import gradio as gr import matplotlib.pyplot as plt import pandas as pd import numpy as np from datetime import datetime from langchain_core.messages import HumanMessage from tools import tools from agents import * from config import * from workflow import create_workflow # Initialize workflow graph = create_workflow() # Helper Functions def run_graph(input_message, history, user_details): try: # Relevant fitness-related keywords to handle irrelevant user prompts relevant_keywords = [ "workout", "training", "exercise", "cardio", "strength training", "hiit (high-intensity interval training)", "flexibility", "yoga", "pilates", "aerobics", "crossfit", "bodybuilding", "endurance", "running", "cycling", "swimming", "martial arts", "stretching", "warm-up", "cool-down", "diet plan", "meal plan", "macronutrients", "micronutrients", "vitamins", "minerals", "protein", "carbohydrates", "fats", "calories", "calorie", "daily", "nutrition", "supplements", "hydration", "weightloss", "weight gain", "healthy eating", "health", "fitness", "intermittent fasting", "keto diet", "vegan diet", "paleo diet", "mediterranean diet", "gluten-free", "low-carb", "high-protein", "bmi", "calculate", "body mass index", "calculator", "mental health", "mindfulness", "meditation", "stress management", "anxiety relief", "depression", "positive thinking", "motivation", "self-care", "relaxation", "sleep hygiene", "therapy", "counseling", "cognitive-behavioral therapy (cbt)", "mood tracking", "mental", "emotional well-being", "healthy lifestyle", "fitness goals", "health routines", "daily habits", "ergonomics", "posture", "work-life balance", "workplace", "habit tracking", "goal setting", "personal growth", "injury prevention", "recovery", "rehabilitation", "physical therapy", "sports injuries", "pain management", "recovery techniques", "foam rolling", "stretching exercises", "injury management", "injuries", "apps", "health tracking", "wearable technology", "equipment", "home workouts", "gym routines", "outdoor activities", "sports", "wellness tips", "water", "adult", "adults", "child", "children", "infant", "sleep", "habit", "habits", "routine", "weight", "fruits", "vegetables", "lose", "lost weight", "weight-loss", "chicken", "veg", "vegetarian", "non-veg", "non-vegetarian", "plant", "plant-based", "plant based", "fat", "resources", "help", "cutting", "bulking", "link", "links", "website", "online", "websites", "peace", "mind", "equipments", "equipment", "watch", "tracker", "watch", "band", "height", "injured", "quick", "remedy", "solution", "solutions", "pain", "male", "female", "kilograms", "kg", "Pounds", "lbs" ] greetings = ["hello", "hi", "how are you doing"] if any(keyword in input_message.lower() for keyword in relevant_keywords): response = graph.invoke({ "messages": [HumanMessage(content=input_message)], "user_details": user_details # Pass user-specific data for customization }) return response['messages'][1].content elif any(keyword in input_message.lower() for keyword in greetings): return "Hi there, I am FIT bot, your personal wellbeing coach! Let me know your fitness goals or questions." else: return "I'm here to assist with fitness, nutrition, mental health, and related topics. Please ask questions related to these areas." except Exception as e: return f"An error occurred while processing your request: {e}" def calculate_bmi(height, weight, gender): try: height_m = height / 100 bmi = weight / (height_m ** 2) if bmi < 18.5: status = "underweight" elif 18.5 <= bmi < 24.9: status = "normal weight" elif 25 <= bmi < 29.9: status = "overweight" else: status = "obese" return bmi, status except Exception: return None, "Invalid height or weight provided." def visualize_bmi(bmi): try: categories = ["Underweight", "Normal Weight", "Overweight", "Obese"] x_pos = np.arange(len(categories)) colors = ['blue', 'green', 'orange', 'red'] plt.figure(figsize=(8, 4)) plt.bar(categories, [18.5, 24.9, 29.9, 40], color=colors, alpha=0.6) plt.axhline(y=bmi, color='purple', linestyle='--', linewidth=2, label=f"Your BMI: {bmi:.2f}") plt.ylabel("BMI Value") plt.title("BMI Visualization") plt.legend(loc="upper left") plt.tight_layout() plt_path = "bmi_chart.png" plt.savefig(plt_path) plt.close() return plt_path except Exception as e: return f"Error creating BMI visualization: {e}" def calculate_calories(age, weight, height, activity_level, gender): try: # Base Metabolic Rate (BMR) calculation if gender.lower() == "male": bmr = 10 * weight + 6.25 * height - 5 * age + 5 else: bmr = 10 * weight + 6.25 * height - 5 * age - 161 # Activity multiplier mapping activity_multipliers = { "Sedentary": 1.2, "Lightly active": 1.375, "Moderately active": 1.55, "Very active": 1.725, "Extra active": 1.9, } if activity_level in activity_multipliers: calories = bmr * activity_multipliers[activity_level] else: raise ValueError("Invalid activity level") return round(calories, 2) except Exception as e: return f"Error in calorie calculation: {e}" # Interface Components with gr.Blocks() as demo: gr.Markdown("# FIT.AI - Your Fitness and Wellbeing Coach") with gr.Tab("Chat with FIT.AI"): with gr.Row(): with gr.Column(): user_name = gr.Textbox(placeholder="Enter your name", label="Name") user_age = gr.Number(label="Age (years)", value=25, precision=0) user_gender = gr.Dropdown(choices=["Male", "Female"], label="Gender", value="Male") user_weight = gr.Number(label="Weight (kg)", value=70, precision=1) user_height = gr.Number(label="Height (cm)", value=170, precision=1) activity_level = gr.Dropdown( choices=["Sedentary", "Lightly active", "Moderately active", "Very active", "Extra active"], label="Activity Level", value="Moderately active" ) chatbot = gr.Chatbot(label="Chat with FIT.AI", type="messages") text_input = gr.Textbox(placeholder="Type your question here...", label="Your Question") submit_button = gr.Button("Submit") clear_button = gr.Button("Clear Chat") def submit_message(message, history=[]): user_details = { "name": user_name.value, "age": user_age.value, "weight": user_weight.value, "height": user_height.value, "activity_level": activity_level.value, "gender": user_gender.value } bmi, status = calculate_bmi(user_details["height"], user_details["weight"], user_details["gender"]) if bmi: bmi_path = visualize_bmi(bmi) calories = calculate_calories(user_details["age"], user_details["weight"], user_details["height"], user_details["activity_level"], user_details["gender"]) response = run_graph(message, history, user_details) history.append({"role": "user", "content": message}) history.append({"role": "assistant", "content": response + f"\nYour BMI is {bmi:.2f}, considered {status}.\nDaily calorie needs: {calories} kcal.", "image": bmi_path}) return history, "" else: history.append({"role": "assistant", "content": "Error in calculation."}) return history, "" submit_button.click(submit_message, inputs=[text_input, chatbot], outputs=[chatbot, text_input]) clear_button.click(lambda: ([], ""), inputs=None, outputs=[chatbot, text_input]) with gr.Tab("BMI and Calorie Calculator"): with gr.Row(): with gr.Column(): user_name = gr.Textbox(placeholder="Enter your name", label="Name") user_age = gr.Number(label="Age (years)", value=25, precision=0) user_gender = gr.Dropdown(choices=["Male", "Female"], label="Gender", value="Male") user_weight = gr.Number(label="Weight (kg)", value=70, precision=1) user_height = gr.Number(label="Height (cm)", value=170, precision=1) activity_level = gr.Dropdown( choices=["Sedentary", "Lightly active", "Moderately active", "Very active", "Extra active"], label="Activity Level", value="Moderately active" ) calculate_button = gr.Button("Calculate") with gr.Column(): bmi_output = gr.Label(label="BMI Result") calorie_output = gr.Label(label="Calorie Needs") bmi_chart = gr.Image(label="BMI Chart") def calculate_metrics(age, weight, height, gender, activity_level): bmi, status = calculate_bmi(height, weight, gender) if bmi: bmi_path = visualize_bmi(bmi) calories = calculate_calories(age, weight, height, activity_level, gender) return f"Your BMI is {bmi:.2f}, considered {status}.", f"Daily calorie needs: {calories} kcal", bmi_path else: return "Invalid inputs.", "", "" calculate_button.click( calculate_metrics, inputs=[user_age, user_weight, user_height, user_gender, activity_level], outputs=[bmi_output, calorie_output, bmi_chart] ) demo.launch(share=True)