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.

.env

@@ -9,7 +9,7 @@ DEBUG=false
 # ===== Milvus向量数据库配置（已有）=====
 MILVUS_HOST=localhost
 MILVUS_PORT=19530
-MILVUS_COLLECTION=regulations_dense_1536
+MILVUS_COLLECTION=regulations_dense_1024_v1
 MILVUS_DB_NAME=default
 
 # ===== MinIO对象存储配置（已有）=====
@@ -34,7 +34,7 @@ POSTGRES_DB=compliance_db
 
 # ===== 嵌入模型配置 =====
 EMBEDDING_MODEL=text-embedding-v3
-EMBEDDING_DIM=1536
+EMBEDDING_DIM=1024
 EMBEDDING_API_KEY=sk-fVr9KmDZNC4pGDBQj0EUWz9bDmFzNxjYC9EzZpe2bVDsxtz8
 EMBEDDING_BASE_URL=http://6.86.80.4:30080/v1
 EMBEDDING_TIMEOUT_SECONDS=120
@@ -59,7 +59,7 @@ LLM_TEMPERATURE=0.7
 # 获取API Key: https://dashscope.console.aliyun.com/
 QWEN_API_KEY=sk-fVr9KmDZNC4pGDBQj0EUWz9bDmFzNxjYC9EzZpe2bVDsxtz8
 QWEN_BASE_URL=http://6.86.80.4:30080/v1
-QWEN_MODEL=qwen3.5-plus
+QWEN_MODEL=qwen3.6-plus
 QWEN_VL_MODEL=qwen3-vl-plus
 
 # ===== DeepSeek API配置 =====
@@ -73,3 +73,15 @@ RAG_TOP_K=10
 RAG_MAX_CONTEXT_TOKENS=4000
 RAG_SUMMARY_MAX_TOKENS=1024
 RAG_SKILLS_MAX_TOKENS=2048
+
+# ===== 阿里云文档解析 =====
+ALIBABA_ACCESS_KEY_ID=LTAI5t9ZjvwSU9bKuMyiExrE
+ALIBABA_ACCESS_KEY_SECRET=hNvY6XocmEO6inYlrmiBwBcx5OfidL
+ALIBABA_ENDPOINT=docmind-api.cn-hangzhou.aliyuncs.com
+ALIYUN_PARSE_POLL_INTERVAL_SECONDS=5
+ALIYUN_PARSE_TIMEOUT_SECONDS=900
+ALIYUN_PARSE_LAYOUT_STEP_SIZE=50
+ALIYUN_LLM_ENHANCEMENT=true
+ALIYUN_ENHANCEMENT_MODE=VLM
+DOCUMENT_PARSE_ARTIFACT_PREFIX=artifacts
+PARSER_FAILURE_MODE=fail