✨ feat(formModal): add Input Variables section to Chat Form modal to allow users to input variables
🎨 style(formModal): adjust width of Chat Form modal and Input Variables section to improve UI
🎨 style(formModal): adjust layout of Input Variables section to improve UI
🎨 style(formModal): adjust layout of From Chat switch to improve UI
🐛 fix(formModal): replace Switch component with custom ToggleShadComponent to fix styling issue
✨ feat(validate.py): add support for dynamic template fields in prompt validation
The changes in this commit remove unused variables from the prompt.frontend_node.template. The commit also adds support for dynamic template fields in prompt validation. The new variables are added to the template and the custom_fields list. The old custom_fields list is copied and then updated with the new variables. The variables that are not in the template anymore are removed from the prompt.frontend_node.template.
The setNodeClass function is now passed down to PromptAreaComponent from ParameterComponent. This allows the nodeClass to be set when a prompt is used.
The `dict()` method was causing a TypeError when trying to serialize the `template_field` object. The `to_dict()` method is the correct method to use to serialize the object.
The try-catch blocks were added to handle errors that may occur when the function is called. This improves the robustness of the function and prevents it from crashing when an error occurs.
🎨 style(chatMessage.tsx): change icon from MessageCircle to MessageSquare to improve semantics
🎨 style(index.tsx): add new icons to the import statement and change MessageSquareDashed to MessageSquare to improve semantics. Add padding to the chat modal to improve aesthetics.
✨ feat(promptComponent, genericModal): add setNodeClass prop to PromptAreaComponent and GenericModal to update nodeClass
The checkPrompt function has been renamed to postValidatePrompt to better reflect its functionality. The PromptTypeAPI now includes a frontend_node property, which is used to update the nodeClass in the PromptAreaComponent and GenericModal components. The setNodeClass prop has been added to both components to allow for updating the nodeClass.
🔥 chore(base.py): remove unused FrontendNodeRequest class
🔨 refactor(validate.py): modify post_validate_prompt function to update the template field in the frontend_node object
The ValidatePromptRequest class was using the FrontendNode class instead of the FrontendNodeRequest class, which caused an error. The unused FrontendNodeRequest class was removed. The post_validate_prompt function was modified to update the template field in the frontend_node object instead of appending to the fields list.
🚀 feat(formModal.tsx): add support for multiple input keys and values to be sent in the chat message
🐛 fix(formModal.tsx): fix keysValue state initialization and message object creation
🚀 feat(formModal.tsx): add switch component to select which input key to send in the chat message
🎨 style(formModal.tsx): add muted background color to input keys container
🐛 fix(api/index.ts): change message type to any to support multiple input keys and values
The noopener and noreferrer attributes were added to the documentation link to improve security by preventing the linked page from having access to the window.opener object and to prevent the referrer header from being sent to the linked page, respectively.
The FrontendNode class now has a new attribute called custom_fields, which is a list of strings. This attribute can be used to store any custom fields that are specific to a particular frontend node. This change allows for more flexibility in the data that can be stored in a FrontendNode object.
✨ feat(base.py): add frontend_node parameter to ValidatePromptRequest and PromptValidationResponse models
The validate_prompt endpoint now accepts a frontend_node parameter in the ValidatePromptRequest model. This parameter is used to add input variables to the frontend_node's template fields and custom fields. The PromptValidationResponse model now includes the frontend_node parameter to return the updated frontend_node object.
🔨 refactor(promptComponent): add nodeClass prop to improve code consistency
🔨 refactor(genericModal): add nodeClass prop to improve code consistency
🔨 refactor(types/components): remove unused imports and add nodeClass prop to TextAreaComponentType
The changes made in the code aim to improve code readability and consistency. The ParameterComponent, PromptAreaComponent, and GenericModal components now have a nodeClass prop to improve consistency with the naming conventions. The TextAreaComponentType now has a nodeClass prop to improve consistency with the other components.
The checkPrompt function was not properly validating prompts due to missing frontend_node parameter. The fix adds the frontend_node parameter to the function and passes it to the axios.post request.
✨ feat(ApiModal): pass the tweak.current value to the getPythonApiCode, getCurlCode and getPythonCode functions to allow tweaking of the flow. Update the tabs with the new code after a tweak is added.
🚀 feat(CodeAreaModal): replace UpdateTemplate function with postCustomComponent function to send custom component code to the server
The UpdateTemplate function was not being used and was removed. The postCustomComponent function was added to send custom component code to the server. The CodeAreaModal component was updated to use the new postCustomComponent function instead of the UpdateTemplate function to send custom component code to the server.
🐛 fix(nodeToolbarComponent): fix documentation link not working when no documentation is provided
The button colors and icons have been updated to improve visibility and consistency. The delete and copy buttons now have a darker background color when hovered over. The edit button now has a rounded right corner and a lighter background color when there are no nodes present. The documentation button now shows a "Coming Soon" tooltip when no documentation is provided and has a muted color. The documentation link now works correctly even when no documentation is provided.
The delayDuration prop was removed from all ShadTooltip components in the ExtraSidebar component. This improves the user experience by removing the delay before the tooltip is displayed.
The required indicator is now next to the title, which improves readability and makes it easier to see which parameters are required. The documentation tooltip has been simplified to only show the documentation link, which improves the user experience by reducing clutter. Unused imports have been removed to improve code quality.
🔨 refactor(parameterComponent): move required indicator next to title
The ShadTooltipComponent has been refactored to destructure the props and add types to improve readability and maintainability. The ShadTooltipProps type has been added to the types/components/index.ts file to define the expected props for the ShadTooltipComponent. The delayDuration, side, content, and children props are now destructured from the props object and have their respective types defined.
🔥 refactor(manager.py): remove unnecessary blank line at the end of the file
The package version has been updated to 0.2.3 in the pyproject.toml file. This is a chore as it does not affect the functionality of the package. The blank line at the end of the manager.py file has been removed as it is unnecessary and does not add any value to the code. This is a refactor as it improves the code readability.
The config.yaml file has been updated to include new prompt templates. In types.py, the input_variables list was not being cleared when prompt or messages were present, which has been fixed. The instantiate_prompt function in loading.py has been updated to support the new prompt templates.
🔀 chore(config): add new prompt templates to config.yaml
🐛 fix(types.py): fix input_variables not being cleared when prompt or messages are present
The variable name static_files_dir was changed to improve semantics. It is now more clear that it is a directory path. An optional static_files_dir parameter was added to the setup_app function to allow for a directory path to be passed in. This allows for more flexibility in serving static files.
🐛 fix(__main__.py): fix static_files_dir variable name to improve semantics
The first change removes an extra blank line in the ChatManager class. The second change updates the try_setting_streaming_options function to use the ChatConfig class to set the streaming option instead of hardcoding it. This makes the code more modular and easier to maintain.
This commit adds a new function `instantiate_llm` to handle LLM (Language Model) instantiation. It also sets the `ChatConfig.streaming` attribute based on the `openai_api_base` parameter. This is a workaround to ensure that JinaChat works until streaming is implemented.
The ChatConfig class is added to the project with a single attribute, streaming, set to True. This attribute is used to determine whether the chatbot should use streaming or request-response communication with the client.
