Expose and propagate RAG (retrieval-augmented generation) source metadata through the stack so clients can display provenance for assistant responses. Adds AIChatRagSourceDto / ChatRagSourceDto DTOs and mapper, includes RagSources on integration and client response/update DTOs, and extracts sources in AIChatCompletionIntegrationService (streamed updates and final response). Introduces IRagSourceCollector and a scoped RagSourceCollector implementation to collect chunks during search/tool execution; DocumentSearchService now adds found sources to the collector. RagService and IndexDocumentJob include file_name metadata when indexing/searching. UI updates: Blazor component and client JS render collapsible source lists; localization key for "AIChat:Sources" added. This enables showing file name, chunk index, similarity score and content preview for RAG context in the chat UI.

Checklist

• I fully tested it as developer / designer and created unit / integration tests
• I documented it (or no need to document or I will create a separate documentation issue)
• I worked with the design team to get their idea for UI/UX design (or no need to design for this PR)
• I've assigned reviewer, related labels and set a milestone for this PR

10.2.0-rc.2 09 March, 2026 abp-module-ai-management ui-mvc ui-blazor