- Updated the API to include new upload options for handling different storage types: chat, knowledge, and assets.
- Improved group building logic for attachment uploads based on user, chat, and assistant IDs.
- Removed deprecated attachment files and refactored related code to streamline the attachment management process.
- Enhanced error handling for required fields in upload options, ensuring better validation and user feedback.
- Updated the API to support dynamic storage paths for file uploads, allowing for differentiated handling of chat, knowledge, and asset uploads.
- Implemented comprehensive authentication checks to ensure only authorized users can upload files.
- Introduced new upload options to handle original filenames and improved error responses for better user feedback.
- Enhanced CORS headers to accommodate new upload requirements and improve API security.
- Initialized authentication settings in the Load function to streamline user management.
- Added support for custom asset upload settings in the Upload struct, allowing for more flexible file handling.
- Implemented logic in initUpload to register default or custom asset upload configurations based on user settings.
- Improved error handling during asset registration to ensure robust functionality.
- Introduced initUpload function to initialize upload settings for chat and knowledge attachments.
- Updated Upload struct to include specific settings for chat and knowledge uploads.
- Implemented RegisterDefault and ReplaceEnv methods in the attachment manager for better configuration management.
- Enhanced error handling during the upload initialization process to ensure robust functionality.
- Introduced locale parameter in GetAssistants and GetAssistant methods across various store implementations to support localized responses.
- Updated handleChatLatest, handleAssistantList, handleAssistantDetail, and handleAssistantTags functions to utilize the new locale handling for better user experience.
- Refactored GetPlaceholder method in the Assistant struct to accept a locale argument for dynamic placeholder translations.
- Removed redundant i18n code and centralized translation logic for cleaner implementation.
- Introduced global i18n initialization and connector setup in the Load function for better localization support.
- Refactored handleAssistantList, handleAssistantDetail, and handleAssistantTags functions to utilize the new Translate method for improved response translation based on user locale.
- Simplified locale handling by removing redundant code and centralizing translation logic.
- Deleted hooks.go as it was no longer needed.
- Updated Load function in load.go to set default assistant name to "mohe" and adjusted store settings.
- Removed unused RAG and Vision initialization functions to simplify the codebase.
- Refactored defaultAssistant function to improve error handling for missing default assistant.
- Updated modification times for various asset files in bindata.go to reflect recent changes.
- Improved context handling in the API by adding support for silent mode, history visibility, and client type.
- Refactored assistant ID usage to ensure consistent access to the default assistant across various methods.
- Enhanced the Agent class in libsui/agent.ts to manage silent mode and history visibility settings effectively.
- Updated `DSL` struct to include `Connectors` with `assistant.ConnectorSetting` type
- Modified `initAssistant()` to set connector settings via `SetConnectorSettings()`
- Adjusted `load.go` and `types.go` to support new connector settings configuration
- Implemented connector-specific tool and vision handling in assistant methods
- Converted initialization methods from receiver methods to package-level functions
- Simplified method calls by directly using the global Neo instance
- Removed redundant method receiver references in initialization logic
- Improved code readability and reduced unnecessary method complexity
This change streamlines the Neo initialization process and makes the code more straightforward and maintainable.
- Removed unused assistant-related functions and types from the Neo API, including local chat and file handling, to streamline the codebase.
- Refactored the assistant initialization process, consolidating the loading and configuration of assistants, including Vision and Connector settings.
- Updated the DSL struct to enhance clarity and maintainability, ensuring better configuration management for assistants.
- Improved error handling and modularity in the assistant loading process, paving the way for future enhancements in AI functionalities.
- Removed obsolete AWS SDK v2 dependencies from go.mod and go.sum to streamline the codebase.
- Added Vision-related imports and initialized Vision settings in the Neo API, enhancing AI capabilities.
- Introduced initVision method to configure and initialize the Vision instance, improving modularity and functionality.
- Updated the DSL struct to include Vision settings, allowing for better configuration management.
This commit supports future enhancements in AI functionalities and improves the overall structure of the Neo API.
- Updated the SetRAG function to include RAG settings, allowing for more detailed configuration during assistant initialization.
- Refactored the LoadBuiltIn function to streamline the saving process of assistants, improving error handling and code clarity.
- Modified loadPrompts and loadScript functions to return timestamps, enabling tracking of creation and update times for assistants.
- Enhanced the Assistant struct with created_at and updated_at fields, improving data management and traceability.
- Overall improvements to the assistant loading process, ensuring better organization and maintainability of the codebase.
- Introduced new methods for initializing RAG and store, improving modularity and clarity in the Load function.
- Refactored the assistant initialization process to streamline the loading of built-in assistants and set RAG configurations.
- Moved the defaultAssistant method from neo.go to load.go for better organization and accessibility.
- Enhanced error handling in store initialization to support multiple connector types, including Redis and Mongo.
- Updated the assistant struct to include RAG settings, improving the overall assistant management capabilities.
- Changed the 'Table' field to 'Prefix' in the Setting struct to better represent its purpose as a table name prefix.
- Updated all relevant instances in the codebase to use the new 'Prefix' field, ensuring consistency across the application.
- Adjusted logging and table retrieval methods to reflect the new naming convention, enhancing clarity and maintainability.
- Bump Go version from 1.22.2 to 1.23 for improved performance.
- Update dependencies in go.mod and go.sum, including:
- github.com/PuerkitoBio/goquery to v1.10.1
- github.com/dchest/captcha to v1.1.0
- github.com/evanw/esbuild to v0.24.2
- github.com/fatih/color to v1.18.0
- github.com/fsnotify/fsnotify to v1.8.0
- github.com/spf13/cobra to v1.8.1
- github.com/stretchr/testify to v1.10.0
- github.com/xuri/excelize/v2 to v2.9.0
- Introduce RAG (Retrieval-Augmented Generation) initialization in the Neo API, enhancing assistant capabilities.
- Refactor workflows to use Go 1.23 for testing and CI processes, ensuring compatibility with the latest features.
- Simplified the assistant loading process by removing the asynchronous query for the assistant list and replacing it with a direct call to retrieve the default assistant.
- Introduced a new method, defaultAssistant, to streamline the retrieval of the default assistant based on the current configuration.
- Enhanced the LoadStore function to support loading assistants from a specified path, improving flexibility in assistant management.
- Updated the overall structure for better readability and maintainability, ensuring a more efficient assistant initialization process.
- Added a new endpoint to retrieve all assistant tags, improving data accessibility for clients.
- Updated the assistant list handling to support filtering by built-in status and assistant ID, enhancing the filtering capabilities.
- Introduced a method to load built-in assistants, streamlining the assistant initialization process.
- Enhanced the Assistant struct with new fields for path, built-in status, and sorting, improving data organization.
- Implemented validation and cloning methods for the Assistant struct, ensuring data integrity and ease of use.
- Updated tests to cover new functionalities, including validation, cloning, and tag retrieval, ensuring robust functionality across the assistant management operations.
- Replaced the conversation handling logic with a new store-based approach, enhancing data management and retrieval capabilities.
- Updated all relevant methods to utilize the new store interface, including GetChats, GetChat, GetHistory, and SaveAssistant, ensuring consistent functionality across the API.
- Removed deprecated conversation-related files and structures, streamlining the codebase and improving maintainability.
- Enhanced the AssistantFilter and AssistantResponse types to support the new store architecture, improving filtering and pagination capabilities.
- Updated tests to cover the new store-based methods and ensure robust functionality across different storage backends.
