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.

tests/verify_mvp.py

@@ -64,11 +64,16 @@ def verify_migration_config() -> bool:
 
     try:
         assert settings.embedding_model == "text-embedding-v3"
-        assert settings.embedding_dim == 1536
-        assert settings.milvus_collection == "regulations_dense_1536"
+        assert settings.embedding_dim == 1024
+        assert settings.milvus_collection == "regulations_dense_1024_v1"
+        assert settings.parser_backend == "aliyun"
+        assert settings.chunk_backend == "aliyun"
         logger.info(f"embedding_model={settings.embedding_model}")
+        logger.info(f"embedding_base_url={settings.embedding_base_url}")
         logger.info(f"embedding_dim={settings.embedding_dim}")
         logger.info(f"milvus_collection={settings.milvus_collection}")
+        logger.info(f"parser_backend={settings.parser_backend}")
+        logger.info(f"chunk_backend={settings.chunk_backend}")
         logger.success("migration config ok")
         return True
     except Exception as exc: