Spaces:
Sleeping
Sleeping
import pandas as pd | |
import streamlit as st | |
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline | |
from langchain.llms import HuggingFacePipeline | |
from huggingface_hub import login | |
# Token de Hugging Face (Secreto) | |
huggingface_token = st.secrets["HUGGINGFACEHUB_API_TOKEN"] | |
login(huggingface_token) | |
# Cargar el modelo Llama 3.1 y el tokenizador | |
model_id = "meta-llama/Llama-3.1-1B" | |
tokenizer = AutoTokenizer.from_pretrained(model_id) | |
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") | |
# Crear pipeline de generaci贸n de texto | |
pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_length=1024) | |
llm_pipeline = HuggingFacePipeline(pipeline=pipe) | |
# Interfaz de Streamlit | |
st.title("Cosine Similarity with Llama 3.1") | |
# Subir archivo CSV | |
uploaded_file = st.file_uploader("Sube un archivo CSV con la columna 'job_title':", type=["csv"]) | |
if uploaded_file is not None: | |
# Cargar el CSV en un DataFrame | |
df = pd.read_csv(uploaded_file) | |
if 'job_title' in df.columns: | |
query = 'aspiring human resources specialist' | |
job_titles = df['job_title'].tolist() | |
# Definir el prompt para el LLM | |
prompt = ( | |
f"You are given a query and a list of job titles. Your task is to calculate the cosine similarity " | |
f"between the query and each job title. The query is: '{query}'. For each job title, provide the similarity " | |
f"score as a new column in the dataframe, called 'Score'. Return the dataframe with job titles and scores.\n" | |
f"Job Titles: {job_titles}\n" | |
f"Output format:\n" | |
f"1. Job Title: [Job Title], Score: [Cosine Similarity Score]\n" | |
f"2. Job Title: [Job Title], Score: [Cosine Similarity Score]\n" | |
f"..." | |
) | |
# Mostrar el prompt inicial | |
st.write("Prompt enviado al LLM:") | |
st.write(prompt) | |
# Generar respuesta del LLM | |
if st.button("Generar puntajes de similitud"): | |
with st.spinner("Calculando similitudes con Llama 3.1..."): | |
try: | |
response = llm_pipeline(prompt) | |
st.write("Respuesta del modelo:") | |
st.write(response) | |
# Simular la asignaci贸n de puntajes en la columna 'Score' (ya que el modelo no ejecuta c谩lculos reales) | |
df['Score'] = [0.95] * len(df) # Este paso es solo ilustrativo | |
# Mostrar el dataframe actualizado | |
st.write("DataFrame con los puntajes de similitud:") | |
st.write(df) | |
except Exception as e: | |
st.error(f"Error durante la generaci贸n: {e}") | |
else: | |
st.error("La columna 'job_title' no se encuentra en el archivo CSV.") | |