- Refactored code to replace the deprecated is_valid property with the is_check_valid method.
- Added validation for the entrypoint function name and return type.
- Modified the error messages to provide more specific details.
This commit implements the necessary changes to refactor the CustomComponent class in the endpoints.py file. The is_valid property has been replaced with the is_check_valid method to check the validity of the custom component. Additionally, validation has been added to ensure the presence of a valid entrypoint function and a valid return type. If any of the validation checks fail, appropriate error messages are raised to provide detailed traceback information.
The code in the CustomComponent class has been refactored to improve readability and maintainability. The `_handle_function` method now handles function arguments correctly. Additionally, the `is_valid_class_template` method has been renamed to `_class_template_validation`, and it now raises an HTTPException with a detailed error message when the main class or the build function contains invalid information.
In the `build_langchain_template_custom_component` function, base classes are now retrieved from the `return_type` and added to the `template.base_classes` list. A try-except block is used to handle possible KeyError or AttributeError exceptions, and an HTTPException is raised with the corresponding error message and traceback if an error occurs.
These changes ensure more accurate validation and handle potential errors more gracefully.
📝 chore(base.py): update comments and remove unused imports
The code in the `Vertex` class has been refactored to improve readability and handle optional parameters more effectively. The code now checks if a parameter is of type "code", "str", or "prompt" and if it is not already set in the `params` dictionary, it sets it to the corresponding value from the `value` dictionary. Additionally, if a parameter is not required and not set in the `params` dictionary, it checks if a default value is provided and sets it to the default value if available, otherwise it removes the parameter from the `params` dictionary. This change improves the handling of optional parameters and makes the code more maintainable.
The `endpoints` module in the API v1 folder has been modified to remove an unnecessary import and some code duplication. These changes improve the code organization and maintainability.
This commit also removes a commented-out test endpoint that was intended for testing purposes but was never used. The endpoint has been removed from the codebase to avoid confusion and clutter.
The changes include removing an unused import statement from the module and removing an unused endpoint. The unused endpoint was a commented-out code block that contained example error responses. Since these examples were not needed for testing or documentation purposes, the endpoint has been safely removed.
- Refactored the tools module to improve code readability and maintainability.
- Fixed import statements in the constants module to correctly import modules.
- Updated documentation and added comments for better understanding of the code.
- Extracted the logic for removing unwanted base classes to a separate method called `process_base_classes`.
- Created a list `CLASSES_TO_REMOVE` which contains the names of the base classes to be removed.
- Updated `to_dict` method to call `process_base_classes` before generating the dict representation of the frontend node.
- Added a new method `process_base_classes` which removes the unwanted base classes from the list of base classes.
- The method `process_base_classes` updates the `base_classes` list, removing any base classes present in `CLASSES_TO_REMOVE`.
This commit enhances the code by separating the concerns of base class removal logic and dict representation generation.
- Modifies the `CustomComponent` class to handle errors using `HTTPException` from FastAPI
- Removes the unused `HTTPExceptionWithTraceback` class
- Updates the error response format with `err.msg` and `traceback.format_exc()`
This commit adds a new class `HTTPExceptionWithTraceback` that extends `HTTPException` from the `fastapi` module. This new class includes a `traceback` attribute. Additionally, in the `extract_class_info` method of the `CustomComponent` class, a try-except block is added to catch any syntax errors raised by parsing the provided code. If a syntax error is encountered, an HTTPException is raised with the error message and traceback.
This commit adds support for dynamic fields in the template field creator class. The "dynamic" attribute has been added to the class definition and its default value is set to False.
This commit adds a dynamic field to the code field in the types module. The dynamic field is set to True, indicating that the field allows updates.
refactor: Remove dynamic field from FrontendNode class
In the FrontendNode class of the base module, the dynamic field has been removed. This change aligns with the removal of the dynamic field in the types module.
refactor: Remove dynamic field from CustomComponentNode class
The dynamic field has been removed from the CustomComponentNode class in the tools module. This aligns with the removal of the dynamic field in the FrontendNode class.
🐛 fix(loading.py): remove unnecessary None default value for file_filter parameter
The unused import statement from langchain.prompts.base has been removed to improve code cleanliness. The None default value for the file_filter parameter in the instantiate_documentloader function has been removed as it is unnecessary and can be safely assumed that the parameter will always be provided.
💡 chore(main.py): clean up code by removing an unused endpoint and a template_node variable that is no longer needed
The /dynamic_node endpoint and the template_node variable are no longer used in the application and can be safely removed. This improves code cleanliness and reduces unnecessary complexity.
🐛 fix(base.py): fix __eq__ method in Edge class to correctly compare objects
The add_edge method in the Vertex class has been modified to prevent adding duplicate edges. Now, before adding an edge, it checks if the edge already exists in the edges list to avoid duplicates.
The __eq__ method in the Edge class has been fixed to correctly compare objects. It now compares the string representation of the objects to determine equality, ensuring that the comparison is accurate.
- The `build` method of `MyPythonClass` is modified to accept an `openai_api_key` parameter instead of using a hardcoded value.
- This change allows for dynamic usage of different API keys when constructing an instance of `ConversationChain`.
- The `my_conversation` method now takes `openai_api_key` as an argument and uses it to initialize the `llm` instance of `OpenAI`.
- The `build` method simply delegates the `openai_api_key` argument to the `my_conversation` method and returns the resulting `ConversationChain` instance.
- Updatethe `get_function_custom` function to use the `validate.extract_class_name` function to extract class name from the `code` parameter.
- Modify `instantiate_tool` function to update the `class_object` with the return value of `get_function_custom` and call the `build` method on the instantiated object with the remaining params.
- Add a new function `extract_class_name` in the `validate` module to extract class name from the `code` parameter.
The code now checks if the variable already exists in the template and if so, sets the new field value with the old value. This ensures that the existing value is preserved when adding new variables to the template.
The multiline option is added to the input_variables field in the add_new_variables_to_template function. This allows the field to accept multiline input, which can be useful in certain scenarios where multiple lines of text need to be entered.
- Added a dynamic flag to CustomComponentNode class in tools.py for enabling dynamic behavior.
- This flag allows for flexibility in executing the Python class.
- The flag defaults to True.
Previously, the `build` method in the `MyPythonClass` class had an argument named `name`, which could be confusing. This commit changes the argument name to `my_custom_input` to improve readability and clarity.
This commit removes the file `extract_info_from_class.py` which contained unnecessary code.
[v1/endpoints.py] Fix error handling in custom_component endpoint
This commit fixes the error handling in the `custom_component` endpoint in `endpoints.py`. If the class template extracted from the code is not valid, an error message is printed.
[importing/utils.py] Comment out unused code
This commit comments out unused code in `get_function_custom` function in `utils.py` file.
[initialize/loading.py] Comment out unused code
This commit comments out unused code in the `instantiate_tool` function in `loading.py` file.
[interface/tools/custom.py] Refactor code and add properties
This commit refactors the code in `CustomComponent` class in `custom.py` file. It adds properties for `data`, `is_valid`, and `args_and_return_type`.
[interface/types.py] Add base classes to custom component template
This commit adds base classes to the custom component template in the `build_langchain_template_custom_component` function in `types.py` file.
[utils/constants.py] Remove unnecessary import
This commit removes an unnecessary import in `DEFAULT_CUSTOM_COMPONENT_CODE` constant in `constants.py` file.
The input_types in the add_new_variables_to_template function were incorrect. They were set to ["BaseLoader", "BaseOutputParser"] instead of ["Document", "BaseOutputParser"]. This fix ensures that the correct input types are used for the template field.
🔀 chore(main.py): add trailing commas to dictionary entries for improved readability
The multiline string in the value of the `my_user_python_function` key was not properly formatted. The double quotes were changed to triple quotes to match the Python docstring convention. Trailing commas were added to the dictionary entries for improved readability and maintainability.
The code now checks if the variable is already in the list before appending it to the custom_fields. Additionally, when removing old variables from the template, the code now also removes the variable from the custom_fields associated with the given name. This ensures that the custom_fields and template stay in sync with the input_variables.
The custom_fields attribute in the FrontendNode class now has a default value of defaultdict(list) instead of an empty list. This change ensures that custom_fields is always a defaultdict, which prevents potential errors when accessing or modifying the custom_fields attribute.
The 'name' field is added to the ValidatePromptRequest model to enhance data validation. This field will allow for more specific identification and validation of prompt names in the API.
✨ feat(validate.py): refactor post_validate_prompt function to improve code readability and maintainability
The parameter 'prompt' in the 'post_validate_prompt' function has been renamed to 'prompt_request' to improve clarity and avoid confusion with the 'prompt' variable used within the function. The function has also been refactored to improve code readability and maintainability by extracting logic into separate helper functions. The helper functions 'get_old_custom_fields', 'add_new_variables_to_template', 'remove_old_variables_from_template', and 'update_input_variables_field' have been added to handle specific tasks within the 'post_validate_prompt' function. This refactoring improves the overall structure and organization of the code.
🔖 chore(config.yaml): update documentation links for vectorstores and output parsers
Added documentation links for the following new modules:
- MongoDBChatMessageHistory
- ChatMessagePromptTemplate
- HumanMessagePromptTemplate
- SystemMessagePromptTemplate
- ChatPromptTemplate
Updated documentation links for the following existing modules:
- MongoDBAtlasVectorSearch
Also, added documentation links for the following output parsers:
- StructuredOutputParser
- ResponseSchema
The documentation links were added or updated to provide easy access to relevant documentation for each module and output parser.
The VERTEX_TYPE_MAP dictionary in constants.py has been refactored to use explicit import paths for each vertex type. This improves the readability and maintainability of the code by making it clear where each vertex type is coming from.
🔀 refactor(base.py): move FieldFormatters class to the top of the file for better organization
The import statement in the base.py file has been updated to import the field_formatters module instead of importing specific modules. This change improves maintainability and readability by reducing the number of import statements and consolidating them into a single import. Additionally, the FieldFormatters class has been moved to the top of the file for better organization and readability.
🐛 fix(base.py): remove "object" from CLASSES_TO_REMOVE list to prevent unnecessary removal
In validate.py, the input_types in the template_field for the "prompt" variable is updated to ["Document", "BaseOutputParser"] to accurately reflect the expected input types.
In base.py, the "object" class is removed from the CLASSES_TO_REMOVE list to prevent unnecessary removal of the "object" class from the FrontendNode class inheritance.
🐛 fix(GenericNode/index.tsx): remove unused imports and unused variable to improve code cleanliness
The extra blank line in the `types.py` file has been removed to improve the readability of the code. In the `GenericNode/index.tsx` file, unused imports and an unused variable have been removed to clean up the code and improve maintainability.
🔧 fix(documentloaders.py): add_extra_base_classes method to set base_classes and output_types for DocumentLoaderFrontNode
🔧 fix(textsplitters.py): add_extra_base_classes method to set base_classes and output_types for TextSplittersFrontendNode
🔧 fix(vectorstores.py): change field_type to "Document" for documents field in VectorStoreFrontendNode
🔧 fix(index.ts): add output_types field to APIClassType interface
The changes were made to add support for specifying output types in the FrontendNode class and its subclasses. This allows for more flexibility in defining the behavior and capabilities of the frontend nodes in the application.
📝 docs(chat.py): explain the need for building the root node before the rest of the graph
The root node in the graph was not being built before the rest of the graph, which caused issues when certain nodes required parameters that were not connected to them. By adding the missing build step for the root node, we ensure that all necessary connections and parameters are properly set up before building the rest of the graph. This improves the overall functionality and reliability of the chat module.
Added the documentation link for the PyPDFDirectoryLoader in the config.yaml file. This allows users to access the documentation on how to use the PyPDFDirectoryLoader for loading PDF documents.
The logger.debug() statements are added to provide more visibility into the process of creating the database and tables. This can be helpful for debugging and troubleshooting purposes.
The change is made to improve the logging of exceptions. Using logger.exception instead of logger.error allows the logger to log the full traceback of the exception, providing more detailed information for debugging purposes.
🔧 refactor(documentloaders.py): remove redundant code for adding fields in DocumentLoaderFrontNode class
The code in the DocumentLoaderFrontNode class has been refactored to extract the logic for building directory loader fields into a separate function called build_directory_loader_fields(). This improves code readability and maintainability by separating concerns and reducing duplication. The redundant code for adding fields in the DocumentLoaderFrontNode class has also been removed.
The default value of the "Persist" extra field in the VectorStoreFrontendNode class has been changed from True to False. This change was made to align the default value with the desired behavior of the application.
The output_key field is now only added to the template if the template type is not VectorStoreRetrieverMemory. This ensures that the output_key field is not added unnecessarily for templates of this type.
The `logger.exception(exc)` line has been added to log the exception that occurred. This will help with error handling and debugging by providing more information about the exception that caused the error.
The code now checks if the "retriever" key exists in the params dictionary and if the value has an "as_retriever" method. If it does, the value is replaced with the result of calling the "as_retriever" method. This change ensures that the "retriever" parameter is always an instance of the retriever object, preventing potential attribute errors later in the code.
The logic for updating memory keys in the `run.py` file has been refactored to use a loop and a try-except block. Instead of individually assigning values to `input_key`, `output_key`, and `memory_key`, the keys and attributes are now stored in lists. The loop iterates over the lists and attempts to set the attribute values using `setattr()`. If an attribute does not exist, a `ValueError` is caught and a debug log message is printed. This refactoring improves code readability and maintainability.
The code now checks if the langchain_object.prompt has a template attribute before adding it to the input_keys_response. This prevents potential errors if the template attribute is not present in the prompt object.
The `process_base_classes` method is added to the `FrontendNode` class. This method removes unwanted base classes specified in the `CLASSES_TO_REMOVE` list from the `base_classes` list. This ensures that only the desired base classes are included in the `base_classes` list. The method is then called in the `to_dict` method to ensure that the processed `base_classes` list is used when converting the `FrontendNode` instance to a dictionary.
