import pysbd
from txtai.embeddings import Embeddings
import networkx as nx
from tqdm import tqdm
from txtai.graph import GraphFactory
from datasets import load_dataset
import streamlit as st
import streamlit.components.v1 as components



st.set_page_config(page_title="DebateKG")
st.title("DebateKG - Automatic Policy Debate Case Creation")
st.caption("github: https://github.com/Hellisotherpeople/DebateKG")





dataset = load_dataset("Hellisotherpeople/DebateSum", split = "train")
seg = pysbd.Segmenter(language="en", clean=False)


embeddings = Embeddings({
  "path": "entence-transformers/all-mpnet-base-v2",
  "content": True,
  "functions": [
    {"name": "graph", "function": "graph.attribute"},
  ],
  "expressions": [
      {"name": "topic", "expression": "graph(indexid, 'topic')"},
      {"name": "topicrank", "expression": "graph(indexid, 'topicrank')"}
  ],
  "graph": {
      "limit": 100,
      "minscore": 0.10,
      "topics": {
          "terms": 4,
          "resolution" : 100
      }
  }
})

embeddings.load("DebateSum_SemanticGraph_mpnet_extract.tar.gz")
graph = embeddings.graph

print(graph.backend.number_of_nodes(), graph.backend.number_of_edges())