YueHuihui
/
RAGflow
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

fix:适配新版本task的表结构，解决Unknown column 'priority'in 'field list' 报错信息

This commit is contained in:
zstar 2025-06-05 11:34:45 +08:00
parent 1fbb0d58c0
commit 8cfc4bba4c
1 changed files with 37 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

48
management/server/services/knowledgebases/document_parser.py
View File

@ -123,12 +123,17 @@ def _update_kb_chunk_count(kb_id, count_delta):
def _create_task_record(doc_id, chunk_ids_list): def _create_task_record(doc_id, chunk_ids_list):
"""创建task记录""" """创建task记录，兼容无 priority 字段的新表结构"""
conn = None conn = None
cursor = None cursor = None
try: try:
conn = get_db_connection() conn = get_db_connection()
cursor = conn.cursor() cursor = conn.cursor()
# 检查 task 表中是否有 priority 字段
cursor.execute("SHOW COLUMNS FROM task LIKE 'priority'")
has_priority = cursor.fetchone() is not None
task_id = generate_uuid() task_id = generate_uuid()
current_datetime = datetime.now() current_datetime = datetime.now()
current_timestamp = int(current_datetime.timestamp() * 1000) current_timestamp = int(current_datetime.timestamp() * 1000)
@ -136,17 +141,38 @@ def _create_task_record(doc_id, chunk_ids_list):
digest = f"{doc_id}_{0}_{1}" # 假设 from_page=0, to_page=1 digest = f"{doc_id}_{0}_{1}" # 假设 from_page=0, to_page=1
chunk_ids_str = " ".join(chunk_ids_list) chunk_ids_str = " ".join(chunk_ids_list)
task_insert = """ common_fields = [
INSERT INTO task ( "id",
id, create_time, create_date, update_time, update_date, "create_time",
doc_id, from_page, to_page, begin_at, process_duation, "create_date",
progress, progress_msg, retry_count, digest, chunk_ids, task_type, priority "update_time",
) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s) "update_date",
""" "doc_id",
task_params = [task_id, current_timestamp, current_date_only, current_timestamp, current_date_only, doc_id, 0, 1, None, 0.0, 1.0, "MinerU解析完成", 1, digest, chunk_ids_str, "", 0] "from_page",
cursor.execute(task_insert, task_params) "to_page",
"begin_at",
"process_duation",
"progress",
"progress_msg",
"retry_count",
"digest",
"chunk_ids",
"task_type",
]
common_values = [task_id, current_timestamp, current_date_only, current_timestamp, current_date_only, doc_id, 0, 1, None, 0.0, 1.0, "MinerU解析完成", 1, digest, chunk_ids_str, ""]
if has_priority:
common_fields.append("priority")
common_values.append(0)
fields_sql = ", ".join(common_fields)
placeholders = ", ".join(["%s"] * len(common_values))
task_insert = f"INSERT INTO task ({fields_sql}) VALUES ({placeholders})"
cursor.execute(task_insert, common_values)
conn.commit() conn.commit()
print(f"[Parser-INFO] Task记录创建成功，Task ID: {task_id}") print(f"[Parser-INFO] Task记录创建成功，Task ID: {task_id}")
except Exception as e: except Exception as e:
print(f"[Parser-ERROR] 创建Task记录失败: {e}") print(f"[Parser-ERROR] 创建Task记录失败: {e}")
finally: finally:
@ -284,7 +310,7 @@ def perform_parse(doc_id, doc_info, file_info, embedding_config, kb_info):
update_progress(0.3, "分析PDF类型") update_progress(0.3, "分析PDF类型")
is_ocr = ds.classify() == SupportedPdfParseMethod.OCR is_ocr = ds.classify() == SupportedPdfParseMethod.OCR
mode_msg = "OCR模式" if is_ocr else "文本模式" mode_msg = "OCR模式" if is_ocr else "文本模式"
update_progress(0.4, f"使用{mode_msg}处理PDF，处理中，具体进度可查看日志") update_progress(0.4, f"使用{mode_msg}处理PDF，处理中，具体进度可查看容器日志")
infer_result = ds.apply(doc_analyze, ocr=is_ocr) infer_result = ds.apply(doc_analyze, ocr=is_ocr)