Update image_analyzer.py

image_analyzer.py

@@ -29,7 +29,48 @@ class ImageAnalysisTool(Tool):
             "Content-Type": "application/json"
         }
 
-    def forward(self, image_path: str, question: str) -> str
+    def forward(self, image_path: str, question: str) -> str:
+        try:
+            with open(image_path, "rb") as img_file:
+                image_bytes = img_file.read()
+
+            # Encode image to base64 string
+            img_b64 = base64.b64encode(image_bytes).decode("utf-8")
+
+            # Prepare payload for the API
+            payload = {
+                "inputs": img_b64
+            }
+
+            response = requests.post(
+                self.api_url,
+                headers=self.headers,
+                json=payload,
+                timeout=60
+            )
+
+            if response.status_code == 200:
+                result = response.json()
+
+                caption = None
+                # Try common keys for caption output
+                if isinstance(result, dict):
+                    caption = result.get("generated_text") or result.get("caption") or result.get("text")
+                elif isinstance(result, list) and len(result) > 0 and isinstance(result[0], dict):
+                    caption = result[0].get("generated_text") or result[0].get("caption") or result[0].get("text")
+
+                if not caption:
+                    return "Error: No caption found in model response."
+
+                # Combine caption with the question to form a simple answer
+                answer = f"Caption: {caption}\nAnswer to question '{question}': {caption}"
+                return answer.strip()
+
+            else:
+                return f"Error analyzing image: {response.status_code} {response.text}"
+
+        except Exception as e:
+            return f"Error analyzing image: {e}"