Spaces:
Sleeping
Sleeping
File size: 1,395 Bytes
532f1f0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 |
import streamlit as st
from config import EMBEDDINGS_DIR
from embeddings.search import run_search
from embeddings.cluster import run_clustering_pipeline
from embeddings.embedder import (
initialize_embedding_model,
initialize_chroma,
run_pipeline,
)
# CONFIGURAÇÃO BÁSICA STREAMLIT
st.set_page_config(
page_title="Semantic Clusters Dashboard",
page_icon="🪐",
layout="wide",
)
st.title("Semantic Clusters Dashboard")
st.markdown("Visualize document clusters with interactive semantic search.")
@st.cache_resource
def get_embeddings_model():
return initialize_embedding_model()
@st.cache_resource
def get_vectordb():
embeddings_model = get_embeddings_model()
return initialize_chroma(embeddings_model, EMBEDDINGS_DIR)
embedding_model = get_embeddings_model()
vectordb = get_vectordb()
# INTERFACE PRINCIPAL
(
tab_ingestion,
tab_clusters,
tab_search,
) = st.tabs(["Ingestion & Embedding", "3D Clusters", "Semantic Search "])
with tab_ingestion:
run_pipeline(force_run=False)
with tab_search:
run_search(embedding_model=embedding_model, vectordb=vectordb)
with tab_clusters:
st.header("3D Clusters View")
if st.button("🌀 Generate clusters"):
with st.spinner("Generating clusters..."):
run_clustering_pipeline(embedding_model=embedding_model, vectordb=vectordb)
st.success("Clusters!")
|