Initial commit

_tools.py

@@ -0,0 +1,148 @@
+import requests
+import io
+
+import pandas as pd
+from PIL import Image
+from llama_index.tools.duckduckgo import DuckDuckGoSearchToolSpec
+from llama_index.core.tools import FunctionTool
+from huggingface_hub import InferenceClient
+
+client = InferenceClient(
+    provider="hf-inference",
+)
+
+
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+search_tool_spec = DuckDuckGoSearchToolSpec()
+
+# Searching tools
+def _search_tool(query: str) -> str:
+    """Browse the web using DuckDuckGo."""
+    print(f"🔍 Executando busca no DuckDuckGo para: {query}")
+    
+    return search_tool_spec.duckduckgo_full_search(query=query)
+  
+def _fetch_file_bytes(task_id: str) -> str | None:
+    """
+    Fetch a file from the given task ID.
+    """
+    
+    try:
+        response = requests.get(f"{DEFAULT_API_URL}/files/{task_id}", timeout=15)
+        response.raise_for_status()
+
+        print(f"File {task_id} fetched successfully.")
+        return response.content
+    
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching file {task_id}: {e}")
+        return None
+  
+# Parsing tools
+def _bytes_to_image(image_bytes: bytes) -> Image:
+    """Convert bytes to image URL."""
+    
+    file = Image.open(io.BytesIO(image_bytes))
+    
+    file.save("temp_image.png")
+
+    return file
+
+def _document_bytes_to_text(doc_bytes: bytes) -> str:
+    """Convert document bytes to text.""" 
+    return doc_bytes.decode("utf-8")
+  
+def _xlsx_to_text(file_bytes: bytes) -> str:
+    """Convert XLSX file bytes to text using pandas."""
+    io_bytes = io.BytesIO(file_bytes)
+    df = pd.read_excel(io_bytes, engine='openpyxl')
+    
+    return df.to_string(index=False)
+
+# Extracting text tools
+def _extract_text_from_image(image_url: bytes) -> str:
+    """Extract text from an image using Tesseract."""
+    return client.image_to_text(image_url=image_url, task="image-to-text", model="Salesforce/blip-image-captioning-base").generated_text
+  
+def _extract_text_from_csv(file_bytes: bytes) -> str:
+    """Extract text from a CSV file."""
+    io_bytes = io.BytesIO(file_bytes)
+    df = pd.read_csv(io_bytes)
+    
+    return df.to_string(index=False)
+    
+def _extract_text_from_code_file(bytes: bytes) -> str:
+    """Extract text from a code file."""
+    return bytes.decode("utf-8")
+  
+def _extract_text_from_audio_file(file_bytes: bytes) -> str:
+    """Extract text from an audio file."""
+    return client.automatic_speech_recognition(file_bytes, model="openai/whisper-large-v2").text
+
+# Initialize tools
+search_tool = FunctionTool.from_defaults(
+  _search_tool,
+  name="DuckDuckGo Search",
+  description="Search the web using DuckDuckGo."
+)
+
+fetch_file_bytes_tool = FunctionTool.from_defaults(
+  _fetch_file_bytes,
+  name="Fetch File Bytes",
+  description="Fetch a file from the given task ID."
+)
+
+bytes_to_image_tool = FunctionTool.from_defaults(
+  _bytes_to_image,
+  name="Bytes to Image",
+  description="Convert bytes to image URL."
+)
+
+document_bytes_to_text_tool = FunctionTool.from_defaults(
+  _document_bytes_to_text,
+  name="Document Bytes to Text",
+  description="Convert bytes to document text, i.e., .txt, .pdf, etc."
+)
+
+xlsx_to_text_tool = FunctionTool.from_defaults(
+  _xlsx_to_text,
+  name="XLSX to Text",
+  description="Convert XLSX file bytes to text."
+)
+
+extract_text_from_image_tool = FunctionTool.from_defaults(
+  _extract_text_from_image,
+  name="Extract Text from Image",
+  description="Extract text from an image using Tesseract."
+)
+
+extract_text_from_csv_tool = FunctionTool.from_defaults(
+  _extract_text_from_csv,
+  name="Extract Text from CSV",
+  description="Extract text from a CSV file."
+)
+
+extract_text_from_code_file_tool = FunctionTool.from_defaults(
+  _extract_text_from_code_file,
+  name="Extract Text from Code File",
+  description="Extract text from a code file, i.e., .py, .js, .java, etc."
+)
+
+extract_text_from_audio_file_tool = FunctionTool.from_defaults(
+  _extract_text_from_audio_file,
+  name="Extract Text from Audio File",
+  description="Extract text from an audio file."
+)
+
+tools = [
+  search_tool,
+  fetch_file_bytes_tool,
+  bytes_to_image_tool,
+  document_bytes_to_text_tool,
+  extract_text_from_image_tool,
+  extract_text_from_csv_tool,
+  extract_text_from_code_file_tool,
+  extract_text_from_audio_file_tool,
+  xlsx_to_text_tool,
+]
+

_types.py

@@ -0,0 +1,10 @@
+from typing import TypedDict, Optional, List
+
+class Question(TypedDict):
+    task_id: str
+    question: str
+    file_name: Optional[str] = None
+    
+    
+# A list of questions based on Question type
+Questions = List[Question]

app.py

@@ -1,8 +1,15 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from _types import Questions, Question
+from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
+from llama_index.core.agent.workflow import AgentWorkflow
+from _tools import tools
+import asyncio
+from huggingface_hub import login
+
+login()
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -13,95 +20,143 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 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
+        
+        llm = HuggingFaceInferenceAPI(model_name="Qwen/Qwen2.5-Coder-32B-Instruct")
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+        agent = AgentWorkflow.from_tools_or_functions(
+            tools,
+            llm=llm,
+            verbose=True
+        )
+        
+        self.agent = agent
 
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+    async def run(self, question: Question) -> str:
+        question_text = question["question"]
+        task_id = question["task_id"]
+        file_name = question.get("file_name")
+        
+        """
+        Run the agent with the provided question and return the answer.
+        """
+        print(f"Agent received question (first 50 chars): {question_text[:50]}...")
+        
+        prompt = f"""
+        You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: 
+        YOUR ANSWER. 
+        
+        YOUR ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. 
+        If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. 
+        If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless 
+        specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in 
+        the list is a number or a string.\n
+        
+        The question is: {question_text}\n
+        
+        If the question has a file, the file name is the task ID: {task_id}. You can use it to fetch the bytes of the file and parse
+        as you want. The file name is: {file_name}.\n
+        """
 
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+        answer = await self.agent.run(prompt)
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+        print(f"Agent returning answer: {answer}")
+        
+        return answer
+
+def instantiate_agent():
     try:
         agent = BasicAgent()
+        
+        return agent, 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)
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
+        
+        return None, f"Error initializing agent: {e}"
 
-    # 2. Fetch Questions
+def fetch_questions(questions_url):
     print(f"Fetching questions from: {questions_url}")
+    
     try:
         response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
-        if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
+        
+        if not questions_data: 
+            print("Fetched questions list is empty.")
+            
+            return None, "Fetched questions list is empty or invalid format."
+        
         print(f"Fetched {len(questions_data)} questions.")
+        
+        return questions_data, None
+    
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
+        
+        return None, f"Error fetching questions: {e}"
+    
     except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
+        print(f"Error decoding JSON response from questions endpoint: {e}")
+        print(f"Response text: {response.text[:500]}")
+        
+        return None, f"Error decoding server response for questions: {e}"
+    
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        
+        return None, f"An unexpected error occurred fetching questions: {e}"
 
-    # 3. Run your Agent
+async def fetch_file(question: Question) -> str | None:
+    """
+    Fetch files from the provided list of file paths.
+    """
+    file_url = f"{DEFAULT_API_URL}/files"
+    
+    try:
+        response = requests.get(f"{file_url}/{question['task_id']}", timeout=15)
+        response.raise_for_status()
+
+        print(f"File {question['task_id']} fetched successfully.")
+        return response.content
+    
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching file {question['task_id']}: {e}")
+        return None
+
+async def run_agent_on_questions(agent: BasicAgent, questions_data: Questions):
     results_log = []
     answers_payload = []
+    
     print(f"Running agent on {len(questions_data)} questions...")
+    
     for item in questions_data:
         task_id = item.get("task_id")
         question_text = item.get("question")
+        
         if not task_id or question_text is None:
             print(f"Skipping item with missing task_id or question: {item}")
             continue
+
         try:
-            submitted_answer = agent(question_text)
+            submitted_answer = await agent.run(item)
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+            
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-
-    if not answers_payload:
-        print("Agent did not produce any answers to submit.")
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+            print(f"Error running agent on task {task_id}: {e}")
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            
+    return answers_payload, results_log
 
-    # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-    print(status_update)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+def submit_answers(submit_url, submission_data, results_log):
+    print(f"Submitting {len(submission_data['answers'])} answers to: {submit_url}")
+    
     try:
         response = requests.post(submit_url, json=submission_data, timeout=60)
         response.raise_for_status()
         result_data = response.json()
+        
         final_status = (
             f"Submission Successful!\n"
             f"User: {result_data.get('username')}\n"
@@ -109,8 +164,10 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
             f"Message: {result_data.get('message', 'No message received.')}"
         )
+        
         print("Submission successful.")
         results_df = pd.DataFrame(results_log)
+        
         return final_status, results_df
     except requests.exceptions.HTTPError as e:
         error_detail = f"Server responded with status {e.response.status_code}."
@@ -119,26 +176,84 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
         except requests.exceptions.JSONDecodeError:
             error_detail += f" Response: {e.response.text[:500]}"
+            
         status_message = f"Submission Failed: {error_detail}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
+        
         return status_message, results_df
+    
     except requests.exceptions.Timeout:
         status_message = "Submission Failed: The request timed out."
         print(status_message)
         results_df = pd.DataFrame(results_log)
+        
         return status_message, results_df
+    
     except requests.exceptions.RequestException as e:
         status_message = f"Submission Failed: Network error - {e}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
+        
         return status_message, results_df
+    
     except Exception as e:
         status_message = f"An unexpected error occurred during submission: {e}"
         print(status_message)
         results_df = pd.DataFrame(results_log)
+        
         return status_message, results_df
 
+async def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    and displays the results.
+    """
+    space_id = os.getenv("SPACE_ID")
+    
+    if profile:
+        username = f"{profile.username}"
+        print(f"User logged in: {username}")
+    else:
+        print("User not logged in.")
+        return "Please Login to Hugging Face with the button.", None
+
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+    
+
+    agent, agent_error = instantiate_agent()
+    
+    if agent_error:
+        return agent_error, None
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+    print(agent_code)
+    questions_data, questions_error = fetch_questions(questions_url)
+    
+    if questions_error:
+        return questions_error, None
+
+    answers_payload, results_log = await run_agent_on_questions(agent, questions_data)
+
+    if not answers_payload:
+        print("Agent did not produce any answers to submit.")
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+
+    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
+    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+    print(status_update)
+
+    return submit_answers(submit_url, submission_data, results_log)
+
+
+
+async def main():
+    await run_and_submit_all(profile=None)
+
+loop = asyncio.get_event_loop()
+loop.run_until_complete(main())
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:

requirements.txt

@@ -1,2 +1,196 @@
-gradio
-requests
+accelerate==1.6.0
+aiofiles==24.1.0
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.18
+aiosignal==1.3.2
+annotated-types==0.7.0
+anthropic==0.50.0
+anyio==4.9.0
+asgiref==3.8.1
+asyncio==3.4.3
+attrs==25.3.0
+backoff==2.2.1
+banks==2.1.2
+bcrypt==4.3.0
+beautifulsoup4==4.13.4
+bm25s==0.2.12
+boto3==1.38.8
+botocore==1.38.8
+build==1.2.2.post1
+cachetools==5.5.2
+certifi==2025.4.26
+charset-normalizer==3.4.2
+chroma-hnswlib==0.7.6
+chromadb==1.0.7
+click==8.1.8
+colorama==0.4.6
+coloredlogs==15.0.1
+dataclasses-json==0.6.7
+datasets==3.5.1
+Deprecated==1.2.18
+dill==0.3.8
+dirtyjson==1.0.8
+distro==1.9.0
+duckduckgo_search==6.4.2
+durationpy==0.9
+et_xmlfile==2.0.0
+fastapi==0.115.9
+ffmpy==0.5.0
+filelock==3.18.0
+filetype==1.2.0
+flatbuffers==25.2.10
+frozenlist==1.6.0
+fsspec==2025.3.0
+google-auth==2.39.0
+googleapis-common-protos==1.70.0
+gradio==5.29.0
+gradio_client==1.10.0
+greenlet==3.2.1
+griffe==1.7.3
+groovy==0.1.2
+grpcio==1.71.0
+h11==0.16.0
+httpcore==1.0.9
+httptools==0.6.4
+httpx==0.28.1
+huggingface-hub==0.30.2
+humanfriendly==10.0
+idna==3.10
+importlib_metadata==8.6.1
+importlib_resources==6.5.2
+Jinja2==3.1.6
+jiter==0.9.0
+jmespath==1.0.1
+joblib==1.5.0
+jsonschema==4.23.0
+jsonschema-specifications==2025.4.1
+kubernetes==32.0.1
+llama-cloud==0.1.19
+llama-cloud-services==0.6.21
+llama-index==0.12.34
+llama-index-agent-openai==0.4.7
+llama-index-cli==0.4.1
+llama-index-core==0.12.34.post1
+llama-index-embeddings-huggingface==0.5.3
+llama-index-embeddings-openai==0.3.1
+llama-index-indices-managed-llama-cloud==0.6.11
+llama-index-llms-anthropic==0.6.10
+llama-index-llms-huggingface==0.5.0
+llama-index-llms-huggingface-api==0.4.2
+llama-index-llms-llama-api==0.4.0
+llama-index-llms-openai==0.3.38
+llama-index-llms-openai-like==0.3.4
+llama-index-multi-modal-llms-openai==0.4.3
+llama-index-program-openai==0.3.1
+llama-index-question-gen-openai==0.3.0
+llama-index-readers-file==0.4.7
+llama-index-readers-llama-parse==0.4.0
+llama-index-retrievers-bm25==0.5.2
+llama-index-tools-duckduckgo==0.3.0
+llama-index-vector-stores-chroma==0.4.1
+llama-parse==0.6.21
+markdown-it-py==3.0.0
+markdownify==1.1.0
+MarkupSafe==3.0.2
+marshmallow==3.26.1
+mdurl==0.1.2
+mmh3==5.1.0
+mpmath==1.3.0
+multidict==6.4.3
+multiprocess==0.70.16
+mypy_extensions==1.1.0
+nest-asyncio==1.6.0
+networkx==3.4.2
+nltk==3.9.1
+numpy==2.2.5
+oauthlib==3.2.2
+onnxruntime==1.21.1
+openai==1.77.0
+openpyxl==3.1.5
+opentelemetry-api==1.32.1
+opentelemetry-exporter-otlp-proto-common==1.32.1
+opentelemetry-exporter-otlp-proto-grpc==1.32.1
+opentelemetry-instrumentation==0.53b1
+opentelemetry-instrumentation-asgi==0.53b1
+opentelemetry-instrumentation-fastapi==0.53b1
+opentelemetry-proto==1.32.1
+opentelemetry-sdk==1.32.1
+opentelemetry-semantic-conventions==0.53b1
+opentelemetry-util-http==0.53b1
+orjson==3.10.18
+overrides==7.7.0
+packaging==25.0
+pandas==2.2.3
+pillow==11.2.1
+platformdirs==4.3.7
+posthog==4.0.1
+primp==0.15.0
+propcache==0.3.1
+protobuf==5.29.4
+psutil==7.0.0
+pyarrow==20.0.0
+pyasn1==0.6.1
+pyasn1_modules==0.4.2
+pydantic==2.11.4
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.1
+pypdf==5.4.0
+PyPika==0.48.9
+pyproject_hooks==1.2.0
+pyreadline3==3.5.4
+PyStemmer==2.2.0.3
+pytesseract==0.3.13
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+python-multipart==0.0.20
+pytz==2025.2
+PyYAML==6.0.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+requests-oauthlib==2.0.0
+rich==14.0.0
+rpds-py==0.24.0
+rsa==4.9.1
+ruff==0.11.8
+s3transfer==0.12.0
+safehttpx==0.1.6
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.2
+semantic-version==2.10.0
+sentence-transformers==4.1.0
+shellingham==1.5.4
+six==1.17.0
+smolagents==1.14.0
+sniffio==1.3.1
+soupsieve==2.7
+SpeechRecognition==3.14.2
+SQLAlchemy==2.0.40
+starlette==0.45.3
+striprtf==0.0.26
+sympy==1.14.0
+tenacity==9.1.2
+tesseract==0.1.3
+threadpoolctl==3.6.0
+tiktoken==0.9.0
+tokenizers==0.21.1
+tomlkit==0.13.2
+torch==2.7.0
+tqdm==4.67.1
+transformers==4.51.3
+typer==0.15.3
+typing-inspect==0.9.0
+typing-inspection==0.4.0
+typing_extensions==4.13.2
+tzdata==2025.2
+urllib3==2.4.0
+uvicorn==0.34.2
+watchfiles==1.0.5
+websocket-client==1.8.0
+websockets==15.0.1
+wrapt==1.17.2
+xxhash==3.5.0
+yarl==1.20.0
+zipp==3.21.0