diff --git a/README.md b/README.md
index 61876dc..bde9e5e 100644
--- a/README.md
+++ b/README.md
@@ -218,14 +218,28 @@ Note: For Windows or macOS, use ipconfig or ifconfig respectively to find the IP
 
 **If you wish to use openai based provider follow the *Run with an API*  section.**
 
-Make sure ollama is installed (Currently our script only support ollama)
+Clone the repository and enter the `server/`folder.
 
-Run our server script.
 
 ```sh
-python3 server_ollama.py --model "deepseek-r1:32b"
+git clone --depth 1 https://github.com/Fosowl/agenticSeek.git
+cd agenticSeek/server/
 ```
 
+Install server specific requirements:
+
+```sh
+pip3 install -r requirements.txt
+```
+
+Run the server script.
+
+```sh
+python3 app.py --provider ollama --port 3333
+```
+
+You have the choice between using `ollama` and `llamacpp` as a LLM service.
+
 ### 2️⃣ **Run it** 
 
 Now on your personal computer:
@@ -238,7 +252,7 @@ Set the `provider_server_address` to the ip address of the machine that will run
 is_local = False
 provider_name = server
 provider_model = deepseek-r1:14b
-provider_server_address = x.x.x.x:5000
+provider_server_address = x.x.x.x:3333
 ```
 
 Run the assistant:
diff --git a/server/app.py b/server/app.py
index aa8d89a..242c576 100644
--- a/server/app.py
+++ b/server/app.py
@@ -1,15 +1,11 @@
 #!/usr/bin python3
 
-import logging
 import argparse
 from flask import Flask, jsonify, request
 
 from sources.llamacpp import LlamacppLLM
 from sources.ollama import OllamaLLM
 
-log = logging.getLogger('werkzeug')
-log.setLevel(logging.ERROR)
-
 parser = argparse.ArgumentParser(description='AgenticSeek server script')
 parser.add_argument('--provider', type=str, help='LLM backend library to use. set to [ollama] or [llamacpp]', required=True)
 parser.add_argument('--port', type=int, help='port to use', required=True)
diff --git a/server/sources/generator.py b/server/sources/generator.py
index 0c70f06..5753ee0 100644
--- a/server/sources/generator.py
+++ b/server/sources/generator.py
@@ -24,6 +24,12 @@ class GeneratorLLM():
         self.model = None
         self.state = GenerationState()
         self.logger = logging.getLogger(__name__)
+        handler = logging.StreamHandler()
+        handler.setLevel(logging.INFO)
+        formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
+        handler.setFormatter(formatter)
+        self.logger.addHandler(handler)
+        self.logger.setLevel(logging.INFO)
     
     def set_model(self, model: str) -> None:
         self.logger.info(f"Model set to {model}")
diff --git a/server/sources/ollama.py b/server/sources/ollama.py
index 8cd7631..7450017 100644
--- a/server/sources/ollama.py
+++ b/server/sources/ollama.py
@@ -1,10 +1,10 @@
 
 from .generator import GeneratorLLM
+import ollama
 
 class OllamaLLM(GeneratorLLM):
 
     def __init__(self):
-        import ollama
         """
         Handle generation using Ollama.
         """
diff --git a/sources/llm_provider.py b/sources/llm_provider.py
index c8f7f88..51657ba 100644
--- a/sources/llm_provider.py
+++ b/sources/llm_provider.py
@@ -116,11 +116,13 @@ class Provider:
         try:
             requests.post(route_setup, json={"model": self.model})
             pretty_print("Setting up server...", color="status")
-            time.sleep(5)
             requests.post(route_gen, json={"messages": history})
             is_complete = False
             while not is_complete:
                 response = requests.get(f"http://{self.server_ip}/get_updated_sentence")
+                print("raw response", response.json())
+                if "error" in response.json():
+                    continue
                 thought = response.json()["sentence"]
                 is_complete = bool(response.json()["is_complete"])
                 time.sleep(2)