- 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.
- Removed Weaviate store implementation, streamlining the codebase and focusing on Mongo and Redis backends.
- Introduced GetAssistant method in both Mongo and Redis stores to retrieve a single assistant by ID, improving data access capabilities.
- Updated LoadStore function to utilize the new storage retrieval logic, enhancing the assistant loading process.
- Enhanced the Assistant struct to include a Script field for better management of assistant scripts.
- Improved tests to cover the new GetAssistant functionality, ensuring robust error handling and data retrieval across different scenarios.
- 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.
- Updated the message handling logic to improve error reporting and content management, ensuring more robust communication with clients.
- Introduced a new ReadBase64 method in both Local and OpenAI assistant implementations to read files and return their base64 encoded content, enhancing file handling capabilities.
- Removed the deprecated JSON message handling code, streamlining the message processing structure.
- Refactored message struct to include new fields and methods for better data management and response handling.
- Improved the chat functionality to handle attachments and user messages more effectively, ensuring a smoother user experience.
- Replaced the base assistant package with a local assistant implementation, enhancing modularity and maintainability.
- Updated the newAssistantByConnector function to utilize the local assistant, ensuring consistent error handling and improved functionality.
- Removed obsolete base assistant files, streamlining the codebase and reducing complexity.
- Added a new 'mentionable' field to the assistant table in the Xun implementation, allowing for better management of assistant visibility in mentions.
- Updated SaveHistory method across Mongo, Redis, and Weaviate to include a context parameter, improving flexibility in message storage.
- Modified the Assistant struct in types.go to add new fields: Type, Avatar, and Flows, enhancing the representation of assistant attributes.
- Adjusted the Xun implementation to support the new context handling in SaveHistory, ensuring messages can now include contextual information.
- Updated tests to reflect changes in message structure and ensure proper functionality with the new context parameter.
- Added new GET and POST endpoints for generating custom content, chat titles, and prompts, expanding the API's capabilities.
- Implemented support for Server-Sent Events (SSE) in response handling, allowing for real-time updates and improved user experience.
- Refactored validation and error handling to differentiate between regular and SSE requests, ensuring appropriate responses based on the request type.
- Updated the GenerateWithAI method to support silent mode for regular HTTP requests, enhancing flexibility in content generation.
- Improved overall structure and maintainability of the API by consolidating request handling logic.
- Introduced new API endpoints for generating custom content, chat titles, and prompts, enhancing the functionality of the Neo API.
- Implemented handleGenerateCustom, handleGenerateTitle, and handleGeneratePrompts methods to process generation requests with appropriate validation and error handling.
- Refactored the GenerateWithAI method to support different content types and system prompts, improving the flexibility of AI-generated responses.
- Updated the API router to include the new generation routes, ensuring seamless integration with existing middleware.
- Added time-based generation of chat IDs when not provided, improving chat session management.
- Updated context handling in handleChat to ensure valid chat IDs are used.
- Expanded allowed HTTP methods in CORS headers to include DELETE, enhancing API flexibility.
- Removed redundant chat history saving logic from GenerateChatTitle method, streamlining chat processing.
- Updated handleChatUpdate method to include content field in the request body, allowing for dynamic chat title generation based on user input.
- Implemented GenerateChatTitle method to create a concise title for chats, improving user experience and interaction.
- Modified JSON response structure in handleChatDetail and handleChatUpdate methods for better clarity and consistency.
- Enhanced error handling for chat updates, ensuring robust validation and feedback for users.
- Introduced new endpoints for retrieving chat details and mentions, enhancing the API's functionality.
- Implemented handleChatDetail method to fetch details of a specific chat by ID, including error handling for missing parameters.
- Added handleMentions method to retrieve mentions based on keywords, improving user interaction with chat content.
- Updated existing GetChats method to support keyword filtering, allowing for more refined chat list retrieval.
- Enhanced the DSL structure to include new methods for managing mentions and chat details, improving overall code organization and maintainability.
- Introduced a new endpoint for downloading files, enhancing the API's capabilities.
- Implemented the handleDownload method to manage download requests, including validation for required parameters (sid and file_id).
- Updated the Download method in the assistant interface to retrieve files based on file_id, ensuring proper error handling and response structure.
- Enhanced file upload logic to include file extensions in generated IDs for better file management.
- Added necessary response headers for file downloads, improving user experience during file retrieval.
Add the SelectModel command to the DSL, allowing the selection of a specific model. This command takes a model name as input and sets the AI to use that model. It returns a success message with a status code of 200 if the selection is successful.
