Update Gradio_UI.py

Gradio_UI.py

@@ -25,159 +25,19 @@ from smolagents.memory import MemoryStep
 from smolagents.utils import _is_package_available
 
 
-def pull_messages_from_step(
-    step_log: MemoryStep,
-):
-    """Extract ChatMessage objects from agent steps with proper nesting"""
-    import gradio as gr
+def pull_messages_from_step(step_log: MemoryStep):
+    # Your existing pull_messages_from_step unchanged...
+    # (omitted here for brevity - keep your existing function as is)
+    ...
 
-    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}**")
 
-        # 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()
-            # 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)
-
-        # 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
-            if isinstance(args, dict):
-                content = str(args.get("answer", str(args)))
-            else:
-                content = str(args).strip()
-
-            if used_code:
-                # 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```"
-
-            parent_message_tool = gr.ChatMessage(
-                role="assistant",
-                content=content,
-                metadata={
-                    "title": f"🛠️ Used tool {first_tool_call.name}",
-                    "id": parent_id,
-                    "status": "pending",
-                },
-            )
-            yield parent_message_tool
-
-            # 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"
-
-        # 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"):
-            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_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=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,
-):
-    """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' extra to use the GradioUI: `pip install 'smolagents[gradio]'`"
-        )
-    import gradio as gr
-
-    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
-            if isinstance(step_log, ActionStep):
-                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,
-        ):
-            yield message
-
-    final_answer = step_log  # Last log is the run's final_answer
-    final_answer = handle_agent_output_types(final_answer)
-
-    if isinstance(final_answer, AgentText):
-        yield gr.ChatMessage(
-            role="assistant",
-            content=f"**Final answer:**\n{final_answer.to_string()}\n",
-        )
-    elif isinstance(final_answer, AgentImage):
-        yield gr.ChatMessage(
-            role="assistant",
-            content={"path": final_answer.to_string(), "mime_type": "image/png"},
-        )
-    elif isinstance(final_answer, AgentAudio):
-        yield gr.ChatMessage(
-            role="assistant",
-            content={"path": final_answer.to_string(), "mime_type": "audio/wav"},
-        )
-    else:
-        yield gr.ChatMessage(role="assistant", content=f"**Final answer:** {str(final_answer)}")
+def stream_to_gradio(agent, task: str, reset_agent_memory: bool = False, additional_args: Optional[dict] = None):
+    # Your existing stream_to_gradio unchanged...
+    # (omitted here for brevity - keep your existing function as is)
+    ...
 
 
 class GradioUI:
-    """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(
@@ -185,13 +45,28 @@ class GradioUI:
             )
         self.agent = agent
         self.file_upload_folder = file_upload_folder
-        if self.file_upload_folder is not None:
-            if not os.path.exists(file_upload_folder):
-                os.mkdir(file_upload_folder)
+        if self.file_upload_folder is not None and not os.path.exists(file_upload_folder):
+            os.mkdir(file_upload_folder)
 
-    def interact_with_agent(self, prompt, messages):
+    def interact_with_agent(self, prompt, messages, pdf_file_path=None):
         import gradio as gr
 
+        # If PDF file and prompt/question are provided, use document_qna_tool
+        if pdf_file_path and prompt:
+            # Run document QnA tool directly
+            for tool in self.agent.tools:
+                # Assuming your document QnA tool is named "document_qna_tool"
+                if hasattr(tool, "name") and tool.name == "document_qna_tool":
+                    try:
+                        answer = tool.run(pdf_path=pdf_file_path, question=prompt)
+                    except Exception as e:
+                        answer = f"Error running Document QnA tool: {str(e)}"
+                    messages.append(gr.ChatMessage(role="user", content=prompt))
+                    messages.append(gr.ChatMessage(role="assistant", content=answer))
+                    yield messages
+                    return
+
+        # Otherwise fallback to normal chat interaction
         messages.append(gr.ChatMessage(role="user", content=prompt))
         yield messages
         for msg in stream_to_gradio(self.agent, task=prompt, reset_agent_memory=False):
@@ -209,49 +84,42 @@ class GradioUI:
             "text/plain",
         ],
     ):
-        """
-        Handle file uploads, default allowed types are .pdf, .docx, and .txt
-        """
         import gradio as gr
 
         if file is None:
-            return gr.Textbox("No file uploaded", visible=True), file_uploads_log
+            return gr.Textbox("No file uploaded", visible=True), file_uploads_log, None
 
         try:
             mime_type, _ = mimetypes.guess_type(file.name)
         except Exception as e:
-            return gr.Textbox(f"Error: {e}", visible=True), file_uploads_log
+            return gr.Textbox(f"Error: {e}", visible=True), file_uploads_log, None
 
         if mime_type not in allowed_file_types:
-            return gr.Textbox("File type disallowed", visible=True), file_uploads_log
+            return gr.Textbox("File type disallowed", visible=True), file_uploads_log, None
 
-        # 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
+        sanitized_name = re.sub(r"[^\w\-.]", "_", original_name)
 
         type_to_ext = {}
         for ext, t in mimetypes.types_map.items():
             if t not in type_to_ext:
                 type_to_ext[t] = ext
 
-        # 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]
+        return gr.Textbox(f"File uploaded: {file_path}", visible=True), file_uploads_log + [file_path], file_path
 
     def log_user_message(self, text_input, file_uploads_log):
+        # Append info about uploaded files to the user message context
         return (
             text_input
             + (
-                f"\nYou have been provided with these files, which might be helpful or not: {file_uploads_log}"
+                f"\nYou have provided these files: {file_uploads_log}"
                 if len(file_uploads_log) > 0
                 else ""
             ),
@@ -264,6 +132,8 @@ class GradioUI:
         with gr.Blocks(fill_height=True) as demo:
             stored_messages = gr.State([])
             file_uploads_log = gr.State([])
+            current_pdf_path = gr.State(None)
+
             chatbot = gr.Chatbot(
                 label="Agent",
                 type="messages",
@@ -274,23 +144,37 @@ class GradioUI:
                 resizeable=True,
                 scale=1,
             )
-            # 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_file = gr.File(label="Upload a PDF file", file_types=[".pdf"])
                 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],
+                    inputs=[upload_file, file_uploads_log],
+                    outputs=[upload_status, file_uploads_log, current_pdf_path],
                 )
-            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])
 
-        demo.launch(debug=True, share=True, **kwargs)
+            text_input = gr.Textbox(lines=1, label="Ask a question about the document or chat")
+            submit_btn = gr.Button("Send")
+
+            # On submit, pass current_pdf_path and text input to interact_with_agent
+            def user_interact(text, messages, pdf_path):
+                if not text:
+                    return messages
+                return self.interact_with_agent(text, messages, pdf_path)
 
+            submit_btn.click(
+                user_interact,
+                inputs=[text_input, stored_messages, current_pdf_path],
+                outputs=chatbot,
+            )
+
+            # Also allow pressing Enter in textbox to submit
+            text_input.submit(
+                user_interact,
+                inputs=[text_input, stored_messages, current_pdf_path],
+                outputs=chatbot,
+            )
 
-__all__ = ["stream_to_gradio", "GradioUI"]
+        demo.launch(debug=True, share=True, **kwargs)