Update app.py

app.py

@@ -110,28 +110,28 @@ class BasicAgent:
                 }
             output_type = "string"
 
-        def forward(self, file_path: str, question: str) -> str:
-            import base64
-            from huggingface_hub import InferenceClient
-
-            client = InferenceClient(token=os.environ["HF_TOKEN"])
-            with open(file_path, "rb") as f:
-                image_bytes = f.read()
-            image_b64 = base64.b64encode(image_bytes).decode("utf-8")
-
-            result = client.chat_completion(
-                model="Qwen/Qwen2.5-VL-72B-Instruct",
-                messages=[
-                     {
-                        "role": "user",
-                        "content": [
-                            {"type": "text", "text": question},
-                            {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_b64}"}},
-                        ],
-                     }
-                ],
-            )
-            return result.choices[0].message.content
+            def forward(self, file_path: str, question: str) -> str:
+                import base64
+                from huggingface_hub import InferenceClient
+
+                client = InferenceClient(token=os.environ["HF_TOKEN"])
+                with open(file_path, "rb") as f:
+                    image_bytes = f.read()
+                image_b64 = base64.b64encode(image_bytes).decode("utf-8")
+
+                result = client.chat_completion(
+                    model="Qwen/Qwen2.5-VL-72B-Instruct",
+                    messages=[
+                        {
+                            "role": "user",
+                            "content": [
+                                {"type": "text", "text": question},
+                                {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_b64}"}},
+                            ],
+                        }
+                    ],
+                )
+                return result.choices[0].message.content
 
 
         class TranscribeAudioTool(Tool):
@@ -145,18 +145,17 @@ class BasicAgent:
         }
             output_type = "string"
 
-        def forward(self, file_path: str) -> str:
-            from huggingface_hub import InferenceClient
-            client = InferenceClient(token=os.environ["HF_TOKEN"])
-            result = client.automatic_speech_recognition(
-                file_path,
-                model="openai/whisper-large-v3",
-            )
-            return result.text
-        #pdf_tool = load_tool(
-            #"matterattetatte/pdf-upload-extractor-tool", 
-           # trust_remote_code = True
-        #)
+            def forward(self, file_path: str) -> str:
+                from huggingface_hub import InferenceClient
+                client = InferenceClient(token=os.environ["HF_TOKEN"])
+                result = client.automatic_speech_recognition(
+                    file_path,
+                    model="openai/whisper-large-v3",
+                )
+                return result.text
+        read_pdf = ReadPDFTool()
+        analyze_image = AnalyzeImageTool()
+        transcribe_audio = TranscribeAudioTool()
         #read_pdf = ReadPDFTool()
         self.agent = CodeAgent(
             tools=[
@@ -174,7 +173,7 @@ class BasicAgent:
                 ],
             model= InferenceClientModel("Qwen/Qwen2.5-Coder-32B-Instruct") ,
             additional_authorized_imports=["pandas", "requests", "re"],
-            instructions = ("You are an advanced CodeAgent that will show your capabilities to work in the real world by being tested in GAIA, the agent testing platform. If the question includes a task_id and mentions a file, call fetch_task_file first; route YouTube URLs to get_youtube_transcript, other URLs to visit_webpage, PDFs to pdf_tool, and spreadsheets to read_spreadsheet, using web_search only when no URL or file is given,then respond with only the exact final answer value, no explanation, no prefix."
+            instructions = ("You are an advanced CodeAgent that will show your capabilities to work in the real world by being tested in GAIA, the agent testing platform. If the question includes a task_id and mentions a file, call fetch_task_file first; route YouTube URLs to get_youtube_transcript, other URLs to visit_webpage, PDFs to read_pdf, and spreadsheets to read_spreadsheet, using web_search only when no URL or file is given,then respond with only the exact final answer value, no explanation, no prefix."
                            "Use the Thought Action observation to produce high quality results and only answer when you are sure you have performed the necessary steps for the task and question"
                            "If the file is an image, use analyze_image with a specific question about it"
                            "what to find. If the file is audio, use transcribe_audio first, then reason over the transcribed text "