import os 
import requests
import gradio as gr 

api_token = os.environ.get("TOKEN")

API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-8B-Instruct"
headers = {"Authorization": f"Bearer {api_token}"}

def query(payload):
        response = requests.post(API_URL, headers=headers, json=payload)
        return response.json()




def analyze_sentiment(text):
    output = query({
    "inputs":   f'''<|begin_of_text|>
    <|start_header_id|>system<|end_header_id|>
you are a feeling analyser and you'll say only "positive" if i'm feeling positive and "negativ" if i'm feeling sad   <|eot_id|>
    <|start_header_id|>user<|end_header_id|>
    {text}
    <|eot_id|>
    <|start_header_id|>assistant<|end_header_id|>
    '''
})

    # Assurez-vous de gérer correctement la sortie de l'API
    if isinstance(output, list) and len(output) > 0:
        return output[0].get('generated_text', 'Erreur: Réponse inattendue')
    if isinstance(output, list) and len(output) > 0:
        response = output[0].get('generated_text', '').strip().lower()
    if 'positive' in response:
       return 'positive'
    elif 'negative' in response:
       return 'negative'
    else:
       return "Erreur: Réponse inattendue"





demo = gr.Interface(
    fn = query,
    inputs=["text"],
    outputs=["text"]
)

demo.launch()