graph class of base.py has been updated to use the get_vertex method instead of creating a new vertex instance. This change improves the efficiency and maintainability of the codebase.
* refactor(graph): Update Graph class to use astep method for asynchronous execution
The `Graph` class in `base.py` has been updated to use the `astep` method for asynchronous execution of vertices. This change improves the efficiency and maintainability of the codebase by leveraging asyncio and allowing for concurrent execution of vertices.
* feat(base.py): implement methods to add components and component edges in the Graph class
* refactor(graph): Import nest_asyncio for asynchronous execution in Graph class
* refactor(base.py): Update Vertex class to handle parameter dictionaries in build_params
The `build_params` method in the `Vertex` class of `base.py` has been updated to handle parameter dictionaries correctly. If the `param_dict` is empty or has more than one key, the method now sets the parameter value to the vertex that is the source of the edge. Otherwise, it sets the parameter value to a dictionary with keys corresponding to the keys in the `param_dict` and values as the vertex that is the source of the edge. This change improves the functionality and maintainability of the codebase.
* refactor(base.py): Add methods to set input values and add component instances in Vertex class
The `Vertex` class in `base.py` has been refactored to include two new methods: `set_input_value` and `add_component_instance`. The `set_input_value` method allows setting input values for a vertex by name, while the `add_component_instance` method adds a component instance to the vertex. These changes enhance the functionality and maintainability of the codebase.
* refactor(message.py): Update _timestamp_to_str to handle datetime or str input
The `_timestamp_to_str` function in `message.py` has been updated to handle both `datetime` and `str` input. If the input is a `datetime` object, it will be formatted as a string using the "%Y-%m-%d %H:%M:%S" format. If the input is already a string, it will be returned as is. This change improves the flexibility and usability of the function.
* refactor(test_base.py): Add unit tests for Graph class
Unit tests have been added to the `test_base.py` file to test the functionality of the `Graph` class. These tests ensure that the graph is prepared correctly, components are added and connected properly, and the graph executes as expected. This change improves the reliability and maintainability of the codebase.
* refactor(initialize/loading.py): Refactor get_instance_results function
The `get_instance_results` function in `initialize/loading.py` has been refactored to simplify the logic for building custom components and components. The previous implementation had separate checks for `CustomComponent` and `Component` types, but the refactored version combines these checks into a single condition based on the `base_type` parameter. This change improves the readability and maintainability of the codebase.
* refactor(component.py): Add set_input_value method to Component class
The `set_input_value` method has been added to the `Component` class in `component.py`. This method allows setting the value of an input by name, and also updates the `load_from_db` attribute if applicable. This change enhances the functionality and maintainability of the codebase.
* refactor(component.py): Set input value in _set_parameter_or_attribute method
The `_set_parameter_or_attribute` method in the `Component` class now sets the input value using the `set_input_value` method. This change improves the clarity and consistency of the codebase.
* refactor(inputs.py): Improve error message for invalid value type
The `SecretStrInput` class in `inputs.py` has been updated to improve the error message when an invalid value type is encountered. Instead of a generic error message, the new message includes the specific value type and the name of the input. This change enhances the clarity and usability of the codebase.
* feat: Add unit test for memory chatbot functionality
* refactor(base.py): Update __repr__ method in ContractEdge class
The `__repr__` method in the `ContractEdge` class of `base.py` has been updated to include the source handle and target handle information when available. This change improves the readability and clarity of the representation of the edge in the codebase.
* refactor(component.py): Update set method to return self
The `set` method in the `Component` class of `component.py` has been updated to return `self` after processing the connection or parameter. This change improves the chaining capability of the method and enhances the readability and consistency of the codebase.
* refactor(starter_projects): Add unit test for vector store RAG
A unit test has been added to the `test_vector_store_rag.py` file in the `starter_projects` directory. This test ensures that the vector store RAG graph is set up correctly and produces the expected results. This change improves the reliability and maintainability of the codebase.
* refactor: remove unused prepare method in Graph class
* refactor: update Output class to use list[str] for types field
* refactor: add name validation to BaseInputMixin
* refactor: update ContractEdge __repr__ method for improved readability and consistency
* refactor: update BaseInputMixin to ensure name field is required with appropriate description
* refactor: remove name validation from BaseInputMixin
* refactor: update input tests to include 'name' field in all input types for better validation and clarity
* refactor: enhance Component class with methods to validate callable outputs and inheritance checks for better robustness
* refactor: disable load_from_db for inputs in Component class to improve input handling logic and prevent unwanted database loading
* refactor: add test for setting invalid output in test_component.py
---------
Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Christophe Bornet