- PostgresChatMessageHistory added to allow loading memory from external
sources
- MultiQueryRetriever added which builds better queries to
Retrievers/VectorStores
- XSS protection in the chat that uses markdown
- FrontendNode refactor start
- Fix Serializable nodes that were exposing wrong base classes on
Components
- ConversationEntityMemory as the first memory with EntityStore (entity
stores coming very soon)
The strenum package has been updated from version 0.4.12 to version 0.4.15. This update may include bug fixes, performance improvements, or new features.
The base class "Serializable" has been renamed to "BaseLLM" to provide a more descriptive and consistent name for the class. This change improves clarity and maintainability of the code.
🔧 fix(frontend): update class names and colors in index.css to match the new design
🔧 fix(frontend): update tailwind.config.js to use the new color variable name 'status-blue' instead of 'medium-dark-blue'
🐛 fix(codeAreaComponent): fix formatting and add missing semicolons to improve code readability and maintainability
🐛 fix(dropdownComponent): fix formatting and add missing semicolons to improve code readability and maintainability
🐛 fix(floatComponent): fix formatting and add missing semicolons to improve code readability and maintainability
🐛 fix(inputFileComponent): fix formatting and add missing semicolons to improve code readability and maintainability
🐛 fix(inputListComponent): fix formatting and add missing semicolons to improve code readability and maintainability
🐛 fix(intComponent): fix formatting and add missing semicolons to improve code readability and maintainability
🐛 fix(promptComponent): fix formatting and add missing semicolons to improve code readability and maintainability
🐛 fix(textAreaComponent): fix formatting and add missing semicolons to improve code readability and maintainability
🐛 fix(ui/accordion.tsx): fix formatting and add missing semicolons to improve code readability and maintainability
The changes were made to fix formatting issues and add missing semicolons in the code. This improves code readability and maintainability, making it easier for developers to understand and work with the code.
🐛 fix(constants.tsx): fix formatting and indentation issues in the buildTweakObject function
🐛 fix(popUpContext.tsx): remove unnecessary empty line
🐛 fix(tabsContext.tsx): remove unnecessary empty line
🐛 fix(ApiModal/index.tsx): fix formatting and indentation issues
🐛 fix(codeAreaModal/index.tsx): fix formatting and indentation issues
🐛 fix(types/components/index.ts): remove unnecessary empty line
The changes in constants.tsx fix formatting and indentation issues in the buildTweakObject function to improve code readability. The changes in popUpContext.tsx, tabsContext.tsx, ApiModal/index.tsx, codeAreaModal/index.tsx, and types/components/index.ts fix formatting and indentation issues to ensure consistent code style.
🐛 fix(base.py): add optional 'name' parameter to the format method in FieldFormatter
In loading.py, the error message when failing to build a connection to the database is now formatted in a more readable way. This improves the clarity of the error message and makes it easier to identify the cause of the issue.
In base.py, the format method in FieldFormatter now accepts an optional 'name' parameter. This allows for more flexibility when formatting the field and provides the ability to include the field name in the formatting process if needed.
The code now checks if the "handle_keys" key is present in the params dictionary. If it is not present, it creates an empty list and adds the input_variable to it. This ensures that the "handle_keys" list is always present and the input_variable is correctly added to it.
The build_input_keys_response function now includes support for handle_keys in the response. This allows the function to populate the handle_keys field in the response with the values from the artifacts dictionary, if available.
The color code for the "retrievers" category in the nodeColors object has been updated from "#F5B85A" to "#e6b25a". This change was made to ensure consistency and improve the visual representation of the "retrievers" category.
The ConversationEntityMemory integration is now documented in the config.yaml file. This provides a link to the documentation for using the ConversationEntityMemory module with SQLite as the underlying storage. This change improves the clarity and accessibility of the documentation for this integration.
🐛 fix(constants.tsx): refactor getCurlCode and getPythonCode to use buildTweakObject function for generating tweak object
🐛 fix(ApiModal): update logic for opening accordions based on tweak.current length and closeEdit value
🔒 chore(poetry.lock): update joblib version to 1.3.1
The versions of the anthropic, google-api-python-client, and joblib packages have been updated to their latest versions. This ensures that the application is using the most recent bug fixes, improvements, and features provided by these packages.
- Simplify class names in the SingleAlert component and update color variables.
- Update class names and color variables in the Dialog component.
- Update color variables in the constants file.
- Update color variables and class names in the index.css file.
- Update class names and color variables in the PageComponent file.
- Add a color variable for shared blur styles.
- Update Tailwind CSS configuration to include new color variables.
Note: These changes improve code readability and maintain color consistency throughout the application.
The code now catches an additional exception when the object does not have a 'conn' field. This improves the error handling by providing a more specific error message when building a connection to the database fails.
The 'from_method_nodes' dictionary in the 'MemoryCreator' class in 'base.py' has been updated to include the 'SQLiteEntityStore' class and its '__init__' method. This change allows the 'SQLiteEntityStore' class to be used as a memory node in the LangFlow application.
✨ feat(memories.py): add show attribute to entity_store field in MemoryFrontendNode class
The condition to add extra fields in the MemoryFrontendNode class has been fixed to correctly check if any of the base classes are in a list of base message classes. Additionally, the show attribute has been added to the entity_store field in the MemoryFrontendNode class to control its visibility.
The "kwargs" and "args" parameters are now excluded from the generated template dictionary. This ensures that only the relevant parameters are included in the template, improving the accuracy and usefulness of the generated template.
When processing the data graph, if the langchain_object is of an unknown type, a ValueError is now raised. This provides better error handling and helps identify any unexpected langchain_object types that may be encountered during processing.
✨ feat(base.py): add support for creating MemoryFrontendNode from a specific method in ZepChatMessageHistory class
The `MemoryCreator` class now supports creating `MemoryFrontendNode` from a specific method in the `ZepChatMessageHistory` class. This is achieved by adding the `from_method_nodes` dictionary with the method name as the key and the class name as the value. The `build_template_from_method` function is used to create the `MemoryFrontendNode` from the specified method. This enhancement allows for more flexibility in creating `MemoryFrontendNode` instances.
✨ feat(base.py): add support for ZepRetriever in from_method_nodes dictionary
The build_template_from_method call for the MultiQueryRetriever in the get_signature method was using the incorrect method name "from_llm". It has been fixed to use the correct method name "from_method_nodes". Additionally, support for the ZepRetriever has been added to the from_method_nodes dictionary to allow for its usage in the RetrieverCreator class.
The 'url' field in the MemoryFrontendNode class is now set to be shown in the frontend. This change allows the 'url' field to be visible and accessible to users in the frontend interface.
The "self" parameter is now excluded from the template building process. This change improves the accuracy of the generated template by removing unnecessary information.
The unused integrations in the memories and retrievers sections have been commented out to improve code readability and remove unnecessary clutter. These integrations are not currently being used in the application and can be safely ignored.
- Update CSS classes in codeAreaComponent, floatComponent, intComponent, and dialog components to improve styling and maintain consistency.
- Replace specific color values with Tailwind CSS utility classes.
- Refactor input styles and focus styles for better user experience.
- Remove unused CSS classes from index.css.
The instantiate_memory function now includes error handling for a specific AttributeError that occurs when the object does not have a 'cursor' attribute. If this error occurs, an AttributeError is raised with a specific error message indicating a failure to build a connection to the database. This change improves the error handling and provides more informative error messages for debugging purposes.
🐛 fix(base.py): call the method to remove unwanted base classes before converting the frontend node to a dict
The `process_base_classes` method is added to the `FrontendNode` class to remove unwanted base classes from the list of base classes. This method iterates over the base classes and filters out any classes that are present in the `CLASSES_TO_REMOVE` list. The method is then called before converting the frontend node to a dictionary representation in the `to_dict` method to ensure that the unwanted base classes are not included in the final output.
The configurations for the ChatPromptTemplate, SystemMessagePromptTemplate, and HumanMessagePromptTemplate wrappers have been commented out as they are currently not being used. This helps to improve code readability and reduces unnecessary clutter in the configuration file.
The config.yaml file now includes an output_parsers section with the StructuredOutputParser and ResponseSchema as the specified parsers. This change was made to enhance the functionality of the backend by enabling the parsing of structured output and response schemas.
🔧 fix(settings.py): add "output_parsers" attribute to the Settings class
The "input_types" list in the template_field of the post_validate_prompt function in validate.py was missing the "BaseOutputParser" type. This fix adds it to the list to ensure proper validation.
The Settings class in settings.py was missing the "output_parsers" attribute. This fix adds the attribute to the class to ensure that the list of output parsers can be properly configured and accessed.
The import statements for vertex types in constants.py have been refactored to import all types from langflow.graph.vertex.types. This improves code readability and maintainability by reducing the number of import statements and consolidating them into a single import.
The OutputParserVertex class is added to the types.py file. This class extends the Vertex class and is used to represent a vertex in the graph that performs output parsing. It takes a data parameter of type Dict in its constructor and calls the super constructor with the data and a base_type of "output_parsers". This change is made to support the implementation of output parsing functionality in the graph.
🔧 fix(loading.py): add import statement for output_parser_creator
🔧 fix(listing.py): add import statement for output_parser_creator
🔧 fix(types.py): add import statement for output_parser_creator
The import statements for the `output_parsers` module were missing in the respective files. This fix adds the necessary import statements to ensure that the `output_parser_creator` is accessible and can be used in the code.
🚀 feat(output_parsers): add OutputParserCreator class to handle creation and loading of output parsers
🚀 feat(output_parsers): add OutputParserFrontendNode class to handle formatting of output parser fields
The commit adds the following changes:
- A new file `__init__.py` is added to the `output_parsers` module.
- A new file `base.py` is added to the `output_parsers` module.
- A new file `output_parsers.py` is added to the `frontend_node` module.
The `__init__.py` file initializes the `OutputParserCreator` class, which is responsible for creating and loading output parsers. It also defines a method to get the signature of an output parser.
The `base.py` file contains the base class `OutputParserCreator` which is a subclass of `LangChainTypeCreator`. It defines the type name as "output_parsers" and provides methods to get the frontend node class and the type to loader dictionary. It also defines a method to convert the output parsers to a list.
The `output_parsers.py` file contains the `OutputParserFrontendNode` class, which is a subclass of `FrontendNode`. It provides a method to format the field of an output parser.
These changes are done to add support for output parsers in the application. The `OutputParserCreator` class allows for dynamic creation and loading of output parsers, while the `OutputParserFrontendNode` class provides a way to format the fields of an output parser.
🚀 feat(utils.ts): add support for output_parsers node name and icon
The `nodeColors` object now includes a color for the `output_parsers` node type, allowing it to be visually distinguished. Similarly, the `nodeNames` object now includes a name for the `output_parsers` node type. Additionally, the `nodeIconsLucide` object now includes an icon for the `output_parsers` node type. These changes improve the consistency and completeness of the node types in the application.
