diff --git a/README-zh.md b/README-zh.md
index 12ab7b62..6aab2a43 100644
--- a/README-zh.md
+++ b/README-zh.md
@@ -749,6 +749,7 @@ async def embedding_func(texts: list[str]) -> np.ndarray:
 rag = LightRAG(
     working_dir=WORKING_DIR,
     llm_model_func=llm_model_func,
+    llm_model_name="gemini-2.0-flash",
     embedding_func=embedding_func
 )
 ```
@@ -972,7 +973,7 @@ async def initialize_rag():
 
 * PostgreSQL 很轻量，包含所有必要插件的完整二进制发行版可以压缩到 40MB：参考 [Windows Release](https://github.com/ShanGor/apache-age-windows/releases/tag/PG17%2Fv1.5.0-rc0)，Linux/Mac 也很容易安装。
 * 如果您喜欢 docker，建议初学者使用此镜像以避免出现问题（默认用户密码：rag/rag）：https://hub.docker.com/r/gzdaniel/postgres-for-rag
-* 如何开始？参考：[examples/lightrag_zhipu_postgres_demo.py](https://github.com/HKUDS/LightRAG/blob/main/examples/lightrag_zhipu_postgres_demo.py)
+* 如何开始？参考：[examples/lightrag_gemini_postgres_demo.py](https://github.com/HKUDS/LightRAG/blob/main/examples/lightrag_gemini_postgres_demo.py)
 * 对于高性能图数据库需求，推荐使用 Neo4j，因为 Apache AGE 的性能不够理想。
 
 </details>
diff --git a/README.md b/README.md
index c10c6927..1674865b 100644
--- a/README.md
+++ b/README.md
@@ -973,7 +973,7 @@ For production level scenarios you will most likely want to leverage an enterpri
 
 * PostgreSQL is lightweight,the whole binary distribution including all necessary plugins can be zipped to 40MB: Ref to [Windows Release](https://github.com/ShanGor/apache-age-windows/releases/tag/PG17%2Fv1.5.0-rc0) as it is easy to install for Linux/Mac.
 * If you prefer docker, please start with this image if you are a beginner to avoid hiccups (Default user password:rag/rag): https://hub.docker.com/r/gzdaniel/postgres-for-rag
-* How to start? Ref to: [examples/lightrag_zhipu_postgres_demo.py](https://github.com/HKUDS/LightRAG/blob/main/examples/lightrag_zhipu_postgres_demo.py)
+* How to start? Ref to: [examples/lightrag_gemini_postgres_demo.py](https://github.com/HKUDS/LightRAG/blob/main/examples/lightrag_gemini_postgres_demo.py)
 * For high-performance graph database requirements, Neo4j is recommended as Apache AGE's performance is not as competitive.
 
 </details>