- Implemented system prompts for tool calls when connector settings disable native tool handling
- Added JSON-formatted tool list and explicit rules for tool call processing
- Included guidelines for tool call response formatting and function usage
- Preserved existing tool prompts functionality
- 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
- Renamed `Functions` to `Tools` across multiple files
- Added `ConnectorSetting` to support vision and tools flags
- Updated loading and serialization logic for tools
- Modified message contents handling for better JSON parsing
- Adjusted test cases to reflect tool-related changes
- Enhanced error handling in OpenAI message processing
- Added colored console output for JSON parsing errors
- Updated Error struct to support flexible code type
- Improved message type and done state setting for various error scenarios
- Added support for parsing different error message formats
- Implemented `select` parameter parsing in `parseAssistantFilter`
- Added support for selecting fields via string, string array, or interface array
- Enhanced `neo/process.go` to handle flexible field selection
- Improved error handling in stream chat processing
- Fixed function message handling in message appending
- Added support for parsing and handling pending and error messages in stream processing
- Improved error message extraction and writing for better error visibility
- Updated message type handling to capture and process raw error messages
- Introduced more flexible input parsing in withHistory and execute methods
- Added environment variable support for connector configuration in assistant loading
This change improves the robustness of error handling and message processing in the Neo API assistant, providing more comprehensive error reporting and input flexibility.
- Added filtering for 'function' type messages in requestMessages method
- Removed debug print statement in streamChat method
- Enhanced message handling to ignore function call messages during processing
This change refines the message filtering logic in the Neo API assistant, improving the clarity and efficiency of message stream processing.
- Updated HookCreate to support extended timeout and input message parsing
- Modified CreateResponse to include optional input messages
- Refactored assistant hooks to improve context and message handling
- Added support for more flexible streaming and done hook processing
- Adjusted timeout contexts and method signatures for better error management
This change improves the Neo API assistant's flexibility and robustness in handling complex message interactions and hook scenarios.
- Added `AssistantIDs` field to `AssistantFilter` to support filtering by multiple assistant IDs
- Updated `GetAssistants` and `DeleteAssistants` methods to handle multiple assistant ID filtering
- Expanded test cases to verify multi-ID filtering, selection, and deletion functionality
- Simplified and improved test data generation and cleanup processes
This change provides more flexible assistant retrieval and management capabilities in the Neo API.
- Implemented `processAssistantMatch` method to handle assistant matching requests
- Added support for limit parameter with default and maximum values
- Introduced `forceStore` flag to control matching method (RAG or store)
- Created placeholder methods `assistantMatchRAG` and `assistantMatchStore`
- Enhanced OpenAI message handling to parse error responses
- Updated message type handling to include error messages
This change adds flexible assistant matching capabilities with initial infrastructure for RAG and store-based matching.
- Introduced Version and RAG flags in the Context struct to support advanced assistant features
- Updated Execute method to set RAG and Version context properties
- Enhanced withOptions method to conditionally add custom options and tools
- Modified HookInit to pass options parameter, improving hook flexibility
This change improves the Assistant's configurability and supports more dynamic assistant interactions.
- 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.
- Improved tag handling in loadMap to support multiple input types
- Added support for parsing tags from []interface{}, string, and other JSON-compatible formats
- Utilized jsoniter for robust type conversion and marshaling
- Increased robustness of tag loading process for diverse input scenarios
This change enhances the flexibility of tag parsing during Assistant initialization, allowing more versatile data input methods.
- Implemented a new `/chats/latest` endpoint to fetch the most recent chat or generate a placeholder
- Added `handleChatLatest` method in the DSL to support retrieving the latest chat for a given session
- Introduced `GetPlaceholder()` method in the Assistant interface to support placeholder generation
- Enhanced API flexibility by allowing optional assistant ID specification for placeholder retrieval
This change improves the chat retrieval capabilities of the Neo API, providing a convenient way to access the most recent chat or generate a starting point for new conversations.
- Introduced a new Placeholder struct to provide additional metadata for assistants
- Updated Assistant struct to include an optional Placeholder field
- Modified loading and mapping methods to handle Placeholder data
- Extended database schema and test cases to support Placeholder functionality
This enhancement provides a flexible way to add descriptive metadata to assistants, improving their discoverability and configuration.
- Modified the message handling logic to include 'action' messages in the ignore list alongside 'loading' and 'error' messages, improving the clarity of message processing.
- This change enhances the robustness of the Neo API assistant by ensuring that irrelevant message types are not processed, streamlining the overall message handling workflow.
- Added a new endpoint for executing assistant calls via POST request, enhancing the API's capabilities.
- Introduced the handleAssistantCall method to process incoming requests, validate parameters, and execute the assistant's script.
- Updated the Assistant interface to include the Call method, allowing for dynamic method invocation based on the provided payload.
- Enhanced error handling for missing parameters and invalid requests, improving the robustness of the assistant's API interactions.
These changes significantly improve the Neo API assistant's functionality, enabling more interactive and dynamic assistant capabilities.
- Added 'updated_at' field to the chat selection query to include the last modified timestamp in chat responses.
- Updated the ordering of chat results to prioritize 'updated_at' over 'created_at', improving the relevance of displayed chats.
- Modified the handling of chat creation timestamps to fall back on 'created_at' if 'updated_at' is not available, ensuring consistent date representation.
- Implemented an update mechanism for the 'updated_at' field when saving chat history, enhancing data integrity and tracking.
These changes improve the chat management capabilities of the Neo API assistant, ensuring more accurate and relevant chat data retrieval.
- Enhanced message generation by introducing NewHistory and NewContent methods for improved handling of message content and history.
- Updated the withHistory method to utilize the new NewHistory method, streamlining the addition of historical messages.
- Improved the call method to conditionally save message history based on input parameters, enhancing flexibility in message management.
- Refactored the String method in the Message struct to better represent message types and properties, improving serialization consistency.
These changes enhance the maintainability and robustness of the Neo API assistant, paving the way for improved message handling and content processing.
- Updated the Assistant methods to include a new Contents parameter in HookInit, HookStream, HookDone, and HookFail, improving message context management.
- Refactored handleChatStream to utilize the new Contents structure, enhancing the clarity and efficiency of chat interactions.
- Introduced new methods in the Contents struct for better type management and properties handling, streamlining message processing.
- Updated the Message struct to support new content types and properties, improving the overall message structure and serialization.
These changes enhance the maintainability and robustness of the Neo API assistant, paving the way for improved message handling and assistant functionalities.
- Renamed the 'is_new' field to 'new' in the Message struct for better clarity and consistency in JSON output.
- This change enhances the maintainability of the Neo API assistant by streamlining the message structure and improving data representation.
- Updated message appending methods to use AppendTo for improved clarity and consistency.
- Changed output types in HookStream and HookDone methods from string to []message.Data, enhancing data handling capabilities.
- Introduced a new Map method in the Data struct for better representation of message data.
- Streamlined JSON marshaling in the Data struct to ensure accurate data serialization.
These changes enhance the maintainability and robustness of the Neo API assistant, paving the way for improved message handling and data processing.
- Replaced the Content struct with a new Contents struct to improve message handling and organization.
- Updated methods across the Assistant and Message structs to utilize the new Contents structure, enhancing the clarity and efficiency of message processing.
- Improved error handling by ensuring proper message appending and content management during chat streaming.
- Removed the deprecated Content struct, streamlining the codebase and reducing complexity.
These changes enhance the maintainability and robustness of the Neo API assistant, paving the way for improved message handling and assistant functionalities.
- Removed the asynchronous execution of method calls, allowing for direct invocation within the current thread.
- Simplified cancellation handling by eliminating the done channel, improving clarity and reducing complexity in the call method.
- Enhanced error handling by ensuring the script context is checked before method invocation.
These changes improve the maintainability and robustness of the Neo API assistant, paving the way for more efficient method execution and context management.
- Removed the forced closure of the script context upon context cancellation in the call method, improving the handling of script execution and cancellation scenarios.
- This change enhances the robustness of the Neo API assistant by preventing potential issues related to premature context termination, paving the way for more reliable assistant functionalities.
- Added nil check for script context in the call method to prevent potential nil pointer dereference.
- Updated the String method in the Content struct to include additional properties (text and props) for better message representation.
These changes improve the robustness and maintainability of the Neo API, paving the way for enhanced message handling and assistant functionalities.
- Added nil checks for response objects in the Execute method to prevent potential nil pointer dereferences.
- Updated the streamChat method to include assistant identification details (ID, name, avatar) in the message structure, improving context for messages.
- Introduced a new field in the Message struct to mark messages as new, enhancing message tracking capabilities.
These changes improve the robustness and maintainability of the Neo API, paving the way for better message handling and assistant functionalities.
- Removed unused utility imports and streamlined the saveChatHistory method to improve message storage efficiency.
- Updated the Message struct to include new fields for assistant identification and mentions, enhancing message context and traceability.
- Modified the history table structure to accommodate new assistant-related fields and mentions, ensuring comprehensive data storage.
- Improved the SaveHistory method to process and store mentions alongside messages, providing better context for user interactions.
These changes enhance the robustness and maintainability of the Neo API, paving the way for improved message handling and assistant functionalities.
- Updated the Assistant struct to include a vision capability flag and an init hook indicator, allowing for better management of vision-enabled functionalities.
- Refactored message handling throughout the assistant methods to utilize the chatMessage package, improving consistency and type safety.
- Enhanced the handleVision method to support dynamic vision processing options, including improved handling of image descriptions and uploads.
- Streamlined the requestMessages and withAttachments methods to better accommodate vision capabilities, ensuring proper integration with image handling.
- Improved the initialize method to check for vision support based on the model, enhancing the assistant's adaptability.
These changes improve the robustness and maintainability of the Neo API, paving the way for enhanced assistant functionalities and better integration of vision capabilities.
- Updated streamChat method to utilize content.Type for function handling, enhancing the interaction with function calls.
- Improved the String method in Content struct to handle function arguments more robustly, including JSON unmarshalling for completed content.
- Set default message type to "text" in NewOpenAI function, ensuring consistent message processing.
These changes enhance the flexibility and maintainability of the Neo API, paving the way for improved assistant functionalities and message management.
- Introduced a new Function type to define assistant functions, enhancing the assistant's capabilities.
- Updated the Assistant struct to include a Functions field, allowing for dynamic function management.
- Refactored the streamChat method to handle tool calls, improving interaction with functions during chat streaming.
- Enhanced message handling in the NewOpenAI function to support tool call responses, ensuring proper message parsing.
- Implemented loading and saving of functions from a JSON file, streamlining function management within the assistant.
These changes improve the robustness and maintainability of the Neo API, paving the way for more flexible and powerful assistant functionalities.
- Introduced a new Execute method for handling next actions in the Assistant struct, allowing for dynamic execution of various actions such as "process" and "assistant".
- Improved error handling by validating payloads and providing meaningful error messages for missing or incorrect data.
- Streamlined the flow of next actions in the Execute method, enhancing the assistant's ability to manage complex interactions and responses.
- Updated the streamChat method to utilize the new Execute method, improving the handling of next actions during chat streaming.
These changes enhance the robustness and maintainability of the Neo API, paving the way for more flexible and powerful assistant functionalities.
- Commented out the message writing logic in the streamChat method to prevent unintended output when the message is marked as done.
- This change enhances the control over the response flow, allowing for better integration with the newly introduced hook methods for managing assistant interactions.
These modifications contribute to the overall robustness and maintainability of the Neo API, aligning with recent enhancements in assistant functionalities.
- Introduced HookDone and HookFail methods to manage completion and failure scenarios in assistant responses, improving error handling and output customization.
- Updated streamChat method to utilize these hooks, allowing for more flexible response management based on the assistant's output and error states.
- Enhanced ResHookDone and ResHookFail structs to include next action handling, input messages, and error information, providing better control over assistant interactions.
These changes improve the robustness and maintainability of the Neo API, paving the way for enhanced assistant functionalities and message management.
- Added message handling in the Execute method to support input messages from the response.
- Updated the handleChatStream method to pass the context to the streamChat method, improving context management during chat streaming.
- Introduced the HookStream method to handle streaming responses, allowing for custom output and next action handling based on the assistant's response.
- Enhanced the ResHookStream struct to include silent output control and next action management, providing better flexibility in assistant interactions.
These changes improve the robustness and maintainability of the Neo API, paving the way for enhanced assistant functionalities and message management.
- Updated the Answer method to utilize the new Execute method, simplifying the assistant interaction process.
- Introduced a new Execute method in the Assistant struct to encapsulate the chat execution logic, enhancing clarity and maintainability.
- Refactored the HookInit method to accept input messages and options, improving the initialization process for assistants.
- Enhanced the ResHookInit struct to include next action handling and input messages, providing better control over assistant responses.
- Removed obsolete chat handling methods, streamlining the codebase and improving overall structure.
These changes improve the robustness and maintainability of the Neo API, paving the way for future enhancements in assistant functionalities and message management.
- Updated the Answer method to utilize the new withHistory function, improving message retrieval and context management.
- Refactored the chat method to accept a slice of message.Message instead of a map, enhancing type safety and clarity.
- Introduced a new withHistory function to streamline the process of retrieving chat history and user messages, improving maintainability.
- Enhanced the HookInit method to accept a gin.Context, allowing for better context handling during assistant initialization.
- Updated the assistant API interface to reflect changes in message handling, ensuring consistency across the codebase.
These changes improve the robustness and maintainability of the Neo API, paving the way for future enhancements in assistant functionalities and message management.
- Updated the Answer method to improve assistant initialization by directly calling the new HookInit method, streamlining the process of selecting and initializing assistants based on context.
- Introduced ResHookInit struct to encapsulate the response from the assistant initialization hook, enhancing clarity and maintainability.
- Enhanced the context package by adding a Map method to facilitate easier mapping of context data, improving the overall structure of context management.
- Refactored the assistant interface to include the new HookInit method, ensuring a consistent approach to assistant interactions.
These changes improve the robustness and maintainability of the Neo API, paving the way for future enhancements in assistant functionalities and context management.
- Replaced the custom context creation functions with a new context package, enhancing consistency and maintainability across the API.
- Updated multiple methods in the DSL to utilize the new context package, ensuring a unified approach to context management.
- Removed the obsolete context.go file, streamlining the codebase and reducing redundancy.
These changes improve the overall structure and clarity of the Neo API, paving the way for future enhancements in context handling and assistant functionalities.
- Updated the TestUpload and TestUploadWithRAG functions to remove unnecessary parameters and improve clarity.
- Enhanced RAG handling by adding options for enabling/disabling RAG processing during file uploads.
- Improved test cases for RAG functionality, ensuring proper indexing behavior based on RAG settings.
- Refactored vision-related tests to include options for enabling/disabling vision processing, ensuring accurate responses based on the model capabilities.
- Streamlined the setup of test assistants to simplify the testing process.
These changes improve the maintainability and clarity of the attachment handling code, paving the way for better functionality in file uploads and processing.
- Refactored the Analyze method in the Vision and OpenAI model to accept a variadic prompt parameter, allowing for optional custom prompts while defaulting to a predefined prompt if none is provided.
- Added multiple test cases in vision_test.go and model_test.go to validate image analysis with default, custom, and empty prompts, ensuring robust functionality and error handling.
- Updated the Model interface to reflect the new prompt handling, improving clarity and usability.
These changes enhance the flexibility of the Vision module, paving the way for improved user experience and functionality in image analysis.
- Updated the Upload method in the DSL to default to the assistant in context, improving error handling for missing assistant IDs.
- Introduced parseEnvValue and convertOptions functions in the Vision module to support parsing environment variables in configuration options, enhancing flexibility.
- Refactored storage and model initialization in the Vision service to utilize converted options, ensuring environment variables are correctly applied.
These changes improve the robustness and maintainability of the Neo API, paving the way for better configuration management and error handling in assistant functionalities.
- Removed obsolete file upload/download functions and related constants from the Assistant struct, streamlining the codebase.
- Updated the connector type in load tests to use "gpt-3_5-turbo" for improved compatibility with current models.
- Introduced VisionCapableModels to support a range of models with vision capabilities, enhancing AI functionality.
- Enhanced the File struct to include additional fields for description, URL, and document IDs, improving data management for file handling.
These changes improve the overall structure and maintainability of the Neo API, paving the way for future enhancements in assistant capabilities.
- Added the github.com/spf13/cast dependency to improve type conversion capabilities.
- Enhanced the requestMessages function to include prompts, allowing for more dynamic message handling.
- Updated the LoadBuiltIn function to ensure the "Built-in" tag is added if it doesn't already exist, improving assistant organization.
- Refactored sorting logic to utilize the cast package for better type safety.
These changes support improved functionality and maintainability in the assistant management process.
- 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.
- Deleted the obsolete prompt.md file, streamlining the codebase.
- Added tests for image upload and download functionality using local and S3 storage drivers, ensuring robust handling of image files.
- Implemented image compression during upload for both local and S3 storage, maintaining aspect ratio and limiting dimensions to a maximum size of 1920x1080.
- Enhanced the local and S3 storage drivers to support image compression, improving storage efficiency.
- Updated tests to verify image dimensions and content type after upload and download operations, ensuring data integrity.
- Added several AWS SDK v2 modules to go.mod and go.sum, enhancing cloud service integration capabilities:
- github.com/aws/aws-sdk-go-v2 and its related services (S3, STS, SSO, etc.) for improved AWS functionality.
- Updated indirect dependencies to ensure compatibility and performance improvements.
- This update supports future development involving AWS services, streamlining the integration process.
- 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.
