Initial commit from (move code from) Colab

.gitignore

@@ -0,0 +1,3 @@
+.env
+.venv
+uv.lock

Gradio_UI.py

@@ -0,0 +1,295 @@
+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)}")
+
+
+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]'`"
+            )
+        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
+
+        # Define instruction text
+        instructions = """
+        # 🎵 Song Meaning Bot 🎶
+        ### How to Use:
+        1️⃣ **Paste a YouTube song link** in the input field.  
+        2️⃣ The AI will **extract the song title & artist** from the video.  
+        3️⃣ It will **search for lyrics**.  
+        4️⃣ If lyrics are found, they will be **translated to English**.  
+        5️⃣ AI will **summarize the song's meaning** in simple terms.  
+        
+        📌 *Note:* The agent currently only takes links in the format https://www.youtube.com/watch?v=XXXXXXXXXX.
+        """
+
+        with gr.Blocks(fill_height=True) as demo:
+            gr.Markdown(instructions)
+            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",
+                ),
+                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_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],
+                )
+            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)
+
+
+__all__ = ["stream_to_gradio", "GradioUI"]

app.py

@@ -1,64 +1,72 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+import os
 
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+from Gradio_UI import GradioUI
+from litellm import completion
+from smolagents import (
+    CodeAgent,
+    DuckDuckGoSearchTool,
+    FinalAnswerTool,
+    LiteLLMModel,
+    VisitWebpageTool,
+    tool,
+)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+os.environ["GEMINI_API_KEY"] = os.getenv("GEMINI_API_KEY")
 
-    messages.append({"role": "user", "content": message})
+@tool
+def analyze_lyrics_tool(song_title: str, artist: str, lyrics: str) -> str:
+    """
+    Performs a deep analysis of the musical track, given its metadata.
+    
+    Args:
+        song_title: title of the song or music trach.
+        artist: The name of the artist.
+        lyrics: The lyrics of the song.
+    
+    Returns:
+        A summary of the song's meaning in English.
+    """
 
-    response = ""
+    prompt = f'''You are an expert in songs and their meanings. 
+    Summarize the meaning of {song_title} by {artist} and identify 
+    key themes based on the lyrics: 
+    {lyrics}. 
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    Includs deep idea and vibes analysis with explainations 
+    based on references to the exact lines
+    '''
 
-        response += token
-        yield response
+    response = completion(
+        model="gemini/gemini-2.0-flash", 
+        messages=[
+            {"role": "user", "content": prompt}
+            ])
+    
+    try:
+        lyrics = response.choices[0].message.content.strip()
+        return lyrics
+    except (AttributeError, KeyError, IndexError):
+        try:
+            lyrics = response['choices'][0]['message']['content'].strip()
+            return lyrics
+        except (AttributeError, KeyError, IndexError):
+            pass
 
+final_answer = FinalAnswerTool()
+model = LiteLLMModel(model_id="gemini/gemini-2.0-flash")
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
+# Example usage within the agent
+agent = CodeAgent(
+    tools=[
+      FinalAnswerTool(), 
+      DuckDuckGoSearchTool(),
+      VisitWebpageTool(),
+      analyze_lyrics_tool
+    ], 
+    model=model,
+    additional_authorized_imports=['numpy', 'bs4'],
+    max_steps=22,
+    verbosity_level=1
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+GradioUI(agent).launch()

pyproject.toml

@@ -0,0 +1,12 @@
+[project]
+name = "lyricsanalyzeragent"
+version = "0.1.0"
+description = "Add your description here"
+readme = "README.md"
+requires-python = ">=3.13"
+dependencies = [
+    "gradio>=5.20.0",
+    "huggingface-hub>=0.29.1",
+    "litellm>=1.61.20",
+    "smolagents>=1.9.2",
+]

requirements.txt

@@ -1 +1,252 @@
-huggingface_hub==0.25.2
+# This file was autogenerated by uv via the following command:
+#    uv pip compile pyproject.toml -o requirements.txt
+aiofiles==23.2.1
+    # via gradio
+aiohappyeyeballs==2.4.6
+    # via aiohttp
+aiohttp==3.11.13
+    # via litellm
+aiosignal==1.3.2
+    # via aiohttp
+annotated-types==0.7.0
+    # via pydantic
+anyio==4.8.0
+    # via
+    #   gradio
+    #   httpx
+    #   openai
+    #   starlette
+attrs==25.1.0
+    # via
+    #   aiohttp
+    #   jsonschema
+    #   referencing
+audioop-lts==0.2.1
+    # via gradio
+beautifulsoup4==4.13.3
+    # via markdownify
+certifi==2025.1.31
+    # via
+    #   httpcore
+    #   httpx
+    #   requests
+charset-normalizer==3.4.1
+    # via requests
+click==8.1.8
+    # via
+    #   duckduckgo-search
+    #   litellm
+    #   typer
+    #   uvicorn
+distro==1.9.0
+    # via openai
+duckduckgo-search==7.5.0
+    # via smolagents
+fastapi==0.115.11
+    # via gradio
+ffmpy==0.5.0
+    # via gradio
+filelock==3.17.0
+    # via huggingface-hub
+frozenlist==1.5.0
+    # via
+    #   aiohttp
+    #   aiosignal
+fsspec==2025.2.0
+    # via
+    #   gradio-client
+    #   huggingface-hub
+gradio==5.20.0
+    # via lyricsanalyzeragent (pyproject.toml)
+gradio-client==1.7.2
+    # via gradio
+groovy==0.1.2
+    # via gradio
+h11==0.14.0
+    # via
+    #   httpcore
+    #   uvicorn
+httpcore==1.0.7
+    # via httpx
+httpx==0.28.1
+    # via
+    #   gradio
+    #   gradio-client
+    #   litellm
+    #   openai
+    #   safehttpx
+huggingface-hub==0.29.1
+    # via
+    #   lyricsanalyzeragent (pyproject.toml)
+    #   gradio
+    #   gradio-client
+    #   smolagents
+    #   tokenizers
+idna==3.10
+    # via
+    #   anyio
+    #   httpx
+    #   requests
+    #   yarl
+importlib-metadata==8.6.1
+    # via litellm
+jinja2==3.1.5
+    # via
+    #   gradio
+    #   litellm
+    #   smolagents
+jiter==0.8.2
+    # via openai
+jsonschema==4.23.0
+    # via litellm
+jsonschema-specifications==2024.10.1
+    # via jsonschema
+litellm==1.61.20
+    # via lyricsanalyzeragent (pyproject.toml)
+lxml==5.3.1
+    # via duckduckgo-search
+markdown-it-py==3.0.0
+    # via rich
+markdownify==1.0.0
+    # via smolagents
+markupsafe==2.1.5
+    # via
+    #   gradio
+    #   jinja2
+mdurl==0.1.2
+    # via markdown-it-py
+multidict==6.1.0
+    # via
+    #   aiohttp
+    #   yarl
+numpy==2.2.3
+    # via
+    #   gradio
+    #   pandas
+openai==1.65.2
+    # via litellm
+orjson==3.10.15
+    # via gradio
+packaging==24.2
+    # via
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+pandas==2.2.3
+    # via
+    #   gradio
+    #   smolagents
+pillow==11.1.0
+    # via
+    #   gradio
+    #   smolagents
+primp==0.14.0
+    # via duckduckgo-search
+propcache==0.3.0
+    # via
+    #   aiohttp
+    #   yarl
+pydantic==2.10.6
+    # via
+    #   fastapi
+    #   gradio
+    #   litellm
+    #   openai
+pydantic-core==2.27.2
+    # via pydantic
+pydub==0.25.1
+    # via gradio
+pygments==2.19.1
+    # via rich
+python-dateutil==2.9.0.post0
+    # via pandas
+python-dotenv==1.0.1
+    # via
+    #   litellm
+    #   smolagents
+python-multipart==0.0.20
+    # via gradio
+pytz==2025.1
+    # via pandas
+pyyaml==6.0.2
+    # via
+    #   gradio
+    #   huggingface-hub
+referencing==0.36.2
+    # via
+    #   jsonschema
+    #   jsonschema-specifications
+regex==2024.11.6
+    # via tiktoken
+requests==2.32.3
+    # via
+    #   huggingface-hub
+    #   smolagents
+    #   tiktoken
+rich==13.9.4
+    # via
+    #   smolagents
+    #   typer
+rpds-py==0.23.1
+    # via
+    #   jsonschema
+    #   referencing
+ruff==0.9.9
+    # via gradio
+safehttpx==0.1.6
+    # via gradio
+semantic-version==2.10.0
+    # via gradio
+shellingham==1.5.4
+    # via typer
+six==1.17.0
+    # via
+    #   markdownify
+    #   python-dateutil
+smolagents==1.9.2
+    # via lyricsanalyzeragent (pyproject.toml)
+sniffio==1.3.1
+    # via
+    #   anyio
+    #   openai
+soupsieve==2.6
+    # via beautifulsoup4
+starlette==0.46.0
+    # via
+    #   fastapi
+    #   gradio
+tiktoken==0.9.0
+    # via litellm
+tokenizers==0.21.0
+    # via litellm
+tomlkit==0.13.2
+    # via gradio
+tqdm==4.67.1
+    # via
+    #   huggingface-hub
+    #   openai
+typer==0.15.2
+    # via gradio
+typing-extensions==4.12.2
+    # via
+    #   beautifulsoup4
+    #   fastapi
+    #   gradio
+    #   gradio-client
+    #   huggingface-hub
+    #   openai
+    #   pydantic
+    #   pydantic-core
+    #   typer
+tzdata==2025.1
+    # via pandas
+urllib3==2.3.0
+    # via requests
+uvicorn==0.34.0
+    # via gradio
+websockets==15.0
+    # via gradio-client
+yarl==1.18.3
+    # via aiohttp
+zipp==3.21.0
+    # via importlib-metadata