gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix mismatch of 'error' and 'error_msg' in MongoDB

Browse source
This commit is contained in:
LinkinPony 2025-08-26 10:43:56 +08:00
parent 31f4f96944
commit ff4c747a2a
1 changed files with 27 additions and 42 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

69
lightrag/kg/mongo_impl.py
View file

@ -280,6 +280,30 @@ class MongoDocStatusStorage(DocStatusStorage):
db: AsyncDatabase = field(default=None) db: AsyncDatabase = field(default=None)
_data: AsyncCollection = field(default=None) _data: AsyncCollection = field(default=None)
def _prepare_doc_status_data(self, doc: dict[str, Any]) -> dict[str, Any]:
"""Normalize and migrate a raw Mongo document to DocProcessingStatus-compatible dict."""
# Make a copy of the data to avoid modifying the original
data = doc.copy()
# Remove deprecated content field if it exists
data.pop("content", None)
# Remove MongoDB _id field if it exists
data.pop("_id", None)
# If file_path is not in data, use document id as file path
if "file_path" not in data:
data["file_path"] = "no-file-path"
# Ensure new fields exist with default values
if "metadata" not in data:
data["metadata"] = {}
if "error_msg" not in data:
data["error_msg"] = None
# Backward compatibility: migrate legacy 'error' field to 'error_msg'
if "error" in data:
if "error_msg" not in data or data["error_msg"] in (None, ""):
data["error_msg"] = data.pop("error")
else:
data.pop("error", None)
return data
def __init__(self, namespace, global_config, embedding_func, workspace=None): def __init__(self, namespace, global_config, embedding_func, workspace=None):
super().__init__( super().__init__(
namespace=namespace, namespace=namespace,
@ -389,20 +413,7 @@ class MongoDocStatusStorage(DocStatusStorage):
processed_result = {} processed_result = {}
for doc in result: for doc in result:
try: try:
# Make a copy of the data to avoid modifying the original data = self._prepare_doc_status_data(doc)
data = doc.copy()
# Remove deprecated content field if it exists
data.pop("content", None)
# Remove MongoDB _id field if it exists
data.pop("_id", None)
# If file_path is not in data, use document id as file path
if "file_path" not in data:
data["file_path"] = "no-file-path"
# Ensure new fields exist with default values
if "metadata" not in data:
data["metadata"] = {}
if "error_msg" not in data:
data["error_msg"] = None
processed_result[doc["_id"]] = DocProcessingStatus(**data) processed_result[doc["_id"]] = DocProcessingStatus(**data)
except KeyError as e: except KeyError as e:
logger.error( logger.error(
@ -420,20 +431,7 @@ class MongoDocStatusStorage(DocStatusStorage):
processed_result = {} processed_result = {}
for doc in result: for doc in result:
try: try:
# Make a copy of the data to avoid modifying the original data = self._prepare_doc_status_data(doc)
data = doc.copy()
# Remove deprecated content field if it exists
data.pop("content", None)
# Remove MongoDB _id field if it exists
data.pop("_id", None)
# If file_path is not in data, use document id as file path
if "file_path" not in data:
data["file_path"] = "no-file-path"
# Ensure new fields exist with default values
if "metadata" not in data:
data["metadata"] = {}
if "error_msg" not in data:
data["error_msg"] = None
processed_result[doc["_id"]] = DocProcessingStatus(**data) processed_result[doc["_id"]] = DocProcessingStatus(**data)
except KeyError as e: except KeyError as e:
logger.error( logger.error(
@ -661,20 +659,7 @@ class MongoDocStatusStorage(DocStatusStorage):
try: try:
doc_id = doc["_id"] doc_id = doc["_id"]
# Make a copy of the data to avoid modifying the original data = self._prepare_doc_status_data(doc)
data = doc.copy()
# Remove deprecated content field if it exists
data.pop("content", None)
# Remove MongoDB _id field if it exists
data.pop("_id", None)
# If file_path is not in data, use document id as file path
if "file_path" not in data:
data["file_path"] = "no-file-path"
# Ensure new fields exist with default values
if "metadata" not in data:
data["metadata"] = {}
if "error_msg" not in data:
data["error_msg"] = None
doc_status = DocProcessingStatus(**data) doc_status = DocProcessingStatus(**data)
documents.append((doc_id, doc_status)) documents.append((doc_id, doc_status))