🐛 fix(process.py): handle missing inputs in process_graph_cached function
The function `build_langchain_object_with_caching` has been renamed to `build_sorted_vertices_with_caching` to provide a more descriptive name that accurately reflects its purpose. Additionally, the `process_graph_cached` function now handles cases where the `inputs` parameter is missing or empty by populating it with values from the `artifacts` dictionary. This ensures that all required inputs are properly set before running the graph.
Both caching mechanisms improve the performance of building the langchain object and sorted vertices, reducing redundant computations and improving overall efficiency.
The `build_langchain_object_with_caching` function now uses the `memoize_dict` decorator to cache the result of building the langchain object from the data graph. This improves performance by avoiding redundant computations when the same data graph is used multiple times.
The `stream_build` function now logs the exception that occurred during the flow building process using the `logger.exception` method. This improves error handling and provides more detailed information about the error in the logs.
The Edge class constructor now takes an additional parameter 'edge' which is a dictionary containing additional information about the edge. This information is used to set the source_handle, target_handle, and target_param attributes of the Edge class. This change allows for more flexibility and extensibility when working with edges in the graph.
🔧 refactor(base.py): add edge parameter to Edge class constructor to pass additional edge information
The unused imports have been removed to improve code cleanliness. The code in the _build_params method has been simplified by removing unnecessary conditions and loops. Default values are now added for string and prompt type parameters to ensure that they have a value even if not explicitly set.
🔧 fix(base.py): remove unused imports and simplify code in _build_params method
🐛 fix(chatComponent): import lodash library to use _.cloneDeep function
✨ feat(chatComponent): add TabsContext to access tabsState and update isBuilt state based on tabsState changes
🐛 fix(interface/initialize/loading.py): handle BaseOutputParser instances in instantiate_prompt
The `optional_inputs` list in the `Vertex` class is now extended with the `input_types` from the `template_dicts` dictionary. This ensures that the `optional_inputs` list contains all the input types that are not required. In the `instantiate_prompt` function, if the `variable` is an instance of `BaseOutputParser` and has a `get_format_instructions` method, the `format_kwargs` dictionary is updated with the result of calling `get_format_instructions()`. This allows handling `BaseOutputParser` instances correctly in the `instantiate_prompt` function.
This pull request introduces significant style changes to the website,
focusing on CSS color modifications and the implementation of a dark
mode feature. These updates enhance the overall visual appeal and
improve user experience in different lighting environments. Below is a
detailed overview of the changes made.
Updated Color Palette: The existing color scheme has been revamped to
create a more visually appealing and cohesive design. This involved
modifying the colors used throughout the website, including background
colors, text colors, and accent colors.
Dark Mode Implementation: A new feature, dark mode, has been added to
provide users with an alternative interface that is easier on the eyes
in low-light environments. The dark mode utilizes a new set of colors
specifically designed for this mode, ensuring optimal readability and
aesthetic appeal.
CSS Classes and Selectors: New CSS classes and selectors have been
introduced to facilitate the implementation of the color changes and
dark mode feature. These classes are applied to specific elements within
the HTML structure, allowing for precise control over the appearance of
different components.
This commit adds support for Custom Component in the Langflow interface. It introduces a new class `CustomComponent`, which takes in a `code` as a parameter and validates it. The `CustomComponent` class also provides a method to get the function specified in the code.
The commit also makes some modifications in `initialize/loading.py` file to handle the new `CustomComponent` class. It adds a new helper function `get_function_custom` which creates a function using `validate.create_function` and the `build` function name.
- 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.
