Update app.py

app.py

@@ -2,25 +2,23 @@ import streamlit as st
 import base64
 from huggingface_hub import InferenceClient
 import os
-import requests
 
-# Initialize Hugging Face Inference client using tokens from environment variables
-client = InferenceClient(api_key=os.getenv("HF_API_TOKEN_DISH"))
-client1 = InferenceClient(api_key=os.getenv("HF_API_TOKEN_DIET"))
-groq_api_key = os.getenv("API_Groq")
+# Initialize Hugging Face Inference clients using tokens from environment variables
+client_dish = InferenceClient(api_key=os.getenv("HF_API_TOKEN_DISH"))
+client_diet = InferenceClient(api_key=os.getenv("HF_API_TOKEN_DIET"))
 
 # 1. Function to identify dish from image
 def identify_dish(image_bytes):
     encoded_image = base64.b64encode(image_bytes).decode("utf-8")
     dish_name = ""
 
-    for message in client.chat_completion(
-        model="meta-llama/Llama-3.2-11B-Vision-Instruct",
+    for message in client_dish.chat_completion(
+        model="meta-llama/Llama-3-11B-Vision-Instruct",
         messages=[
             {
                 "role": "You are a highly specialized food identification AI with extensive knowledge of global cuisines. Your sole task is to accurately identify dishes from images. Adhere strictly to these guidelines:\n1. Analyze the image thoroughly, focusing on ingredients, presentation, and cultural context.\n2. Provide ONLY the name of the main dish or dishes visible. Do not list individual ingredients or components.\n3. Use the most specific and widely recognized name for the dish.\n4. If multiple distinct dishes are present, list them separated by commas.\n5. If you cannot identify a dish with high confidence (>90%), respond with 'Unidentified dish'.\n6. Do not provide any explanations, descriptions, or additional commentary.\n7. Respond in a concise, list-like format.\nYour response should contain nothing but the dish name(s) or 'Unidentified dish'.",
                 "content": [
-                    {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{encoded_image}" }},
+                    {"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{encoded_image}"}},
                     {"type": "text", "text": "Identify the dishes in the image and return only the names of the dishes."},
                 ],
             }
@@ -33,7 +31,7 @@ def identify_dish(image_bytes):
 
     return dish_name.strip()
 
-# 2. Function to calculate daily caloric needs
+# 2. Function to get user inputs and calculate daily caloric needs
 def calculate_metrics(age, gender, height_cm, weight_kg, weight_goal, activity_level, time_frame_months):
     bmi = weight_kg / ((height_cm / 100) ** 2)
 
@@ -88,7 +86,7 @@ def generate_diet_plan(dish_name, calorie_intake_per_day, goal):
     - Caloric Intake per Day: {calorie_intake_per_day} calories
     - Goal: {goal}
     """
-    response = client1.chat_completion(
+    response = client_diet.chat_completion(
         model="meta-llama/Meta-Llama-3-8B-Instruct",
         messages=[{"role": "You are a certified Dietitian with 20 years of Experience", "content": user_input}],
         max_tokens=500
@@ -96,40 +94,16 @@ def generate_diet_plan(dish_name, calorie_intake_per_day, goal):
 
     return response.choices[0].message.content
 
-# 4. Function to generate a recipe using Groq API
-def generate_recipe(recipe_name):
-    url = "https://api.groq.com/openai/v1/chat/completions"
-    headers = {
-        "Authorization": f"Bearer {groq_api_key}",
-        "Content-Type": "application/json"
-    }
-    data = {
-        "model": "llama-3.1-70b-versatile",
-        "messages": [
-            {"role": "system", "content": "You are a skilled chef with 10 years of experience."},
-            {"role": "user", "content": f"Create a detailed recipe for {recipe_name}"}
-        ]
-    }
-
-    response = requests.post(url, headers=headers, json=data)
-
-    if response.status_code == 200:
-        result = response.json()
-        generated_recipe = result['choices'][0]['message']['content']
-        return generated_recipe
-    else:
-        return f"Error: {response.status_code}, {response.text}"
-
 # Streamlit App Title
 st.title("AI Diet Planner")
 
 # Sidebar for user input
 st.sidebar.title("User Input")
 image_file = st.sidebar.file_uploader("Upload an image of the dish", type=["jpeg", "png"])
-age = st.sidebar.number_input("Enter your age", min_value=1)
+age = st.sidebar.number_input("Enter your age", min_value=18)
 gender = st.sidebar.selectbox("Select your gender", ["male", "female"])
-height_cm = st.sidebar.number_input("Enter your height (cm)", min_value=1.0)
-weight_kg = st.sidebar.number_input("Enter your weight (kg)", min_value=1.0)
+height_cm = st.sidebar.number_input("Enter your height (cm)", min_value=150.0)
+weight_kg = st.sidebar.number_input("Enter your weight (kg)", min_value=50.0)
 weight_goal = st.sidebar.selectbox("Weight goal", ["loss", "gain", "maintain"])
 activity_level = st.sidebar.selectbox("Activity level", ["sedentary", "light", "moderate", "active", "very active"])
 time_frame = st.sidebar.number_input("Time frame to achieve goal (months)", min_value=1)
@@ -169,16 +143,6 @@ if submit:
         st.write("#### Diet Plan Based on Dish & Goal:")
         st.markdown(f"<div style='background-color: #d1ecf1; color: #0c5460; padding: 10px; border-radius: 10px;'>{diet_plan}</div>", unsafe_allow_html=True)
 
-        # Step 4: Ask for recipe generation
-        st.markdown("<hr>", unsafe_allow_html=True)
-        recipe_option = st.radio("Would you like a recipe for a dish?", ["No", "Yes"])
-
-        if recipe_option == "Yes":
-            recipe_name = st.text_input("Enter the dish name for the recipe:")
-            if st.button("Generate Recipe"):
-                recipe = generate_recipe(recipe_name)
-                st.write("### Generated Recipe:")
-                st.markdown(f"<div style='background-color: #fff3cd; color: #856404; padding: 10px; border-radius: 10px;'>{recipe}</div>", unsafe_allow_html=True)
     else:
         st.error("Please upload a valid image in JPEG or PNG format.")