Update app.py

app.py

@@ -1,19 +1,123 @@
 import gradio as gr
-import torch
+import base64
+import io
+import json
+import os
+import re
+import urllib.error
+import urllib.request
 from PIL import Image
 # from transformers import AutoModel, AutoProcessor 
 
 # ==========================================
-# 1. Load Model Weights 
+# 1. Configure SiliconFlow API
 # ==========================================
-MODEL_ID = "yangxiaoda/SpatialLogic-ckpt-tag"
-device = "cuda" if torch.cuda.is_available() else "cpu"
+API_URL = "https://api.siliconflow.cn/v1/chat/completions"
+MODEL_ID = "Qwen/Qwen3.6-35B-A3B"
+API_KEY = os.getenv(
+    "SILICONFLOW_API_KEY",
+    "sk-aflkmenvmawlrzbmlawwnhdyaacpylqeebiqzvjhgkujbttw",
+)
 
-print(f"Loading model to {device}...")
-# [REPLACE THIS] with your actual model loading code
-# processor = AutoProcessor.from_pretrained(MODEL_ID)
-# model = AutoModel.from_pretrained(MODEL_ID).to(device)
-print("Model loaded successfully!")
+print("SiliconFlow API mode enabled.")
+
+
+def pil_to_data_url(img: Image.Image) -> str:
+    """Convert PIL image to data URL string for API transport."""
+    buffered = io.BytesIO()
+    img.convert("RGB").save(buffered, format="JPEG", quality=92)
+    img_b64 = base64.b64encode(buffered.getvalue()).decode("utf-8")
+    return f"data:image/jpeg;base64,{img_b64}"
+
+
+def extract_json_block(text: str) -> dict:
+    """Extract first valid JSON object from model text output."""
+    text = text.strip()
+
+    try:
+        return json.loads(text)
+    except json.JSONDecodeError:
+        pass
+
+    fenced = re.search(r"```(?:json)?\s*(\{[\s\S]*?\})\s*```", text)
+    if fenced:
+        return json.loads(fenced.group(1))
+
+    inline = re.search(r"(\{[\s\S]*\})", text)
+    if inline:
+        return json.loads(inline.group(1))
+
+    raise ValueError("No valid JSON found in model response")
+
+
+def call_siliconflow_compare(img1: Image.Image, img2: Image.Image, action_desc: str):
+    """Call SiliconFlow API and return (score_img1, score_img2, explanation)."""
+    img1_data_url = pil_to_data_url(img1)
+    img2_data_url = pil_to_data_url(img2)
+
+    system_prompt = (
+        "You are an image-comparison judge. Given two images and an action description, "
+        "decide which image is closer to the completed state of the action. "
+        "Return only JSON with keys: score_img1, score_img2, explanation. "
+        "score_img1 and score_img2 must be numbers in [0,1]."
+    )
+
+    payload = {
+        "model": MODEL_ID,
+        "temperature": 0.1,
+        "response_format": {"type": "json_object"},
+        "messages": [
+            {"role": "system", "content": system_prompt},
+            {
+                "role": "user",
+                "content": [
+                    {
+                        "type": "text",
+                        "text": (
+                            "Action description: "
+                            f"{action_desc}\n"
+                            "Please compare image1 and image2 and output JSON only."
+                        ),
+                    },
+                    {"type": "image_url", "image_url": {"url": img1_data_url}},
+                    {"type": "image_url", "image_url": {"url": img2_data_url}},
+                ],
+            },
+        ],
+    }
+
+    data = json.dumps(payload).encode("utf-8")
+    request = urllib.request.Request(
+        API_URL,
+        data=data,
+        headers={
+            "Authorization": f"Bearer {API_KEY}",
+            "Content-Type": "application/json",
+        },
+        method="POST",
+    )
+
+    try:
+        with urllib.request.urlopen(request, timeout=120) as response:
+            raw = response.read().decode("utf-8")
+    except urllib.error.HTTPError as e:
+        error_body = e.read().decode("utf-8", errors="ignore")
+        raise RuntimeError(f"HTTP {e.code}: {error_body}") from e
+    except urllib.error.URLError as e:
+        raise RuntimeError(f"Network error: {e.reason}") from e
+
+    api_result = json.loads(raw)
+    content = api_result["choices"][0]["message"]["content"]
+    parsed = extract_json_block(content)
+
+    score_img1 = float(parsed.get("score_img1", 0.0))
+    score_img2 = float(parsed.get("score_img2", 0.0))
+    explanation = str(parsed.get("explanation", "No explanation provided."))
+
+    score_img1 = max(0.0, min(1.0, score_img1))
+    score_img2 = max(0.0, min(1.0, score_img2))
+
+    return score_img1, score_img2, explanation
 
 
 # ==========================================
@@ -32,29 +136,39 @@ def compare_images(img1, img2, action_desc):
         return "⚠️ Please enter an action description!"
 
     try:
-        # [REPLACE THIS] with your actual inference code
-        # Example pseudo-code:
-        # inputs = processor(text=action_desc, images=[img1, img2], return_tensors="pt").to(device)
-        # outputs = model(**inputs)
-        # score1, score2 = outputs.logits 
-        
-        # Dummy scores for UI testing (Replace with real logic)
-        score_img1 = 0.8  
-        score_img2 = 0.4  
+        score_img1, score_img2, api_explanation = call_siliconflow_compare(
+            img1=img1,
+            img2=img2,
+            action_desc=action_desc,
+        )
 
         # 2. Logic Judgment
         if score_img1 > score_img2:
             result = "img1"
-            explanation = "The model evaluates that **Image 1 (img1)** is closer to the completed state of the described task."
+            explanation = (
+                "The model evaluates that **Image 1 (img1)** is closer to the completed "
+                f"state of the described task.\n\nModel rationale: {api_explanation}"
+            )
         elif score_img2 > score_img1:
             result = "img2"
-            explanation = "The model evaluates that **Image 2 (img2)** is closer to the completed state of the described task."
+            explanation = (
+                "The model evaluates that **Image 2 (img2)** is closer to the completed "
+                f"state of the described task.\n\nModel rationale: {api_explanation}"
+            )
         else:
             result = "Tie"
-            explanation = "The model evaluates both images equally regarding the task completion."
+            explanation = (
+                "The model evaluates both images equally regarding the task completion."
+                f"\n\nModel rationale: {api_explanation}"
+            )
 
         # 3. Format Output
-        return f"### **Output:** {result}\n\n**Explanation:** {explanation}"
+        return (
+            f"### **Output:** {result}\n\n"
+            f"**Score(img1):** {score_img1:.3f}  \n"
+            f"**Score(img2):** {score_img2:.3f}\n\n"
+            f"**Explanation:** {explanation}"
+        )
     
     except Exception as e:
         return f"❌ An error occurred during inference: {str(e)}"