diff --git a/llama_hub/llama_packs/rag_cli_local/README.md b/llama_hub/llama_packs/rag_cli_local/README.md
index c45ee2ab64..e567a4a028 100644
--- a/llama_hub/llama_packs/rag_cli_local/README.md
+++ b/llama_hub/llama_packs/rag_cli_local/README.md
@@ -25,14 +25,22 @@ from llama_index.llama_pack import download_llama_pack
 
 # download and install dependencies
 download_llama_pack(
-  "LocalRAGCLIPack", "./local_rag_cli_pack"
+  "LocalRAGCLIPack", "./local_rag_cli_pack", skip_load=True
 )
 ```
 
-From here, you can use the pack. The most straightforward way is through the CLI.
+From here, you can use the pack. The most straightforward way is through the CLI. You can directly run base.py, or run the `setup_cli.sh` script.
 
-```python
-TODO
+```bash
+cd local_rag_cli_pack
+
+# option 1
+python base.py rag -h
+
+# option 2 - you may need sudo
+# default name is lcli_local
+sudo sh setup_cli.sh
+lcli_local rag -h
 
 ```
 
diff --git a/llama_hub/llama_packs/rag_cli_local/base.py b/llama_hub/llama_packs/rag_cli_local/base.py
index 566884a9a7..0c862a6eea 100644
--- a/llama_hub/llama_packs/rag_cli_local/base.py
+++ b/llama_hub/llama_packs/rag_cli_local/base.py
@@ -42,7 +42,7 @@ def init_local_rag_cli(
     llm = Ollama(model=llm_model_name, request_timeout=30.0)
     print("> LLM initialized")
     embed_model = HuggingFaceEmbedding(model_name=embed_model_name)
-    print('> Embedding model initialized')
+    print("> Embedding model initialized")
 
     ingestion_pipeline = IngestionPipeline(
         transformations=[SentenceSplitter(), embed_model],
@@ -76,7 +76,7 @@ def init_local_rag_cli(
         llm=llm,  # optional
         persist_dir=persist_dir,
         query_pipeline=query_pipeline,
-        verbose=False
+        verbose=False,
     )
     return rag_cli_instance
 
@@ -97,10 +97,10 @@ def __init__(
         self.llm_model_name = llm_model_name
         self.embed_model_name = embed_model_name
         self.rag_cli = init_local_rag_cli(
-            persist_dir=self.persist_dir, 
+            persist_dir=self.persist_dir,
             verbose=self.verbose,
             llm_model_name=self.llm_model_name,
-            embed_model_name=self.embed_model_name
+            embed_model_name=self.embed_model_name,
         )
 
     def get_modules(self) -> Dict[str, Any]:
@@ -114,4 +114,4 @@ def run(self, *args: Any, **kwargs: Any) -> Any:
 
 if __name__ == "__main__":
     rag_cli_instance = init_local_rag_cli()
-    rag_cli_instance.cli()
\ No newline at end of file
+    rag_cli_instance.cli()
diff --git a/pyproject.toml b/pyproject.toml
index 6f2e657d42..f4852224b7 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -16,7 +16,7 @@ include = [
 [tool.poetry.dependencies]
 # Updated Python version
 python = ">=3.8.1,<3.12"
-llama-index = ">=0.9.39"
+llama-index = ">=0.9.41"
 html2text = "*"
 psutil = "*"
 retrying = "*"