Refactor document handling and update Milvus collection settings

- Removed multiple failed document entries from `documents.json`.
- Added a new document entry with updated metadata and changed the index name to `regulations_dense_1024_v2`.
- Updated architecture documentation to reflect changes in the Milvus collection name.
- Adjusted requirements by removing the sqlalchemy dependency.
- Modified test cases to align with new document structure and naming conventions.
- Introduced a new test file for Milvus vector index runtime recovery and error handling.
- Updated assertions in various test files to ensure compatibility with the new schema.

tests/test_milvus.py

@@ -18,11 +18,11 @@ class FakeRetriever:
             RetrievedChunk(
                 chunk_id="chunk-1",
                 doc_id="doc-1",
-                doc_name="测试法规",
-                content="法规正文",
+                doc_title="测试法规",
+                text="法规正文",
                 score=0.91,
                 section_title="第一章",
-                page_number=1,
+                page_start=1,
                 metadata={"section_title": "第一章"},
             )
         ]
@@ -47,12 +47,12 @@ class FakeAnswerGenerator:
             sources=[
                 AnswerSource(
                     doc_id=item.doc_id,
-                    doc_name=item.doc_name,
+                    doc_title=item.doc_title,
                     chunk_id=item.chunk_id,
                     section_title=item.section_title,
-                    page_number=item.page_number,
+                    page_start=item.page_start,
                     score=item.score,
-                    content=item.content,
+                    text=item.text,
                     metadata=item.metadata,
                 )
                 for item in retrieved_chunks