Enhance knowledge base functionality and integrate S3 storage support

- Add new models for `KnowledgeDocument` and `KnowledgeChunk` to manage document ingestion and chunking.
- Implement S3-compatible storage integration for knowledge documents, allowing for file uploads and retrieval.
- Introduce API endpoints for managing knowledge bases and documents, including creation, deletion, and searching.
- Update frontend components to support knowledge base configuration and document management, improving user interaction.
- Enhance backend services for knowledge processing and retrieval, ensuring robust handling of document statuses and errors.

backend/routes/assistants.py

@@ -6,6 +6,7 @@ from db.models import (
     Assistant,
     AssistantModelBinding,
     AssistantToolBinding,
+    KnowledgeBase,
     ModelResource,
     Tool,
 )
@@ -52,6 +53,14 @@ async def _validate_vision_model(
             raise HTTPException(400, "视觉模型必须支持图片输入")
 
 
+async def _validate_knowledge_base(session: AsyncSession, body: AssistantUpsert) -> None:
+    if body.runtime_mode != "pipeline" or body.type not in {"prompt", "workflow"}:
+        body.knowledge_base_id = None
+        return
+    if body.knowledge_base_id and not await session.get(KnowledgeBase, body.knowledge_base_id):
+        raise HTTPException(400, "知识库不存在")
+
+
 async def _sync_bindings(
     session: AsyncSession, assistant_id: str, resource_ids: dict[str, str]
 ) -> None:
@@ -166,6 +175,7 @@ async def create_assistant(
 ):
     _validate_workflow(body)
     await _validate_vision_model(session, body)
+    await _validate_knowledge_base(session, body)
     data = body.model_dump()
     resource_ids = data.pop("model_resource_ids")
     tool_ids = data.pop("tool_ids")
@@ -235,6 +245,7 @@ async def update_assistant(
         raise HTTPException(404, "助手不存在")
     _validate_workflow(body)
     await _validate_vision_model(session, body)
+    await _validate_knowledge_base(session, body)
     data = body.model_dump()
     resource_ids = data.pop("model_resource_ids")
     tool_ids = data.pop("tool_ids")