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/core/config.py

@@ -27,12 +27,12 @@ class Settings(BaseSettings):
     # Milvus
     milvus_host: str = "localhost"
     milvus_port: int = 19530
-    milvus_collection: str = "regulations_dense_1536"
+    milvus_collection: str = "regulations_dense_1024_v1"
 
     # LLM / embedding defaults aligned with the migrated backend path.
     llm_model: str = "qwen-max"
     embedding_model: str = "text-embedding-v3"
-    embedding_dim: int = 1536
+    embedding_dim: int = 1024
 
     # Legacy workflow compatibility only.
     vector_top_k: int = 10
@@ -47,7 +47,7 @@ class Settings(BaseSettings):
     api_port: int = 8000
 
     # Legacy aliases retained for old utility modules.
-    regulations_collection: str = "regulations_dense_1536"
+    regulations_collection: str = "regulations_dense_1024_v1"
     compliance_collection: str = "compliance_cache"
 
 # Preserve the legacy module API while keeping env resolution centralized at the repo root.