Description:
This pull request proposes the addition of a scrollbar to the modal
window containing advanced settings when the number of input fields
exceeds the limit of the screen. This enhancement aims to improve user
experience by providing a convenient way to access all settings, even
when the available screen space is limited.
The number of inputs in the screen is limited by a variable on Utils
that can be easily changed in the future if It's needed.
✨ feat(template): add method to add fields to a template
The VectorStoreFrontendNode now supports adding extra fields to its
template. The add_extra_fields method is called after the node is loaded
and adds the weaviate_url field to the template if the node is of type
Weaviate. The Template class now has a method to add fields to a
template. This method is used by the VectorStoreFrontendNode to add the
weaviate_url field to its template.
✨ feat(template): add method to add fields to a template
The VectorStoreFrontendNode now supports adding extra fields to its template. The add_extra_fields method is called after the node is loaded and adds the weaviate_url field to the template if the node is of type Weaviate. The Template class now has a method to add fields to a template. This method is used by the VectorStoreFrontendNode to add the weaviate_url field to its template.
The changes in this commit are purely cosmetic, as the code has been formatted with prettier to improve its readability and consistency. No functional changes have been made.
The langchain and langchain-serve dependencies have been updated to versions 0.0.184 and 0.0.38 respectively. This update may include bug fixes, performance improvements, or new features.
Description:
This pull request implements several UI feature enhancements to improve
the user experience. The changes include title casing on names and
titles, fixing and changing icons, and adding a cursor pointer on the
chat interface.
Changes Made:
Title case on names and titles: Modified the code to convert names and
titles to title case. This ensures consistent capitalization and
enhances readability throughout the application.
Fixing/Changing icons: Replaced outdated or inconsistent icons with
updated versions to provide a more visually appealing and cohesive user
interface.
Cursor on chat: Added a cursor pointer to the chat interface to indicate
interactivity and enhance user engagement. The cursor appears when
hovering over the chat area, making it clear that the chat is responsive
to user input.
Added new text splitters to the configuration file: RecursiveCharacterTextSplitter, LatexTextSplitter, and PythonCodeTextSplitter. These text splitters will be used to split text into smaller chunks for processing. Also, added new toolkits to the configuration file: OpenAPIToolkit and JsonToolkit. These toolkits will be used to process the text chunks generated by the text splitters.
This pull request resolves a bug related to error handling when
components attempt to call the same modals within different flows. The
issue occurs due to a lack of proper validation and error handling in
the existing codebase. This bugfix aims to provide a comprehensive
solution to mitigate the problem and ensure a smoother user experience.
The code that was causing issues with file upload has been commented out for now. The code was resetting the content of a file, which was causing issues with the file upload.
🎨 style(inputListComponent): change input placeholder text to be more descriptive
The placeholder text for both input components has been changed to "Type something..." to be more descriptive and provide better guidance to the user.
The CohereEmbeddings is added to the list of supported embeddings in the config.yaml file. This allows the application to use the CohereEmbeddings for language processing tasks.
FastAPI and Langchain dependencies have been updated to their latest versions to ensure that the application is using the latest features and security patches. The Llama-cpp-python dependency has also been updated to a more recent version.
✨ feat(pyproject.toml): add cohere dependency to enable new features
🔧 chore(config.yaml): add Cohere to the list of supported LLMS
The langchain dependency was updated to version 0.0.183 to take advantage of the latest features and bug fixes. The cohere dependency was added to enable new features. Cohere is now added to the list of supported LLMS in the config.yaml file.
The try_setting_streaming_options function now correctly sets the streaming attribute of the llm object to True if it is an instance of BaseLanguageModel and has the streaming attribute. This fixes a bug where the streaming attribute was not being set correctly.
✨ feat(pyproject.toml): add ctransformers dependency to support text classification tasks
The langchain dependency has been updated to version 0.0.183 to ensure that the latest features and bug fixes are available. The ctransformers dependency has been added to support text classification tasks.
🐛 fix(utils.py): fix setting of streaming option for llm
🎨 style(llms.py): add model_file and model_type fields to the list of non-advanced fields
The first change adds CTransformers to the list of supported llms in the config.yaml file. The second change fixes a bug in the try_setting_streaming_options function in utils.py where the streaming option was not being set correctly. The third change is a style change that adds the model_file and model_type fields to the list of non-advanced fields in the LLMFrontendNode class in llms.py.
The Makefile now has two new targets, `install_backend` and `install_frontend`, which install the dependencies for the backend and frontend respectively. This makes it easier for developers to set up the project as they can now run `make init` to install the pre-commit hooks and all dependencies.
✅ test(embeddings_template.py): add tests for openai fields formatting
The openai fields formatting is now done in a separate method, which improves the readability and maintainability of the code. Tests were added to ensure that the formatting is done correctly.
The previous condition was checking if the content was None, but it should check if it is empty. This change fixes the error message to be more accurate.
The prompt field was previously set as not required when no value was provided, but this is not the intended behavior. The prompt field should always be required, even if the default prompt is used. This commit fixes the issue by setting the required attribute to True when the value is None.
