fix: server script

README.md

@@ -212,6 +212,8 @@ If you have a powerful computer or a server that you can use, but you want to us
 
 ### 1️⃣  **Set up and start the server scripts** 
 
+You need to have ollama installed on the server (We will integrate VLLM and llama.cpp soon).
+
 On your "server" that will run the AI model, get the ip address
 
 ```sh
@@ -223,7 +225,7 @@ Note: For Windows or macOS, use ipconfig or ifconfig respectively to find the IP
 Clone the repository and then, run the script `stream_llm.py` in `server/`
 
 ```sh
-python3 server_ollama.py
+python3 server_ollama.py --model "deepseek-r1:32b"
 ```
 
 ### 2️⃣ **Run it** 

server/config.json

@@ -1,30 +0,0 @@
-{
-    "model_name": "deepseek-r1:14b",
-    "known_models": [
-        "qwq:32b",
-        "deepseek-r1:1.5b",
-        "deepseek-r1:7b",
-        "deepseek-r1:14b",
-        "deepseek-r1:32b",
-        "deepseek-r1:70b",
-        "deepseek-r1:671b",
-        "deepseek-coder:1.3b",
-        "deepseek-coder:6.7b",
-        "deepseek-coder:33b",
-        "llama2-uncensored:7b",
-        "llama2-uncensored:70b",
-        "llama3.1:8b",
-        "llama3.1:70b",
-        "llama3.3:70b",
-        "llama3:8b",
-        "llama3:70b",
-        "i4:14b",
-        "mistral:7b",
-        "mistral:70b",
-        "mistral:33b",
-        "qwen1:7b",
-        "qwen1:14b",
-        "qwen1:32b",
-        "qwen1:70b"
-    ]
-}

server/server_ollama.py

@@ -6,13 +6,18 @@ from flask import Flask, jsonify, request
 import threading
 import ollama
 import logging
+import argparse
 
 log = logging.getLogger('werkzeug')
 log.setLevel(logging.ERROR)
 
+parser = argparse.ArgumentParser(description='AgenticSeek server script')
+parser.add_argument('--model', type=str, help='Model to use. eg: deepseek-r1:14b', required=True)
+args = parser.parse_args()
+
 app = Flask(__name__)
 
-model = 'deepseek-r1:14b'
+model = args.model
 
 # Shared state with thread-safe locks
 class GenerationState: