Upload 4 files

README.md

@@ -1,15 +1,13 @@
 ---
-title: Template Final Assignment
-emoji: 🕵🏻‍♂️
-colorFrom: indigo
-colorTo: indigo
+title: AgenticRAG
+emoji: 🌖
+colorFrom: pink
+colorTo: pink
 sdk: gradio
-sdk_version: 5.25.2
+sdk_version: 5.29.1
 app_file: app.py
 pinned: false
-hf_oauth: true
-# optional, default duration is 8 hours/480 minutes. Max duration is 30 days/43200 minutes.
-hf_oauth_expiration_minutes: 480
+license: apache-2.0
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -1,380 +1,31 @@
-import os
 import gradio as gr
-import requests
-import inspect
-import pandas as pd
-from text_analyzer import TextAnalyzer
-import json
+import random
+from smolagents import GradioUI, CodeAgent, HfApiModel
 
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+# Import our custom tools from their modules
+from tools import DuckDuckGoSearchTool, CurrencyConverterTool
+from retriever import load_guest_dataset
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-        self.analyzer = TextAnalyzer()
-        
-    def __call__(self, text: str) -> str:
-        print(f"Agent received text (first 50 chars): {text[:50]}...")
-        try:
-            resultado = self.analyzer(text)
-            
-            # Formatear la respuesta según el tipo de texto
-            if resultado.get("tipo") == "historia_usuario":
-                return self._format_user_story_response(resultado)
-            elif resultado.get("tipo") == "pregunta_general":
-                return self._format_general_question_response(resultado)
-            else:
-                return f"Error: {resultado.get('error', 'Tipo de texto no reconocido')}"
-        except Exception as e:
-            error_msg = f"Error analizando el texto: {str(e)}"
-            print(error_msg)
-            return error_msg
-    
-    def _format_user_story_response(self, resultado: dict) -> str:
-        """Formatea la respuesta para una historia de usuario."""
-        respuesta = []
-        if resultado["tiene_ambiguedad"]:
-            respuesta.append("Se encontraron las siguientes ambigüedades:")
-            
-            if resultado["ambiguedad_lexica"]:
-                respuesta.append("\nAmbigüedades léxicas:")
-                for amb in resultado["ambiguedad_lexica"]:
-                    respuesta.append(f"- {amb}")
-            
-            if resultado["ambiguedad_sintactica"]:
-                respuesta.append("\nAmbigüedades sintácticas:")
-                for amb in resultado["ambiguedad_sintactica"]:
-                    respuesta.append(f"- {amb}")
-            
-            respuesta.append(f"\nScore de ambigüedad: {resultado['score_ambiguedad']}")
-            respuesta.append("\nSugerencias de mejora:")
-            for sug in resultado["sugerencias"]:
-                respuesta.append(f"- {sug}")
-        else:
-            respuesta.append("No se encontraron ambigüedades en la historia de usuario.")
-            respuesta.append(f"Score de ambigüedad: {resultado['score_ambiguedad']}")
-        
-        return "\n".join(respuesta)
-    
-    def _format_general_question_response(self, resultado: dict) -> str:
-        """Formatea la respuesta para una pregunta general."""
-        analisis = resultado["analisis"]
-        respuesta = []
-        
-        respuesta.append("📝 Análisis de la pregunta:")
-        if analisis["is_question"]:
-            respuesta.append(f"• Tipo de pregunta: {analisis['question_type'] or 'No identificado'}")
-        
-        if analisis["entities"]:
-            respuesta.append("\n🏷️ Entidades identificadas:")
-            for ent, label in analisis["entities"]:
-                respuesta.append(f"• {ent} ({label})")
-        
-        if analisis["key_phrases"]:
-            respuesta.append("\n🔑 Frases clave identificadas:")
-            for phrase in analisis["key_phrases"]:
-                respuesta.append(f"• {phrase}")
-        
-        if resultado["sugerencias"]:
-            respuesta.append("\n💡 Sugerencias:")
-            for sug in resultado["sugerencias"]:
-                respuesta.append(f"• {sug}")
-        
-        return "\n".join(respuesta)
+# Initialize the Hugging Face model
+model = HfApiModel()
 
-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
+# Initialize the web search tool
+search_tool = DuckDuckGoSearchTool()
 
-    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
+# Initialize the weather tool
+currency_converter_tool = CurrencyConverterTool()
 
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
-    try:
-        agent = BasicAgent()
-    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)
+# Load the guest dataset and initialize the guest info tool
+guest_info_tool = load_guest_dataset()
 
-    # 2. Fetch Questions
-    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
-        print(f"Fetched {len(questions_data)} questions.")
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
-    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
-    except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
-
-    # 3. Run your Agent
-    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)
-            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)
-
-    # 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}")
-    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"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            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}."
-        try:
-            error_json = e.response.json()
-            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
-
-
-# Inicializar el clasificador
-classifier = TextAnalyzer()
-
-def analyze_text(text: str) -> str:
-    """Analiza un texto y determina automáticamente si es una historia de usuario o una pregunta general."""
-    if not text.strip():
-        return "Por favor, ingrese un texto para analizar."
-    
-    # Analizar el texto
-    result = classifier(text)
-    
-    # Formatear resultados según el tipo
-    output = []
-    output.append(f"📝 Texto analizado:\n{text}\n")
-    
-    if result.get("tipo") == "historia_usuario":
-        output.append("📋 Tipo: Historia de Usuario")
-        output.append(f"🎯 Score de ambigüedad: {result['score_ambiguedad']}")
-        
-        if result['ambiguedad_lexica']:
-            output.append("\n📚 Ambigüedades léxicas encontradas:")
-            for amb in result['ambiguedad_lexica']:
-                output.append(f"• {amb}")
-        
-        if result['ambiguedad_sintactica']:
-            output.append("\n🔍 Ambigüedades sintácticas encontradas:")
-            for amb in result['ambiguedad_sintactica']:
-                output.append(f"• {amb}")
-        
-        if result['sugerencias']:
-            output.append("\n💡 Sugerencias de mejora:")
-            for sug in result['sugerencias']:
-                output.append(f"• {sug}")
-    
-    elif result.get("tipo") == "pregunta_general":
-        output.append("📋 Tipo: Pregunta General")
-        analisis = result['analisis']
-        
-        if analisis['is_question']:
-            output.append(f"❓ Tipo de pregunta: {analisis['question_type'] or 'No identificado'}")
-        
-        if analisis['entities']:
-            output.append("\n🏷️ Entidades identificadas:")
-            for ent, label in analisis['entities']:
-                output.append(f"• {ent} ({label})")
-        
-        if analisis['key_phrases']:
-            output.append("\n🔑 Frases clave:")
-            for phrase in analisis['key_phrases']:
-                output.append(f"• {phrase}")
-        
-        output.append("\n💡 Sugerencias:")
-        for sug in result['sugerencias']:
-            output.append(f"• {sug}")
-    
-    else:
-        output.append("❌ Error: No se pudo determinar el tipo de texto")
-    
-    return "\n".join(output)
-
-def analyze_multiple_texts(texts: str) -> str:
-    """Analiza múltiples textos separados por líneas."""
-    if not texts.strip():
-        return "Por favor, ingrese al menos un texto para analizar."
-    
-    texts_list = [t.strip() for t in texts.split('\n') if t.strip()]
-    all_results = []
-    
-    for text in texts_list:
-        result = classifier(text)
-        result["texto_original"] = text
-        all_results.append(result)
-    
-    return json.dumps(all_results, indent=2, ensure_ascii=False)
-
-# --- Build Gradio Interface using Blocks ---
-with gr.Blocks(title="Analizador de Textos") as demo:
-    gr.Markdown("""
-    # 🔍 Analizador de Textos
-
-    Esta herramienta analiza dos tipos de texto:
-    1. **Historias de Usuario**: Detecta ambigüedades léxicas y sintácticas
-    2. **Preguntas Generales**: Analiza estructura y contexto
-    
-    ## 📝 Instrucciones:
-    1. Ingrese su texto en el campo correspondiente
-    2. El sistema detectará automáticamente el tipo de texto
-    3. Revise el análisis detallado y las sugerencias
-    """)
-
-    with gr.Tab("Análisis Individual"):
-        input_text = gr.Textbox(
-            label="Texto a Analizar",
-            placeholder="Ingrese una historia de usuario o una pregunta general...",
-            lines=3
-        )
-        analyze_btn = gr.Button("Analizar")
-        output = gr.Textbox(
-            label="Resultados del Análisis",
-            lines=10
-        )
-        analyze_btn.click(
-            analyze_text,
-            inputs=[input_text],
-            outputs=[output]
-        )
-    
-    with gr.Tab("Análisis Múltiple"):
-        input_texts = gr.Textbox(
-            label="Textos a Analizar (uno por línea)",
-            placeholder="Como usuario quiero...\n¿Cuál es el proceso para...?\n",
-            lines=5
-        )
-        analyze_multi_btn = gr.Button("Analizar Todos")
-        output_json = gr.JSON(label="Resultados del Análisis")
-        analyze_multi_btn.click(
-            analyze_multiple_texts,
-            inputs=[input_texts],
-            outputs=[output_json]
-        )
-    
-    gr.Markdown("""
-    ## 🚀 Ejemplos
-
-    ### Historias de Usuario:
-    - Como usuario quiero un sistema rápido y eficiente para gestionar mis tareas
-    - El sistema debe permitir exportar varios tipos de archivos
-    - Como administrador necesito acceder fácilmente a los reportes
-
-    ### Preguntas Generales:
-    - ¿Cuál es el proceso para recuperar una contraseña olvidada?
-    - ¿Cómo puedo generar un reporte mensual de ventas?
-    - ¿Dónde encuentro la documentación del API?
-    """)
-
-    gr.LoginButton()
-
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    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]
-    )
+# Create Alfred with all the tools
+alfred = CodeAgent(
+    tools=[currency_converter_tool, search_tool], 
+    model=model,
+    add_base_tools=True,  # Add any additional base tools
+    planning_interval=3   # Enable planning every 3 steps
+)
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
-        print(f"✅ SPACE_ID found: {space_id_startup}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    GradioUI(alfred).launch()

requirements.txt

@@ -1,15 +1,5 @@
-gradio>=5.25.2
-requests>=2.31.0
-spacy>=3.7.0
-es-core-news-sm @ https://github.com/explosion/spacy-models/releases/download/es_core_news_sm-3.7.0/es_core_news_sm-3.7.0-py3-none-any.whl
-transformers>=4.30.0
-torch>=2.0.0
-numpy>=1.24.0
-pandas>=2.2.0
-pytesseract>=0.3.10
-opencv-python>=4.8.0
-librosa>=0.10.1
-Pillow>=10.0.0
-openpyxl>=3.1.2
-scikit-learn>=1.3.0
-setuptools>=69.1.0
+datasets 
+smolagents 
+langchain-community 
+rank_bm25
+duckduckgo-search

tools.py

@@ -0,0 +1,62 @@
+from smolagents import DuckDuckGoSearchTool
+from smolagents import Tool
+
+
+# Initialize the DuckDuckGo search tool
+search_tool = DuckDuckGoSearchTool()
+
+
+import random
+
+class CurrencyConverterTool(Tool):
+    name = "currency_converter"
+    description = "Converts amounts between different currencies using dummy exchange rates."
+    inputs = {
+        "amount": {
+            "type": "float",
+            "description": "The amount to convert."
+        },
+        "from_currency": {
+            "type": "string",
+            "description": "The source currency code (e.g., USD, EUR, CLP)."
+        },
+        "to_currency": {
+            "type": "string",
+            "description": "The target currency code (e.g., USD, EUR, CLP)."
+        }
+    }
+    output_type = "string"
+
+    def forward(self, amount: float, from_currency: str, to_currency: str):
+        # Dummy exchange rates (base: USD)
+        exchange_rates = {
+            "USD": 1.0,
+            "EUR": 0.85,
+            "CLP": 800.0,
+            "ARS": 350.0,
+            "BRL": 5.2,
+            "MXN": 18.5,
+            "GBP": 0.75,
+            "JPY": 110.0,
+            "CAD": 1.25
+        }
+        
+        # Validate currencies
+        if from_currency not in exchange_rates or to_currency not in exchange_rates:
+            available_currencies = ", ".join(exchange_rates.keys())
+            return f"Error: Moneda no soportada. Divisas disponibles: {available_currencies}"
+        
+        # Same currency conversion
+        if from_currency == to_currency:
+            return f"{amount:.2f} {from_currency} = {amount:.2f} {to_currency} (misma divisa)"
+        
+        # Convert to USD first, then to target currency
+        usd_amount = amount / exchange_rates[from_currency]
+        converted_amount = usd_amount * exchange_rates[to_currency]
+        
+        # Add small random variation to simulate real market fluctuations (±2%)
+        variation = random.uniform(-0.02, 0.02)
+        converted_amount *= (1 + variation)
+        
+        return f"{amount:.2f} {from_currency} = {converted_amount:.2f} {to_currency} (tasa simulada)"
+