Use 5562 as default port to avoid conflicting common 8000 port

Author: rogeriochaves

README.md

@@ -24,7 +24,7 @@ Then right away you can start LangEvals as a server with:
 langevals-server
 ```
 
-And navigate to `http://localhost:8000/` to try out the evaluators.
+And navigate to `http://localhost:5562/` to try out the evaluators.
 
 Alternatively, you can use it as a library as the examples below show.
 

langevals/server.py

@@ -143,7 +143,7 @@ def main():
     import gunicorn.app.base
 
     host = "0.0.0.0"
-    port = int(os.getenv("PORT", 8000))
+    port = int(os.getenv("PORT", 5562))
     workers = get_cpu_count()
 
     class StandaloneApplication(gunicorn.app.base.BaseApplication):