feat: Migrate document parsing to Aliyun and update embedding configurations

- Updated LocalDocumentParser to include raw_layouts and artifact_prefix from settings.
- Added new documents with failure reasons and metadata to documents.json for better error tracking.
- Created a new documentation file detailing the Aliyun ingest implementation process.
- Updated RFC to reflect changes in the parsing backend and embedding dimensions.
- Modified tests to accommodate the new embedding dimension of 1024 and updated parser and chunk builder assertions.
- Verified migration configurations to ensure correct settings for embedding model and backend.

backend/app/infrastructure/parser/aliyun_document_parser.py

@@ -1,19 +1,18 @@
-"""Implement infrastructure support for aliyun document parser."""
+"""Implement infrastructure support for Aliyun document parsing."""
 
 from __future__ import annotations
 
-from app.aliyun_parser.parse_pdf import (
+from app.config.settings import settings
+from app.domain.documents import DocumentParser, ParsedDocument
+from app.infrastructure.parser.aliyun_docmind_gateway import AliyunDocmindGateway
+from app.infrastructure.parser.aliyun_layout_normalizer import (
     MAX_CHARS,
     OVERLAP_CHARS,
     build_semantic_blocks,
     build_structure_nodes,
     build_vector_chunks,
-    collect_all_results,
-    init_client,
-    submit_job,
-    wait_for_completion,
 )
-from app.domain.documents import DocumentParser, ParsedDocument
+
 # Keep adapter behavior explicit so integration details remain easy to audit.
 
 
@@ -22,13 +21,14 @@ class AliyunDocumentParser(DocumentParser):
     """Provide the Aliyun Document Parser parser."""
     parser_name = "aliyun_docmind"
 
+    def __init__(self) -> None:
+        """Initialize the parser adapter and its gateway dependency."""
+        self.gateway = AliyunDocmindGateway()
+
     def parse(self, *, file_path: str, doc_id: str, doc_name: str) -> ParsedDocument:
         """Handle parse for the Aliyun Document Parser instance."""
-        client = init_client()
-        task_id = submit_job(client, file_path)
-        if not wait_for_completion(client, task_id):
-            raise RuntimeError("阿里云文档解析任务失败")
-        layouts = collect_all_results(client, task_id)
+        payload = self.gateway.parse_document(file_path=file_path)
+        layouts = payload.layouts
         structure_nodes = build_structure_nodes(layouts)
         semantic_blocks = build_semantic_blocks(layouts)
         vector_chunks = build_vector_chunks(
@@ -51,5 +51,13 @@ class AliyunDocumentParser(DocumentParser):
             vector_chunks=vector_chunks,
             parser_name=self.parser_name,
             raw_text=raw_text,
-            metadata={"task_id": task_id, "layout_count": len(layouts)},
+            raw_layouts=layouts,
+            metadata={
+                "task_id": payload.task_id,
+                "layout_count": len(layouts),
+                "poll_attempts": payload.poll_attempts,
+                "duration_ms": payload.duration_ms,
+                "parser_backend": self.parser_name,
+                "artifact_prefix": settings.document_parse_artifact_prefix,
+            },
         )