perf: trying to improve perf

server/app.py

@@ -1,6 +1,7 @@
 #!/usr/bin python3
 
 import argparse
+import time
 from flask import Flask, jsonify, request
 
 from sources.llamacpp_handler import LlamacppLLM
@@ -36,16 +37,6 @@ def setup():
     generator.set_model(model)
     return jsonify({"message": "Model set"}), 200
 
-@app.route('/get_complete_sentence', methods=['GET'])
-def get_complete_sentence():
-    if not generator:
-        return jsonify({"error": "Generator not initialized"}), 404
-    while True:
-        status = generator.get_status()
-        if status["is_complete"]:
-            return jsonify(status)
-    return None
-
 @app.route('/get_updated_sentence')
 def get_updated_sentence():
     if not generator:

server/requirements.txt

@@ -1,3 +1,4 @@
 flask>=2.3.0
 ollama>=0.4.7
+gunicorn==19.10.0
 llama-cpp-python

sources/llm_provider.py

@@ -120,7 +120,7 @@ class Provider:
             requests.post(route_gen, json={"messages": history})
             is_complete = False
             while not is_complete:
-                response = requests.get(f"http://{self.server_ip}/get_complete_sentence")
+                response = requests.get(f"http://{self.server_ip}/get_updated_sentence")
                 if "error" in response.json():
                     pretty_print(response.json()["error"], color="failure")
                     break