🐛 fix(directory_reader.py): return False if code is not valid Python to prevent false positives
🐛 fix(directory_reader.py): fix method name from is_type_hint_used_but_not_imported to _is_type_hint_used_in_args for consistency
🐛 fix(directory_reader.py): fix method name from is_type_hint_imported to _is_type_hint_imported for consistency
🐛 fix(directory_reader.py): fix return value of _is_type_hint_used_in_args method to return False if type hint is used but not imported
✨ feat(OpenAIConversationalAgent.py): add support for return_intermediate_steps parameter in AgentExecutor constructor to enable returning intermediate steps during conversation
This commit adds a new file `ConversationalAgent.py` to the `src/backend/langflow/components/agents` directory. The `ConversationalAgent` class is a custom component that represents a conversational agent capable of using OpenAI's function calling API.
The `ConversationalAgent` class has the following features:
- It inherits from the `CustomComponent` class.
- It has a `display_name` attribute set to "OpenaAI Conversational Agent".
- It has a `description` attribute set to "Conversational Agent that can use OpenAI's function calling API".
- It implements the `build_config` method to define the configuration options for the agent.
- It implements the `build` method to create an instance of the `AgentExecutor` class, which represents the agent's execution environment.
- The `build` method takes several parameters, including `model_name`, `tools`, `memory`, `system_message`, and `max_token_limit`.
- It uses the `ChatOpenAI` class from the `langchain.chat_models` module to create an instance of the OpenAI language model.
- It uses the `ConversationTokenBufferMemory` class from the `langchain.memory.token_buffer` module to handle conversation history and token buffering.
- It uses the `OpenAIFunctionsAgent` class from the `langchain.agents.openai_functions_agent.base` module to create an instance of the OpenAI functions agent.
- It returns an instance of the `AgentExecutor` class with the agent, tools, memory, verbose, and return_intermediate_steps parameters set.
📝 feat(__init__.py): add empty __init__.py file to the agents directory
This commit adds an empty `__init__.py` file to the `src/backend/langflow/components/agents` directory. The `__init__.py` file is necessary to make the `agents` directory a Python package.
📝 WHY: The addition of BaseMemory to LANGCHAIN_BASE_TYPES allows for the customization of the memory component in the Langchain interface. This enables users to implement their own memory functionality according to their specific needs.
✨ feat(PaginatorComponent): add support for custom icons using IconComponent for better customization options
🔧 fix(UserManagementModal): remove unused imports and fix import order for better organization
✨ feat(UserManagementModal): add password confirmation validation and reset form on modal open for better user experience
🔧 fix(UserManagementModal): fix modal size to be full height for better visibility and usability
✨ feat(UserManagementModal): add form fields for username and password with validation for better user input handling
🔧 fix(UserManagementModal): fix form field labels and error messages for better clarity and user guidance
✨ feat(UserManagementModal): add form submission and confirmation handling for better user interaction and data management
🔧 fix(UserManagementModal): fix cancel button styling for better consistency and user experience
🔧 fix(baseModal): add missing size options to the size prop to support additional modal sizes
✨ feat(baseModal): add support for "small-h-full" and "medium-h-full" sizes to allow modals with smaller height and full width
🔧 fix(AdminPage): import missing IconComponent and ShadTooltip components
✨ feat(AdminPage): add functionality to handle editing and adding new users
🔧 fix(applies.css): add missing semicolon to .field-invalid and .label-invalid classes
🔧 fix(styleUtils.ts): import missing Pencil, ChevronsRight, and ChevronsLeft icons
🐛 fix(test_custom_component.py): update assertion to expect return_type as a list instead of a string
🐛 fix(test_vectorstore_template.py): update assertion to check if all vectorstores in settings are present in the response
🔧 chore(Metaphor.py): update search method to use the provided parameters for use_autoprompt and search_num_results
🔧 chore(Metaphor.py): update find_similar method to use the provided parameter for similar_num_results
🐛 fix(Metaphor.py): ignore type error for returning a list with mixed types
🐛 fix(Vectara.py): add condition to check if documents and embedding are not None before creating Vectara instance
🐛 fix(CustomComponent.py): change return type of get_function_entrypoint_return_type to List[str] to match the actual return value
The MetaphorToolkit component is added to the langflow toolkit. It provides functionality for searching metaphors using the Metaphor API. The component includes three tools: search, get_contents, and find_similar. The search tool allows users to search for metaphors using a query. The get_contents tool retrieves the contents of a webpage based on the ids returned from the search tool. The find_similar tool finds search results similar to a given URL returned from the search tool.
The MetaphorToolkit component is still in beta and requires a Metaphor API key to function. The API key is stored securely and can be configured in the field_config of the component. For more information, refer to the documentation: [Metaphor Toolkit Documentation](https://python.langchain.com/docs/integrations/tools/metaphor_search)
✨ feat(Vectara.py): add VectaraComponent to implement Vector Store using Vectara
🔧 chore(vectorstores): add empty __init__.py file to the vectorstores directory
🐛 fix(types.py): handle multiple return types in add_base_classes function and raise HTTPException with appropriate error message if return type is invalid
🔨 refactor(PaginatorComponent): remove unnecessary whitespace in paginate prop
📝 docs(ConfirmationModal): add missing JSDoc comments and improve code readability
📝 docs(UserManagementModal): add missing JSDoc comments and improve code readability
🔨 refactor(baseModal): improve code readability by adding a div wrapper for headerChild
✨ feat(AdminPage/index.tsx): add Pencil icon from lucide-react library to the import statement to use it in the component
✨ feat(AdminPage/index.tsx): add ConfirmationModal and UserManagementModal components to import statements to use them in the component
🐛 fix(AdminPage/index.tsx): remove unused handleSaveClick function
✨ feat(AdminPage/index.tsx): add modalEditOpen and modalDeleteOpen states to handle the opening and closing of the modals
✨ feat(AdminPage/index.tsx): add handleEditUser function to handle the edit user functionality
🐛 fix(AdminPage/index.tsx): remove unused handleSaveClick function
✨ feat(AdminPage/index.tsx): add ConfirmationModal component to handle the delete user functionality
✨ feat(AdminPage/index.tsx): add UserManagementModal component to handle the edit user functionality
✨ feat(components/index.ts): add ConfirmationModalType and UserManagementType types to handle the props of ConfirmationModal and UserManagementModal components
🐛 fix(components/index.ts): add missing newline at the end of the file
✨ feat(utils/styleUtils.ts): add UserMinus2 and UserPlus2 icons from lucide-react library to the import statement
This PR is a code refactoring initiative aiming to improve the
readability and maintainability of our codebase. It specifically targets
generic or non-descriptive variable names, renaming them to more
meaningful names that better express their purpose within the code.
As noted in the
[documentation](https://python.langchain.com/docs/integrations/document_loaders/slack)
for this plugin zip_path is the first named parameter not file_path and
workspace_url is the second with zip_path being required and
workspace_url being optional.
Fixes#695
Signed-off-by: Melvin Hillsman <mhillsma@redhat.com>
