Update Gradio_UI.py

Gradio_UI.py

@@ -1,331 +1,85 @@
-#!/usr/bin/env python
-# coding=utf-8
-# Copyright 2024 The HuggingFace Inc. team. All rights reserved.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.
-import mimetypes
-import os
-import re
-import shutil
-from typing import Optional
-
-from smolagents.agent_types import AgentAudio, AgentImage, AgentText, handle_agent_output_types
-from smolagents.agents import ActionStep, MultiStepAgent
-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
-
-    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)}")
-
+import gradio as gr
 
 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(
-                "Please install 'gradio' extra to use the GradioUI: `pip install 'smolagents[gradio]'`"
-            )
+    def __init__(self, agent):
         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)
-
-    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):
-            messages.append(msg)
-            yield messages
-        yield messages
-
-    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 file is None:
-            return gr.Textbox("No file uploaded", visible=True), file_uploads_log
-
-        try:
-            mime_type, _ = mimetypes.guess_type(file.name)
-        except Exception as e:
-            return gr.Textbox(f"Error: {e}", visible=True), file_uploads_log
-
-        if mime_type not in allowed_file_types:
-            return gr.Textbox("File type disallowed", visible=True), file_uploads_log
-
-        # 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
-
-        # 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]
-
-    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 len(file_uploads_log) > 0
-                else ""
-            ),
-            "",
-        )
-
-    def launch(self, **kwargs):
-        import gradio as gr
-    
-        with gr.Blocks(fill_height=True) as demo:
-            stored_messages = gr.State([])
-            file_uploads_log = gr.State([])
-            
-            # Upload UI row (only if file_upload_folder is set)
-            if self.file_upload_folder is not None:
-                with gr.Row():
-                    upload_file = gr.File(
-                        label="Upload a file (PDF, DOCX, TXT)",
-                        file_types=['.pdf', '.docx', '.txt'],
-                        interactive=True,
-                    )
-                    upload_status = gr.Textbox(
-                        label="Upload Status",
-                        interactive=False,
-                        visible=True,
-                        max_lines=1,
-                        show_label=True,
-                    )
-                # Hook upload event
-                upload_file.change(
-                    self.upload_file,
-                    inputs=[upload_file, file_uploads_log],
-                    outputs=[upload_status, file_uploads_log],
-                )
-            else:
-                # If no upload folder provided, these widgets don’t exist
-                upload_file = None
-                upload_status = None
-    
-            chatbot = gr.Chatbot(
-                label="Agent",
-                type="messages",
-                avatar_images=(
-                    None,
-                    "https://huggingface.co/datasets/agents-course/course-images/resolve/main/en/communication/Alfred.png",
-                ),
-                resizeable=True,
-                scale=1,
-            )
-    
-            text_input = gr.Textbox(lines=1, label="Chat Message")
-    
-            # When user submits the text input
-            def on_submit(text, files_log):
-                combined_prompt = (
-                    text
-                    + (
-                        f"\nYou have been provided with these files, which might be helpful or not: {files_log}"
-                        if len(files_log) > 0
-                        else ""
-                    )
-                )
-                return combined_prompt, ""
-    
-            text_input.submit(
-                on_submit,
-                inputs=[text_input, file_uploads_log],
-                outputs=[stored_messages, text_input],
-            ).then(
-                self.interact_with_agent,
-                inputs=[stored_messages, chatbot],
-                outputs=chatbot,
-            )
-    
-        demo.launch(debug=True, share=True, **kwargs)
 
-__all__ = ["stream_to_gradio", "GradioUI"]
+    def launch(self):
+        with gr.Blocks() as demo:
+            gr.Markdown("# Multi-Tool AI Agent")
+            gr.Markdown("Use the tabs below to interact with different tools:")
+
+            with gr.Tabs():
+
+                # Tab 1: Weather
+                with gr.TabItem("Weather"):
+                    place_input = gr.Textbox(label="Enter place name (e.g., London)", placeholder="City or location")
+                    weather_output = gr.Textbox(label="Current Weather", interactive=False)
+                    get_weather_btn = gr.Button("Get Weather")
+
+                    def get_weather(place):
+                        if not place.strip():
+                            return "Please enter a valid place name."
+                        return self.agent.tools[1](place)
+
+                    get_weather_btn.click(get_weather, inputs=place_input, outputs=weather_output)
+
+                # Tab 2: Local Time
+                with gr.TabItem("Local Time"):
+                    timezone_input = gr.Textbox(label="Enter timezone (e.g., America/New_York)", placeholder="Timezone string")
+                    time_output = gr.Textbox(label="Current Time", interactive=False)
+                    get_time_btn = gr.Button("Get Local Time")
+
+                    def get_time(tz):
+                        if not tz.strip():
+                            return "Please enter a valid timezone."
+                        return self.agent.tools[0](tz)
+
+                    get_time_btn.click(get_time, inputs=timezone_input, outputs=time_output)
+
+                # Tab 3: Image Generation
+                with gr.TabItem("Image Generation"):
+                    image_prompt = gr.Textbox(label="Enter image description prompt", lines=2)
+                    image_output = gr.Image(label="Generated Image")
+                    gen_image_btn = gr.Button("Generate Image")
+
+                    def gen_image(prompt):
+                        if not prompt.strip():
+                            return None
+                        # The image generation tool might return an image URL or PIL.Image.
+                        # Adjust this depending on your tool's output format.
+                        result = self.agent.tools[2](prompt)
+                        return result
+
+                    gen_image_btn.click(gen_image, inputs=image_prompt, outputs=image_output)
+
+                # Tab 4: Web Search
+                with gr.TabItem("Web Search"):
+                    search_query = gr.Textbox(label="Enter search query")
+                    search_output = gr.Textbox(label="Search Results", interactive=False)
+                    search_btn = gr.Button("Search")
+
+                    def search(q):
+                        if not q.strip():
+                            return "Please enter a search query."
+                        return self.agent.tools[3](q)
+
+                    search_btn.click(search, inputs=search_query, outputs=search_output)
+
+                # Tab 5: Document Q&A
+                with gr.TabItem("Document Q&A"):
+                    pdf_upload = gr.File(label="Upload PDF Document", file_types=[".pdf"])
+                    question_input = gr.Textbox(label="Enter your question about the document")
+                    answer_output = gr.Textbox(label="Answer", interactive=False)
+                    docqa_btn = gr.Button("Get Answer")
+
+                    def doc_qa(pdf_file, question):
+                        if pdf_file is None:
+                            return "Please upload a PDF file."
+                        if not question.strip():
+                            return "Please enter a question."
+                        return self.agent.tools[4](pdf_file.name, question)
+
+                    docqa_btn.click(doc_qa, inputs=[pdf_upload, question_input], outputs=answer_output)
+
+            demo.launch()