# Setup and load your keys
import os
from g4f import ChatCompletion
from google.colab import userdata
from pinecone import Pinecone
import pandas as pd
from datasets import Dataset
from sentence_transformers import SentenceTransformer
import gradio as gr

model_name = "BAAI/bge-m3"

# APIs personales
#PINECONE_ENVIRONMENT = us-east-1
#PINECONE_API_KEY = 3a3e9022-381d-436e-84cb-ba93464d283e

os.environ["PINECONE_ENVIRONMENT"] = "us-east-1"
os.environ["PINECONE_API_KEY"] = "3a3e9022-381d-436e-84cb-ba93464d283e"

# Retrieve the Pinecone API key from the user
PINECONE_API_KEY = userdata.get("PINECONE_API_KEY")  # Use the key you set in the secrets
PINECONE_ENVIRONMENT = "us-east-1"  # Use the environment you set in the secrets

# Initialize Pinecone with the API key
pc = Pinecone(api_key=PINECONE_API_KEY)

# Ruta del archivo CSV
file_path = '/content/dataset.csv'

# Cargar el dataset y establecerlo como variable global
try:
    df = pd.read_csv(file_path)
    DATASET = Dataset.from_pandas(df)
    print(f"Dataset '{file_path}' loaded successfully.\n")
    print(DATASET)
except Exception as e:
    DATASET = None
    print(f"Error loading dataset: {e}")

# Función para imprimir la información del dataset actual
def print_dataset_info():
    print(f"Current dataset: {DATASET}" if DATASET else "No dataset loaded.")

# Guardar la variable global para uso en otras celdas
get_ipython().run_cell_magic('capture', '', '%store DATASET')