Update Gradio_UI.py

Gradio_UI.py

@@ -10,32 +10,46 @@ from smolagents.memory import MemoryStep
 from smolagents.utils import _is_package_available
 
 
-def pull_messages_from_step(step_log: MemoryStep):
+def pull_messages_from_step(
+    step_log: MemoryStep,
+):
     """Extract ChatMessage objects from agent steps with proper nesting"""
     import gradio as gr
 
     if isinstance(step_log, ActionStep):
+        # Output the step number
         step_number = f"Step {step_log.step_number}" if step_log.step_number is not None else ""
         yield gr.ChatMessage(role="assistant", content=f"**{step_number}**")
 
-        if hasattr(step_log, "model_output") and step_log.model_output:
+        # First yield the thought/reasoning from the LLM
+        if hasattr(step_log, "model_output") and step_log.model_output is not None:
+            # Clean up the LLM output
             model_output = step_log.model_output.strip()
-            model_output = re.sub(r"```\s*<end_code>", "```", model_output)
-            model_output = re.sub(r"<end_code>\s*```", "```", model_output)
-            model_output = re.sub(r"```\s*\n\s*<end_code>", "```", model_output)
+            # Remove any trailing <end_code> and extra backticks, handling multiple possible formats
+            model_output = re.sub(r"```\s*<end_code>", "```", model_output)  # handles ```<end_code>
+            model_output = re.sub(r"<end_code>\s*```", "```", model_output)  # handles <end_code>```
+            model_output = re.sub(r"```\s*\n\s*<end_code>", "```", model_output)  # handles ```\n<end_code>
+            model_output = model_output.strip()
             yield gr.ChatMessage(role="assistant", content=model_output)
 
-        if hasattr(step_log, "tool_calls") and step_log.tool_calls:
+        # For tool calls, create a parent message
+        if hasattr(step_log, "tool_calls") and step_log.tool_calls is not None:
             first_tool_call = step_log.tool_calls[0]
             used_code = first_tool_call.name == "python_interpreter"
             parent_id = f"call_{len(step_log.tool_calls)}"
 
+            # Tool call becomes the parent message with timing info
+            # First we will handle arguments based on type
             args = first_tool_call.arguments
-            content = str(args.get("answer", str(args))) if isinstance(args, dict) else str(args).strip()
+            if isinstance(args, dict):
+                content = str(args.get("answer", str(args)))
+            else:
+                content = str(args).strip()
 
             if used_code:
-                content = re.sub(r"```.*?\n", "", content)
-                content = re.sub(r"\s*<end_code>\s*", "", content)
+                # Clean up the content by removing any end code tags
+                content = re.sub(r"```.*?\n", "", content)  # Remove existing code blocks
+                content = re.sub(r"\s*<end_code>\s*", "", content)  # Remove end_code tags
                 content = content.strip()
                 if not content.startswith("```python"):
                     content = f"```python\n{content}\n```"
@@ -43,51 +57,75 @@ def pull_messages_from_step(step_log: MemoryStep):
             parent_message_tool = gr.ChatMessage(
                 role="assistant",
                 content=content,
-                metadata={"title": f"🛠️ Used tool {first_tool_call.name}", "id": parent_id, "status": "pending"},
+                metadata={
+                    "title": f"🛠️ Used tool {first_tool_call.name}",
+                    "id": parent_id,
+                    "status": "pending",
+                },
             )
             yield parent_message_tool
 
-            if hasattr(step_log, "observations") and step_log.observations:
-                log_content = re.sub(r"^Execution logs:\s*", "", step_log.observations.strip())
-                yield gr.ChatMessage(
-                    role="assistant",
-                    content=log_content,
-                    metadata={"title": "📝 Execution Logs", "parent_id": parent_id, "status": "done"},
-                )
-
-            if hasattr(step_log, "error") and step_log.error:
+            # Nesting execution logs under the tool call if they exist
+            if hasattr(step_log, "observations") and (
+                step_log.observations is not None and step_log.observations.strip()
+            ):  # Only yield execution logs if there's actual content
+                log_content = step_log.observations.strip()
+                if log_content:
+                    log_content = re.sub(r"^Execution logs:\s*", "", log_content)
+                    yield gr.ChatMessage(
+                        role="assistant",
+                        content=f"{log_content}",
+                        metadata={"title": "📝 Execution Logs", "parent_id": parent_id, "status": "done"},
+                    )
+
+            # Nesting any errors under the tool call
+            if hasattr(step_log, "error") and step_log.error is not None:
                 yield gr.ChatMessage(
                     role="assistant",
                     content=str(step_log.error),
                     metadata={"title": "💥 Error", "parent_id": parent_id, "status": "done"},
                 )
 
+            # Update parent message metadata to done status without yielding a new message
             parent_message_tool.metadata["status"] = "done"
 
-        elif hasattr(step_log, "error") and step_log.error:
+        # Handle standalone errors but not from tool calls
+        elif hasattr(step_log, "error") and step_log.error is not None:
             yield gr.ChatMessage(role="assistant", content=str(step_log.error), metadata={"title": "💥 Error"})
 
+        # Calculate duration and token information
         step_footnote = f"{step_number}"
         if hasattr(step_log, "input_token_count") and hasattr(step_log, "output_token_count"):
-            step_footnote += f" | Input-tokens:{step_log.input_token_count:,} | Output-tokens:{step_log.output_token_count:,}"
+            token_str = (
+                f" | Input-tokens:{step_log.input_token_count:,} | Output-tokens:{step_log.output_token_count:,}"
+            )
+            step_footnote += token_str
         if hasattr(step_log, "duration"):
-            step_footnote += f" | Duration: {round(float(step_log.duration), 2)}"
+            step_duration = f" | Duration: {round(float(step_log.duration), 2)}" if step_log.duration else None
+            step_footnote += step_duration
         step_footnote = f"""<span style="color: #bbbbc2; font-size: 12px;">{step_footnote}</span> """
-        yield gr.ChatMessage(role="assistant", content=step_footnote)
+        yield gr.ChatMessage(role="assistant", content=f"{step_footnote}")
         yield gr.ChatMessage(role="assistant", content="-----")
 
 
-def stream_to_gradio(agent, task: str, reset_agent_memory: bool = False, additional_args: Optional[dict] = None):
+def stream_to_gradio(
+    agent,
+    task: str,
+    reset_agent_memory: bool = False,
+    additional_args: Optional[dict] = None,
+):
+    """Runs an agent with the given task and streams the messages from the agent as gradio ChatMessages."""
     if not _is_package_available("gradio"):
-        raise ModuleNotFoundError("Please install 'gradio': `pip install 'smolagents[gradio]'`")
-
+        raise ModuleNotFoundError(
+            "Please install 'gradio' extra to use the GradioUI: `pip install 'smolagents[gradio]'`"
+        )
     import gradio as gr
-    from smolagents.agents import FinalAnswerStep
 
     total_input_tokens = 0
     total_output_tokens = 0
 
     for step_log in agent.run(task, stream=True, reset=reset_agent_memory, additional_args=additional_args):
+        # Track tokens if model provides them
         if hasattr(agent.model, "last_input_token_count"):
             total_input_tokens += agent.model.last_input_token_count
             total_output_tokens += agent.model.last_output_token_count
@@ -95,13 +133,18 @@ def stream_to_gradio(agent, task: str, reset_agent_memory: bool = False, additio
                 step_log.input_token_count = agent.model.last_input_token_count
                 step_log.output_token_count = agent.model.last_output_token_count
 
-        for message in pull_messages_from_step(step_log):
+        for message in pull_messages_from_step(
+            step_log,
+        ):
             yield message
 
-    final_output = None
+    from smolagents.agents import FinalAnswerStep
+
+    # Safely extract the final output from the last step
     if isinstance(step_log, FinalAnswerStep):
         final_output = step_log.final_answer
     else:
+        # If not a FinalAnswerStep, fallback to tool_output or tool_calls
         final_output = getattr(step_log, "tool_output", None)
         if not final_output and hasattr(step_log, "tool_calls"):
             for call in step_log.tool_calls:
@@ -109,30 +152,47 @@ def stream_to_gradio(agent, task: str, reset_agent_memory: bool = False, additio
                     final_output = call.arguments.get("answer")
                     break
 
+
     final_output = handle_agent_output_types(final_output)
 
     if isinstance(final_output, AgentText):
-        yield gr.ChatMessage(role="assistant", content=final_output.to_string().strip())
+        yield gr.ChatMessage(
+            role="assistant",
+            content=final_output.to_string().strip(),
+        )
     elif isinstance(final_output, AgentImage):
-        yield gr.ChatMessage(role="assistant", content={"path": final_output.to_string(), "mime_type": "image/png"})
+        yield gr.ChatMessage(
+            role="assistant",
+            content={"path": final_output.to_string(), "mime_type": "image/png"},
+        )
     elif isinstance(final_output, AgentAudio):
-        yield gr.ChatMessage(role="assistant", content={"path": final_output.to_string(), "mime_type": "audio/wav"})
+        yield gr.ChatMessage(
+            role="assistant",
+            content={"path": final_output.to_string(), "mime_type": "audio/wav"},
+        )
     else:
         yield gr.ChatMessage(role="assistant", content=str(final_output).strip())
 
 
+
+
 class GradioUI:
-    def __init__(self, agent: MultiStepAgent, file_upload_folder: Optional[str] = None, submit_fn=None):
+    """A one-line interface to launch your agent in Gradio"""
+
+    def __init__(self, agent: MultiStepAgent, file_upload_folder: str | None = None):
         if not _is_package_available("gradio"):
-            raise ModuleNotFoundError("Please install 'gradio': `pip install 'smolagents[gradio]'`")
+            raise ModuleNotFoundError(
+                "Please install 'gradio' extra to use the GradioUI: `pip install 'smolagents[gradio]'`"
+            )
         self.agent = agent
         self.file_upload_folder = file_upload_folder
-        self.submit_fn = submit_fn
-        if self.file_upload_folder and not os.path.exists(file_upload_folder):
-            os.mkdir(file_upload_folder)
+        if self.file_upload_folder is not None:
+            if not os.path.exists(file_upload_folder):
+                os.mkdir(file_upload_folder)
 
     def interact_with_agent(self, prompt, messages):
         import gradio as gr
+
         messages.append(gr.ChatMessage(role="user", content=prompt))
         yield messages
         for msg in stream_to_gradio(self.agent, task=prompt, reset_agent_memory=False):
@@ -140,14 +200,21 @@ class GradioUI:
             yield messages
         yield messages
 
-    def upload_file(self, file, file_uploads_log, allowed_file_types=None):
+    def upload_file(
+        self,
+        file,
+        file_uploads_log,
+        allowed_file_types=[
+            "application/pdf",
+            "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+            "text/plain",
+        ],
+    ):
+        """
+        Handle file uploads, default allowed types are .pdf, .docx, and .txt
+        """
         import gradio as gr
-        if allowed_file_types is None:
-            allowed_file_types = [
-                "application/pdf",
-                "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
-                "text/plain",
-            ]
+
         if file is None:
             return gr.Textbox("No file uploaded", visible=True), file_uploads_log
 
@@ -159,11 +226,24 @@ class GradioUI:
         if mime_type not in allowed_file_types:
             return gr.Textbox("File type disallowed", visible=True), file_uploads_log
 
-        sanitized_name = re.sub(r"[^\w\-.]", "_", os.path.basename(file.name))
-        ext = mimetypes.guess_extension(mime_type)
-        sanitized_name = f"{os.path.splitext(sanitized_name)[0]}{ext or ''}"
+        # Sanitize file name
+        original_name = os.path.basename(file.name)
+        sanitized_name = re.sub(
+            r"[^\w\-.]", "_", original_name
+        )  # Replace any non-alphanumeric, non-dash, or non-dot characters with underscores
+
+        type_to_ext = {}
+        for ext, t in mimetypes.types_map.items():
+            if t not in type_to_ext:
+                type_to_ext[t] = ext
 
-        file_path = os.path.join(self.file_upload_folder, sanitized_name)
+        # Ensure the extension correlates to the mime type
+        sanitized_name = sanitized_name.split(".")[:-1]
+        sanitized_name.append("" + type_to_ext[mime_type])
+        sanitized_name = "".join(sanitized_name)
+
+        # Save the uploaded file to the specified folder
+        file_path = os.path.join(self.file_upload_folder, os.path.basename(sanitized_name))
         shutil.copy(file.name, file_path)
 
         return gr.Textbox(f"File uploaded: {file_path}", visible=True), file_uploads_log + [file_path]
@@ -171,8 +251,11 @@ class GradioUI:
     def log_user_message(self, text_input, file_uploads_log):
         return (
             text_input
-            + (f"\nYou have been provided with these files, which might be helpful or not: {file_uploads_log}"
-               if file_uploads_log else ""),
+            + (
+                f"\nYou have been provided with these files, which might be helpful or not: {file_uploads_log}"
+                if len(file_uploads_log) > 0
+                else ""
+            ),
             "",
         )
 
@@ -182,36 +265,33 @@ class GradioUI:
         with gr.Blocks(fill_height=True) as demo:
             stored_messages = gr.State([])
             file_uploads_log = gr.State([])
-
             chatbot = gr.Chatbot(
                 label="Agent",
                 type="messages",
-                avatar_images=(None, "https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/Alfred.png"),
+                avatar_images=(
+                    None,
+                    "https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/Alfred.png",
+                ),
+                resizeable=True,
+                scale=1,
             )
-
-            if self.file_upload_folder:
+            # If an upload folder is provided, enable the upload feature
+            if self.file_upload_folder is not None:
                 upload_file = gr.File(label="Upload a file")
                 upload_status = gr.Textbox(label="Upload Status", interactive=False, visible=False)
-                upload_file.change(self.upload_file, [upload_file, file_uploads_log], [upload_status, file_uploads_log])
-
+                upload_file.change(
+                    self.upload_file,
+                    [upload_file, file_uploads_log],
+                    [upload_status, file_uploads_log],
+                )
             text_input = gr.Textbox(lines=1, label="Chat Message")
             text_input.submit(
                 self.log_user_message,
                 [text_input, file_uploads_log],
                 [stored_messages, text_input],
             ).then(self.interact_with_agent, [stored_messages, chatbot], [chatbot])
-
-            submit_btn = gr.Button("📤 Submit All GAIA Answers")
-            submit_status = gr.Textbox(label="Submission Status", interactive=False)
-
-            if self.submit_fn:
-                submit_btn.click(
-                    fn=lambda: self.submit_fn() or "✅ Submitted to GAIA scoring API",
-                    inputs=[],
-                    outputs=[submit_status],
-                )
-
+        
         demo.launch(debug=True, share=True, show_error=True, **kwargs)
 
 
-__all__ = ["stream_to_gradio", "GradioUI"]
+__all__ = ["stream_to_gradio", "GradioUI"]