공급자 cost-tier/vision passthrough + 내부 원샷 비전 엔드포인트
AiProviderController reads/echoes costTier + supportVision. 계정 관리 서비스 이득 selectVisionProvider (orgId, 계층). *************** 원샷 실행 org의 공급자/adapter ( session/RAG/...
익명 방문자를위한 RAG 통합으로 공공 AI 채팅 엔드 포인트 추가
/api/ai/public/sessions endpoints를 마케팅 사이트에 익명 AI 채팅에 추가합니다. OTK auth 필터를 우회합니다. public-facing 시스템 프롬프트 사용 RAG with memberType=null for public-only KB 기사 가시성.
RAG를 통한 회원유형 조회
MemberRepository에서 회원 유형에 용해하고 RAG 검색 요청에 포함 그래서 벡터 DB는 청중 가시성에 의해 KB 기사를 필터링 할 수 있습니다.
Wire ConversationContextService for sliding window context management
Trims conversation history to fit model's context window before sending to LLM. Keeps recent messages verbatim, summarizes older ones.
Include clickable source links in RAG context for AI chat
Update RagClient to embed markdown links in the context sent to the AI model. KB articles link to /kb/{guid}, notes link to /notes?id={noteId}. Instructs the mo...
Pass memberId to RAG for note-aware AI chat
Add extractMemberId to SessionHelper. Update RagClient to send memberId in search requests so RAG returns both org KB articles and the member's own AI-enabled n...
Add RAG context injection for Knowledge Base in AI chat
- New RagClient service for calling RAGService semantic search - ChatOrchestrationService injects KB context before AI responds - Configurable via AiOrgSettings...
Support enabling/disabling models via PUT /api/ai/providers/{id}
When the frontend sends a 'models' array of model IDs in the provider update request, models in the array are set active and models not in the array (belonging ...
Add POST **************** endpoint for sending chat messages
Receives user message, sends to AI provider via ChatOrchestrationService, returns complete response. Supports REST-based chat flow.
Add Hugging Face as dedicated provider type with custom adapter
- HuggingFaceAdapter handles HF's URL structure **************** - Model discovery via HF API (warm text-generation models) - Registered in ProviderAdapterFacto...
Add manual model creation, handle 410/404 in test, use discovered model for CUSTOM providers
- POST /api/ai/models endpoint for manually adding models - DELETE /api/ai/models/{id} endpoint - CUSTOM providers use first discovered model for chat test inst...
Implement model auto-discovery on provider test connection
Each provider adapter discovers available models from the provider API. Models are automatically saved to the database when Test Connection succeeds.
Scaffold AIService project with providers, services, websocket, and controllers
AI chat orchestration service on port 4205 with: - WebSocket streaming with session auth via ***/Redis - Chat orchestration with auto-routing, usage tracking, a...