From 457d51952e608de0eadc7df2cdcda7542be1fb85 Mon Sep 17 00:00:00 2001
From: yangdx <gzdaniel@me.com>
Date: Sun, 5 Oct 2025 11:44:27 +0800
Subject: [PATCH] Add doc_name field to full docs storage

- Store file_path in full_docs storage
- Update PostgreSQL implementation by map file_path to doc_name
- Other storage implementation automatically handles the new field
---
 lightrag/kg/postgres_impl.py | 15 ++++++++++-----
 lightrag/lightrag.py         |  7 +++++--
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/lightrag/kg/postgres_impl.py b/lightrag/kg/postgres_impl.py
index ad271b15..f22674c0 100644
--- a/lightrag/kg/postgres_impl.py
+++ b/lightrag/kg/postgres_impl.py
@@ -1750,6 +1750,7 @@ class PGKVStorage(BaseKVStorage):
                 _data = {
                     "id": k,
                     "content": v["content"],
+                    "doc_name": v.get("file_path", ""),  # Map file_path to doc_name
                     "workspace": self.workspace,
                 }
                 await self.db.execute(upsert_sql, _data)
@@ -4588,7 +4589,8 @@ TABLES = {
 
 SQL_TEMPLATES = {
     # SQL for KVStorage
-    "get_by_id_full_docs": """SELECT id, COALESCE(content, '') as content
+    "get_by_id_full_docs": """SELECT id, COALESCE(content, '') as content,
+                                COALESCE(doc_name, '') as file_path
                                 FROM LIGHTRAG_DOC_FULL WHERE workspace=$1 AND id=$2
                             """,
     "get_by_id_text_chunks": """SELECT id, tokens, COALESCE(content, '') as content,
@@ -4603,7 +4605,8 @@ SQL_TEMPLATES = {
                                 EXTRACT(EPOCH FROM update_time)::BIGINT as update_time
                                 FROM LIGHTRAG_LLM_CACHE WHERE workspace=$1 AND id=$2
                                """,
-    "get_by_ids_full_docs": """SELECT id, COALESCE(content, '') as content
+    "get_by_ids_full_docs": """SELECT id, COALESCE(content, '') as content,
+                                 COALESCE(doc_name, '') as file_path
                                  FROM LIGHTRAG_DOC_FULL WHERE workspace=$1 AND id IN ({ids})
                             """,
     "get_by_ids_text_chunks": """SELECT id, tokens, COALESCE(content, '') as content,
@@ -4639,10 +4642,12 @@ SQL_TEMPLATES = {
                                  FROM LIGHTRAG_FULL_RELATIONS WHERE workspace=$1 AND id IN ({ids})
                                 """,
     "filter_keys": "SELECT id FROM {table_name} WHERE workspace=$1 AND id IN ({ids})",
-    "upsert_doc_full": """INSERT INTO LIGHTRAG_DOC_FULL (id, content, workspace)
-                        VALUES ($1, $2, $3)
+    "upsert_doc_full": """INSERT INTO LIGHTRAG_DOC_FULL (id, content, doc_name, workspace)
+                        VALUES ($1, $2, $3, $4)
                         ON CONFLICT (workspace,id) DO UPDATE
-                           SET content = $2, update_time = CURRENT_TIMESTAMP
+                           SET content = $2,
+                               doc_name = $3,
+                               update_time = CURRENT_TIMESTAMP
                        """,
     "upsert_llm_response_cache": """INSERT INTO LIGHTRAG_LLM_CACHE(workspace,id,original_prompt,return_value,chunk_id,cache_type,queryparam)
                                       VALUES ($1, $2, $3, $4, $5, $6, $7)
diff --git a/lightrag/lightrag.py b/lightrag/lightrag.py
index 60c296ac..b4345405 100644
--- a/lightrag/lightrag.py
+++ b/lightrag/lightrag.py
@@ -961,7 +961,7 @@ class LightRAG:
                 doc_key = compute_mdhash_id(full_text, prefix="doc-")
             else:
                 doc_key = doc_id
-            new_docs = {doc_key: {"content": full_text}}
+            new_docs = {doc_key: {"content": full_text, "file_path": file_path}}
 
             _add_doc_keys = await self.full_docs.filter_keys({doc_key})
             new_docs = {k: v for k, v in new_docs.items() if k in _add_doc_keys}
@@ -1139,7 +1139,10 @@ class LightRAG:
         # 4. Store document content in full_docs and status in doc_status
         #    Store full document content separately
         full_docs_data = {
-            doc_id: {"content": contents[doc_id]["content"]}
+            doc_id: {
+                "content": contents[doc_id]["content"],
+                "file_path": contents[doc_id]["file_path"],
+            }
             for doc_id in new_docs.keys()
         }
         await self.full_docs.upsert(full_docs_data)