From 62c774bf24d35a1ebdcdb9927f8a6c6ae3949c82 Mon Sep 17 00:00:00 2001
From: oobabooga <112222186+oobabooga@users.noreply.github.com>
Date: Tue, 13 May 2025 06:42:25 -0700
Subject: [PATCH] Revert "New attempt"

This reverts commit e7ac06c1694024594450437f3b899e32ab2ce6e4.
---
 modules/llama_cpp_server.py | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/modules/llama_cpp_server.py b/modules/llama_cpp_server.py
index 615f29ad..1046969a 100644
--- a/modules/llama_cpp_server.py
+++ b/modules/llama_cpp_server.py
@@ -146,9 +146,8 @@ class LlamaServer:
             pprint.PrettyPrinter(indent=4, sort_dicts=False).pprint(printable_payload)
             print()
 
-        # Make a request with streaming enabled
-        response = self.session.post(url, json=payload, stream=True)
-        try:
+        # Make a direct request with streaming enabled using a context manager
+        with self.session.post(url, json=payload, stream=True) as response:
             response.raise_for_status()  # Raise an exception for HTTP errors
 
             full_text = ""
@@ -186,9 +185,6 @@ class LlamaServer:
                     print(f"Problematic line: {line}")
                     continue
 
-        finally:
-            response.close()
-
     def generate(self, prompt, state):
         output = ""
         for output in self.generate_with_streaming(prompt, state):