Switched to OpenRouter meta-llama/llama-4-scout:free

app.py

@@ -4,6 +4,7 @@ import requests
 import inspect
 import pandas as pd
 from huggingface_hub import InferenceClient  # Import Hugging Face InferenceClient
+from openai import OpenAI
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -18,7 +19,8 @@ class BasicAgent:
         print("BasicAgent initialized.")
 
         print("Loading huggingface default model...")
-        self.client = InferenceClient(model="mistralai/Mistral-7B-Instruct-v0.3", token=os.getenv("HF_TOKEN"))
+        # self.client = InferenceClient(model="mistralai/Mistral-7B-Instruct-v0.3", token=os.getenv("HF_TOKEN"))
+        self.client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=os.getenv("OR_TOKEN"))
 
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
@@ -26,9 +28,35 @@ class BasicAgent:
         try:
             # Generate response
             print("Using Inference API for generation...")
-            prompt = f"""<s>[INST] Answer the following question directly without any explanations, introductions, or conclusions. Just provide the answer itself: {question} [/INST]</s>"""
-            response = self.client.text_generation(prompt, max_new_tokens=512, do_sample=True, temperature=0.1)
-            answer = response
+            # prompt = f"""<s>[INST] Answer the following question directly without any explanations, introductions, or conclusions. Just provide the answer itself: {question} [/INST]</s>"""
+            # response = self.client.text_generation(prompt, max_new_tokens=512, do_sample=True, temperature=0.1)
+            # answer = response
+            completion = self.client.chat.completions.create(
+                extra_headers={
+                    "HTTP-Referer": "<YOUR_SITE_URL>",  # Optional. Site URL for rankings on openrouter.ai.
+                    "X-Title": "<YOUR_SITE_NAME>",  # Optional. Site title for rankings on openrouter.ai.
+                },
+                extra_body={},
+                model="meta-llama/llama-4-scout:free",
+                messages=[
+                    {
+                        "role": "user",
+                        "content": [
+                            {
+                                "type": "text",
+                                "text": question
+                            },
+                            # {
+                            #  "type": "image_url",
+                            #  "image_url": {
+                            #    "url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
+                            #  }
+                            # }
+                        ]
+                    }
+                ]
+            )
+            answer = completion.choices[0].message.content
             print(f"Agent generated response (first 50 chars): {answer[:50]}...")
             return answer
         except Exception as e:
@@ -163,7 +191,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner #15")
+    gr.Markdown("# Basic Agent Evaluation Runner #16")
     gr.Markdown(
         """
         **Instructions:**

requirements.txt

@@ -1,3 +1,4 @@
 gradio
 requests
-huggingface_hub
+huggingface_hub
+openai