tools.py

import os
from smolagents import Tool, tool
from huggingface_hub import HfApi
from dotenv import load_dotenv
from huggingface_hub import InferenceClient
from utils import upload_file
load_dotenv()
HF_TOKEN = os.environ.get("HF_TOKEN")

api = HfApi()
client = InferenceClient(
    provider="hf-inference",
    api_key=HF_TOKEN,
)

# --- Constants ---
local_data_path = "../data"

if not os.path.exists(local_data_path):
    os.makedirs(local_data_path)



@tool
def image_question_answering(image_path: str, prompt: str) -> str:
    """
    This function takes a image path and a prompt, and returns the answer to the question.
    Args:
        image_path: The path to the image file
        prompt: The prompt to the question
    Returns:
        The answer to the question
    """
    file_extension = image_path.split(".")[-1]
    if file_extension in [".mp4", ".avi", ".mov", ".wmv", ".mkv", ".webm"]:
        return "Media type not supported. Please upload an image."
   
    if image_path.startswith("http"):
        media_url = image_path
    else:
        media_url = upload_file(image_path)

    
    messages = [
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": prompt,
                        },
                        {
                            "type": "image_url",
                            "image_url": {"url": media_url},
                        }
                    ],
                }
            ]

    completion = client.chat.completions.create(
            model="meta-llama/Llama-3.2-11B-Vision-Instruct",
            messages=messages,
    )
    return completion.choices[0].message


@tool
def transcribe_audio(file_local_path: str) -> str:
    """
    Transcribe the audio file and return the transcript
    Args:
        file_local_path: The local path to the audio file
    Returns:
        The transcript of the audio file
    """
    file_url = upload_file(file_local_path)

    asr_tool = Tool.from_space(
        "hf-audio/whisper-large-v3",
        api_name="/predict_1", # from file
        name="transcribe_audio",
        description="Use this tool to transcribe the audio"
    )

    transcript = asr_tool(file_url)
    return transcript


class GetFileTool(Tool):
    name = "get_file"
    description = "Download a file from the given file name"
    inputs = {
        "file_name": {
            "type": "string",
            "description": "Download the file from the given file name and outputs the local path"
        }

    }
    output_type = "string"

    def forward(self, file_name: str) -> str:
        import requests

        if file_name == "":
            return "No file name provided"

        task_id = file_name.split(".")[0]
        url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"
        headers = {
            "accept": "application/json"
        }
        req = requests.get(url, headers=headers)

        if req.status_code != 200:
            return "File not found, please check the file name and try again."
        
        local_file_path = local_data_path + "/" + file_name

        with open(local_file_path, "wb") as f:
            f.write(req.content)
        
        print(f"File saved to {local_file_path}. You can read this file to process its contents.")
        return local_file_path