Release v4

agent.py

@@ -1,4 +1,4 @@
-from typing import Any, Optional
+from typing import Any, List, Optional
 
 from smolagents import CodeAgent
 
@@ -8,15 +8,24 @@ logger = get_logger(__name__)
 
 
 class Agent:
+    """
+    Agent class that wraps a CodeAgent and provides a callable interface for answering questions.
+
+    Args:
+        model (Any): The language model to use.
+        tools (Optional[List[Any]]): List of tools to provide to the agent.
+        prompt (Optional[str]): Custom prompt template for the agent.
+    """
+
     def __init__(
-        self, model: Any, tools: Optional[list] = None, prompt: Optional[str] = None
+        self,
+        model: Any,
+        tools: Optional[List[Any]] = None,
+        prompt: Optional[str] = None,
     ):
         logger.info("Initializing Agent")
-
         self.model = model
-
         self.tools = tools
-
         self.imports = [
             "pandas",
             "numpy",
@@ -28,15 +37,14 @@ class Agent:
             "time",
             "re",
             "openpyxl",
+            "pathlib",
         ]
-
         self.agent = CodeAgent(
             model=self.model,
             tools=self.tools,
             add_base_tools=True,
             additional_authorized_imports=self.imports,
         )
-
         self.prompt = prompt or (
             """
             You are an advanced AI assistant specialized in solving complex, real-world tasks that require multi-step reasoning, factual accuracy, and use of external tools.
@@ -57,10 +65,19 @@ class Agent:
             ANSWER:
             """
         )
-
         logger.info("Agent initialized")
 
     def __call__(self, question: str, file_path: Optional[str] = None) -> str:
+        """
+        Run the agent to answer a question, optionally using a file as context.
+
+        Args:
+            question (str): The question to answer.
+            file_path (Optional[str]): Path to a file to use as context (if any).
+
+        Returns:
+            str: The agent's answer as a string.
+        """
         answer = self.agent.run(
             self.prompt.format(question=question, context=file_path)
         )

app.py

@@ -1,6 +1,7 @@
 import inspect
 import os
 import tempfile
+from typing import Any, Optional, Tuple
 
 import gradio as gr
 import pandas as pd
@@ -17,21 +18,19 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
 
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
 
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
+def run_and_submit_all(
+    profile: Optional[gr.OAuthProfile],
+) -> Tuple[str, Optional[pd.DataFrame]]:
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Fetches all questions, runs the Agent on them, submits all answers, and displays the results.
+
+    Args:
+        profile (Optional[gr.OAuthProfile]): The OAuth profile of the user.
+
+    Returns:
+        Tuple[str, Optional[pd.DataFrame]]: Status message and DataFrame of results.
     """
     # --- Determine HF Space Runtime URL and Repo URL ---
     space_id = "exsandebest/agent-course-final-assessment"  # Get the SPACE_ID for sending link to the code
@@ -56,7 +55,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+    # In the case of an app running as a hugging Face space, this link points toward your codebase (usefull for others so please keep it public)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
@@ -92,7 +91,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-            file_path = None
+            file_path: Optional[str] = None
             try:
                 file_response = requests.get(f"{files_url}/{task_id}", timeout=15)
                 if file_response.status_code == 200 and file_response.content:
@@ -207,7 +206,6 @@ with gr.Blocks() as demo:
     status_output = gr.Textbox(
         label="Run Status / Submission Result", lines=5, interactive=False
     )
-    # Removed max_rows=10 from DataFrame constructor
     results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
 
     run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])

model.py

@@ -1,10 +1,20 @@
 import os
-from typing import Any
+from typing import Any, Callable
 
 from smolagents import HfApiModel, InferenceClientModel, LiteLLMModel, OpenAIServerModel
 
 
-def get_huggingface_api_model(model_id: str, **kwargs) -> Any:
+def get_huggingface_api_model(model_id: str, **kwargs) -> HfApiModel:
+    """
+    Returns a Hugging Face API model instance.
+
+    Args:
+        model_id (str): The model identifier.
+        **kwargs: Additional keyword arguments for the model.
+
+    Returns:
+        HfApiModel: Hugging Face API model instance.
+    """
     api_key = os.getenv("HUGGINGFACEHUB_API_TOKEN")
     if not api_key:
         raise ValueError("HUGGINGFACEHUB_API_TOKEN is not set")
@@ -12,7 +22,17 @@ def get_huggingface_api_model(model_id: str, **kwargs) -> Any:
     return HfApiModel(model_id=model_id, token=api_key, **kwargs)
 
 
-def get_inference_client_model(model_id: str, **kwargs) -> Any:
+def get_inference_client_model(model_id: str, **kwargs) -> InferenceClientModel:
+    """
+    Returns an Inference Client model instance.
+
+    Args:
+        model_id (str): The model identifier.
+        **kwargs: Additional keyword arguments for the model.
+
+    Returns:
+        InferenceClientModel: Inference client model instance.
+    """
     api_key = os.getenv("HUGGINGFACEHUB_API_TOKEN")
     if not api_key:
         raise ValueError("HUGGINGFACEHUB_API_TOKEN is not set")
@@ -20,7 +40,17 @@ def get_inference_client_model(model_id: str, **kwargs) -> Any:
     return InferenceClientModel(model_id=model_id, token=api_key, **kwargs)
 
 
-def get_openai_server_model(model_id: str, **kwargs) -> Any:
+def get_openai_server_model(model_id: str, **kwargs) -> OpenAIServerModel:
+    """
+    Returns an OpenAI server model instance.
+
+    Args:
+        model_id (str): The model identifier.
+        **kwargs: Additional keyword arguments for the model.
+
+    Returns:
+        OpenAIServerModel: OpenAI server model instance.
+    """
     api_key = os.getenv("OPENAI_API_KEY")
     if not api_key:
         raise ValueError("OPENAI_API_KEY is not set")
@@ -34,13 +64,33 @@ def get_openai_server_model(model_id: str, **kwargs) -> Any:
     )
 
 
-def get_lite_llm_model(model_id: str, **kwargs) -> Any:
+def get_lite_llm_model(model_id: str, **kwargs) -> LiteLLMModel:
+    """
+    Returns a LiteLLM model instance.
+
+    Args:
+        model_id (str): The model identifier.
+        **kwargs: Additional keyword arguments for the model.
+
+    Returns:
+        LiteLLMModel: LiteLLM model instance.
+    """
     return LiteLLMModel(model_id=model_id, **kwargs)
 
 
 def get_model(model_type: str, model_id: str, **kwargs) -> Any:
-
-    models = {
+    """
+    Returns a model instance based on the specified type.
+
+    Args:
+        model_type (str): The type of the model (e.g., 'HfApiModel').
+        model_id (str): The model identifier.
+        **kwargs: Additional keyword arguments for the model.
+
+    Returns:
+        Any: Model instance of the specified type.
+    """
+    models: dict[str, Callable[..., Any]] = {
         "HfApiModel": get_huggingface_api_model,
         "InferenceClientModel": get_inference_client_model,
         "OpenAIServerModel": get_openai_server_model,

requirements.txt

@@ -2,6 +2,8 @@ gradio
 numpy
 openpyxl
 pandas
+pillow
+pytesseract
 requests
 smolagents
 smolagents[audio]

tools.py

@@ -1,3 +1,7 @@
+from typing import Any, List
+
+import pytesseract
+from PIL import Image
 from smolagents import (
     DuckDuckGoSearchTool,
     PythonInterpreterTool,
@@ -10,6 +14,16 @@ from youtube_transcript_api import YouTubeTranscriptApi
 
 
 class YouTubeTranscriptionTool(Tool):
+    """
+    Tool to fetch the transcript of a YouTube video given its URL.
+
+    Args:
+        video_url (str): YouTube video URL.
+
+    Returns:
+        str: Transcript of the video as a single string.
+    """
+
     name = "youtube_transcription"
     description = "Fetches the transcript of a YouTube video given its URL"
     inputs = {
@@ -23,7 +37,56 @@ class YouTubeTranscriptionTool(Tool):
         return " ".join([entry["text"] for entry in transcript])
 
 
-def get_tools():
+class ReadFileTool(Tool):
+    """
+    Tool to read a file and return its content.
+
+    Args:
+        file_path (str): Path to the file to read.
+
+    Returns:
+        str: Content of the file or error message.
+    """
+
+    name = "read_file"
+    description = "Reads a file and returns its content"
+    inputs = {
+        "file_path": {"type": "string", "description": "Path to the file to read"},
+    }
+    output_type = "string"
+
+    def forward(self, file_path: str) -> str:
+        try:
+            with open(file_path, "r") as file:
+                return file.read()
+        except Exception as e:
+            return f"Error reading file: {str(e)}"
+
+
+class ExtractTextFromImageTool(Tool):
+    name = "extract_text_from_image"
+    description = "Extracts text from an image using pytesseract"
+    inputs = {
+        "image_path": {"type": "string", "description": "Path to the image file"},
+    }
+    output_type = "string"
+
+    def forward(self, image_path: str) -> str:
+        try:
+            image = Image.open(image_path)
+            text = pytesseract.image_to_string(image)
+            return text
+        except Exception as e:
+            return f"Error extracting text from image: {str(e)}"
+
+
+def get_tools() -> List[Tool]:
+    """
+    Returns a list of available tools for the agent.
+
+    Returns:
+        List[Tool]: List of initialized tool instances.
+    """
     tools = [
         DuckDuckGoSearchTool(),
         PythonInterpreterTool(),
@@ -31,5 +94,7 @@ def get_tools():
         VisitWebpageTool(),
         SpeechToTextTool(),
         YouTubeTranscriptionTool(),
+        ReadFileTool(),
+        ExtractTextFromImageTool(),
     ]
     return tools

utils/logger.py

@@ -3,7 +3,7 @@ import logging
 
 def get_logger(name: str = __name__) -> logging.Logger:
     """
-    Create and configure a logger.
+    Create and configure a logger instance for the given module or name.
 
     Args:
         name (str, optional): Name of the logger. Defaults to the module name.