diff --git a/server/README.md b/server/README.md
index c3004bcb..a70fb7e7 100644
--- a/server/README.md
+++ b/server/README.md
@@ -33,15 +33,21 @@ Then run the server:
 
 ```
 # With a config.ini
-$ poetry run python -m reflector.server
+$ poetry run python -m reflector.app
 
 
 # Within a poetry env
 $ poetry shell
-$ LLM_URL=http://.../api/v1/generate python -m reflector.server
+$ LLM_URL=http://.../api/v1/generate python -m reflector.app
 
 ```
 
+### Using local GPT4All
+
+- Start GPT4All with any model you want
+- Ensure the API server is activated in GPT4all
+- Run with: `LLM_BACKEND=openai LLM_URL=http://localhost:4891/v1/completions LLM_OPENAI_MODEL="GPT4All Falcon" python -m reflector.app`
+
 # Old documentation
 
 This is the code base for the Reflector demo (formerly called agenda-talk-diff) for the leads : Troy Web Consulting
diff --git a/server/reflector/app.py b/server/reflector/app.py
index f40af489..4a10b685 100644
--- a/server/reflector/app.py
+++ b/server/reflector/app.py
@@ -26,3 +26,7 @@ app.add_middleware(
 
 # register views
 app.include_router(rtc_offer_router)
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run("reflector.app:app", host="0.0.0.0", port=1250, reload=True)