- Removed the synchronous preparation of the knowledge base (KB) collection from the InitializeConversation method, now initializing it asynchronously after user login.
- Introduced a new method, GetDocumentsContent, to retrieve content for multiple documents by their IDs, supporting text-based files and improving document handling.
- Updated the API interface to include the new GetDocumentsContent method, enhancing the document management capabilities.
- Enhanced locale handling in the login context to support user preferences during KB collection creation.
- Added ExecuteWithAuthorized method to the Script struct, allowing scripts to be executed with user authorization information.
- Updated existing Execute method to utilize ExecuteWithAuthorized for improved authorization handling.
- Enhanced script execution tests to verify behavior with and without authorized information, ensuring accurate context management.
- Implemented authorized information conversion to a map for easier integration with runtime environments.
- Refactored context handling in script execution to ensure authorized data is correctly passed and utilized.
- Updated job execution identifiers in AddFileAsync, AddTextAsync, and AddURLAsync to use more descriptive names.
- Removed obsolete async processing functions for file, text, and URL, streamlining the codebase.
- Enhanced the registration of document processing handlers in the knowledge base initialization, ensuring clarity and consistency.
- Renamed the Start method to Push for better semantic clarity in job execution.
- Introduced OnceAndSave, CronAndSave, and DaemonAndSave methods for immediate job creation and saving.
- Added new test cases for OnceAndSave, CronAndSave, and DaemonAndSave methods to ensure proper functionality.
- Updated AddFileProcess, AddTextProcess, and AddURLProcess to utilize new job handling methods, improving consistency across document operations.
- Enhanced error handling and logging in document processing functions for better traceability.
- Introduced readonly field for collections and documents to indicate if they are read-only.
- Updated ListCollections endpoint to support pagination and filtering by various parameters, including keywords, status, and system flags.
- Enhanced query capabilities with dynamic field selection and sorting options for collections.
- Refactored GetCollections to ListCollections for improved clarity in functionality.
- Updated API response structures to reflect new filtering and sorting features, ensuring better data access and management.
- Enhanced GetSegmentGraph function to retrieve segment entities and relationships based on query parameters, improving data access.
- Introduced new endpoint GetSegmentRelationshipsByEntities for fetching relationships connected to entities, with appropriate error handling.
- Updated response structures to reflect counts and types of queries used, ensuring clarity in API responses.
- Modified go.mod and go.sum to update the dependency for github.com/ulikunitz/xz to version 0.5.14.
- Implemented new endpoints for retrieving segment entities and relationships, improving data access for clients.
- Added error handling for missing document and segment IDs, ensuring robust validation in GetSegmentEntities and GetSegmentRelationships functions.
- Enhanced GetSegmentGraph function to support filtering options for entities and relationships, allowing for more flexible responses.
- Updated response structures to include counts for entities and relationships, improving clarity in API responses.
- Added error handling for uninitialized knowledge base in hit and vote endpoints.
- Implemented ScrollHits and ScrollVotes methods to retrieve paginated results with filtering options.
- Updated AddHits and AddVotes functions to handle request validation and response formatting.
- Enhanced response structures to include updated counts for added and removed hits and votes.
- Introduced new request types for updating hits and votes, allowing for default reactions in segments.
- Renamed segment extraction functions to better reflect their purpose, changing `ExtractSegmentEntities` to `ExtractSegmentGraph` and `ExtractSegmentEntitiesAsync` to `ExtractSegmentGraphAsync`.
- Updated API routes to use the new function names for segment extraction, enhancing clarity and consistency.
- Introduced new request structures for batch updates of scores and weights, improving the API's capabilities for segment management.
- Removed the outdated `store.go` file to streamline the codebase.
- Rearranged and updated API endpoints for collections, including adding GetCollections and adjusting the order of operations for better clarity.
- Enhanced segment management by introducing new endpoints for segment scores, weights, and votes, along with async operations for adding and updating segments.
- Improved error handling for missing document IDs in segment-related functions, ensuring robust validation.
- Streamlined response structures to include document and segment IDs in relevant endpoints, enhancing the API's usability.
- Added GetCollection endpoint to retrieve collections by ID, including error handling for missing IDs and uninitialized knowledge base.
- Updated CreateCollectionConfig to use more descriptive field names for embedding provider and option IDs.
- Refactored UpdateSegments function to improve validation and error handling, ensuring document IDs and segment texts are properly checked.
- Introduced new request structures for updating votes, scores, and weights for segments, enhancing the API's capabilities.
- Removed the outdated vote handling file to streamline the codebase.
- Replaced ListSegments function with ScrollSegments to implement iterator-style pagination.
- Updated related comments and error messages to reflect the new scrolling functionality.
- Streamlined API routes by removing the redundant ListSegments endpoint, enhancing overall clarity.
- Introduced `file_id` field in the document model to link documents with their corresponding files in the attachment system.
- Updated `AddFileProcess` to include `file_id` in the response, improving document tracking.
- Modified `GetDocument` function to support the new `file_id` field in document retrieval.
- Removed the unused `ScrollDocuments` endpoint to streamline the API.
- Improved error handling and response structure for document-related operations.
- Renamed extractor provider to extraction provider across the codebase for consistency and clarity.
- Updated references in configuration files, provider factories, and asset management to reflect the new terminology.
- Removed the extractor provider implementation and associated test files, streamlining the provider structure.
- Adjusted test cases and documentation to align with the new extraction provider framework.
- Introduced a Validator interface and a validateRequest function to streamline request validation across handlers.
- Added checkKBInstance function to ensure the knowledge base instance is initialized before processing requests.
- Implemented handleAsync function to manage asynchronous processing for file and text addition.
- Updated AddFile and AddText functions to utilize the new validation and async handling logic.
- Added async variants for AddFile and AddText to support non-blocking operations.
- Enhanced AddURL and its async variant with similar validation and processing improvements.
- Implemented GetProviders and GetProvider methods to retrieve providers based on type and ID, improving the knowledge base's provider management capabilities.
- Enhanced the Schema methods for chunking providers to retrieve schemas from bindata, ensuring better integration with the overall system.
- Updated OpenAPI routes to include endpoints for provider management, allowing for easier access to provider information via HTTP requests.
- Implemented UpdateCollectionMetadata function to handle metadata updates for existing collections.
- Added request structure and validation for updating collection metadata.
- Integrated new endpoint in the router for updating collection metadata via PUT request.
- Introduced the Knowledge Base (KB) API by creating a new kb package with various endpoints for collection and document management, segment management, and search functionalities.
- Updated the OpenAPI router to attach the KB API, ensuring OAuth protection for all endpoints.
- Implemented logging for configuration validation to enhance error handling and user feedback.
