From 75de7993531cb5f55d8532143e630dc265ba5ebd Mon Sep 17 00:00:00 2001
From: yangdx <gzdaniel@me.com>
Date: Wed, 30 Jul 2025 01:00:06 +0800
Subject: [PATCH] Remove deprecated content field from doc status storage

- Remove content field from JSON storage
- Remove content field from MongoDB storage
- Remove content field from Redis storage
---
 lightrag/kg/json_doc_status_impl.py | 4 ++++
 lightrag/kg/mongo_impl.py           | 4 ++++
 lightrag/kg/redis_impl.py           | 4 ++++
 3 files changed, 12 insertions(+)

diff --git a/lightrag/kg/json_doc_status_impl.py b/lightrag/kg/json_doc_status_impl.py
index aecb8713..404dc260 100644
--- a/lightrag/kg/json_doc_status_impl.py
+++ b/lightrag/kg/json_doc_status_impl.py
@@ -95,6 +95,8 @@ class JsonDocStatusStorage(DocStatusStorage):
                     try:
                         # Make a copy of the data to avoid modifying the original
                         data = v.copy()
+                        # Remove deprecated content field if it exists
+                        data.pop("content", 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"
@@ -120,6 +122,8 @@ class JsonDocStatusStorage(DocStatusStorage):
                     try:
                         # Make a copy of the data to avoid modifying the original
                         data = v.copy()
+                        # Remove deprecated content field if it exists
+                        data.pop("content", 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"
diff --git a/lightrag/kg/mongo_impl.py b/lightrag/kg/mongo_impl.py
index f15576a9..1f9ce5e1 100644
--- a/lightrag/kg/mongo_impl.py
+++ b/lightrag/kg/mongo_impl.py
@@ -381,6 +381,8 @@ class MongoDocStatusStorage(DocStatusStorage):
             try:
                 # 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)
                 # 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"
@@ -406,6 +408,8 @@ class MongoDocStatusStorage(DocStatusStorage):
             try:
                 # 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)
                 # 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"
diff --git a/lightrag/kg/redis_impl.py b/lightrag/kg/redis_impl.py
index e5a59c80..536f1a85 100644
--- a/lightrag/kg/redis_impl.py
+++ b/lightrag/kg/redis_impl.py
@@ -786,6 +786,8 @@ class RedisDocStatusStorage(DocStatusStorage):
 
                                         # Make a copy of the data to avoid modifying the original
                                         data = doc_data.copy()
+                                        # Remove deprecated content field if it exists
+                                        data.pop("content", 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"
@@ -840,6 +842,8 @@ class RedisDocStatusStorage(DocStatusStorage):
 
                                         # Make a copy of the data to avoid modifying the original
                                         data = doc_data.copy()
+                                        # Remove deprecated content field if it exists
+                                        data.pop("content", 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"