o1 (has vision) and o3-mini (no vision)

computer_use_demo/gradio/agent/llm_utils/oaiclient.py

@@ -7,7 +7,6 @@ from .utils import is_image_path, encode_image
 def run_oai_interleaved(messages: list, system: str, model_name: str, api_key: str, max_tokens=256, temperature=0, provider_base_url: str = "https://api.openai.com/v1"):    
     headers = {"Content-Type": "application/json",
                "Authorization": f"Bearer {api_key}"}
-
     final_messages = [{"role": "system", "content": system}]
 
     if type(messages) == list:
@@ -16,7 +15,8 @@ def run_oai_interleaved(messages: list, system: str, model_name: str, api_key: s
             if isinstance(item, dict):
                 for cnt in item["content"]:
                     if isinstance(cnt, str):
-                        if is_image_path(cnt):
+                        if is_image_path(cnt) and 'o3-mini' not in model_name:
+                            # 03 mini does not support images
                             base64_image = encode_image(cnt)
                             content = {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"}}
                         else:
@@ -41,9 +41,12 @@ def run_oai_interleaved(messages: list, system: str, model_name: str, api_key: s
     payload = {
         "model": model_name,
         "messages": final_messages,
-        "max_tokens": max_tokens,
-        "temperature": temperature
     }
+    if 'o1' in model_name or 'o3-mini' in model_name:
+        payload['reasoning_effort'] = 'low'
+        payload['max_completion_tokens'] = max_tokens
+    else:
+        payload['max_tokens'] = max_tokens
 
     response = requests.post(
         f"{provider_base_url}/chat/completions", headers=headers, json=payload