File size: 2,706 Bytes
514204a 13a4ba2 ca8334f 13a4ba2 cdd85c7 13a4ba2 69217a0 13a4ba2 69217a0 13a4ba2 69217a0 13a4ba2 e900f04 69217a0 13a4ba2 e900f04 cdd85c7 13a4ba2 e900f04 69217a0 13a4ba2 69217a0 13a4ba2 1a5536b 13a4ba2 ca8334f cdd85c7 a0bc52e |
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 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 |
import streamlit as st
import json
import os
from sentence_transformers import SentenceTransformer, util
import torch
# Load the processed legal code data
@st.cache_resource
def load_data(file_path):
with open(file_path, 'r', encoding='utf-8') as f:
return json.load(f)
# Initialize the sentence transformer model
@st.cache_resource
def load_model():
return SentenceTransformer('distiluse-base-multilingual-cased-v1')
def search_relevant_chunks(query, chunks, model, top_k=3):
query_embedding = model.encode(query, convert_to_tensor=True)
chunk_embeddings = model.encode([chunk['text'] for chunk in chunks], convert_to_tensor=True)
cos_scores = util.pytorch_cos_sim(query_embedding, chunk_embeddings)[0]
top_results = torch.topk(cos_scores, k=top_k)
return [chunks[idx] for idx in top_results.indices]
def main():
st.title("Chatbot Prawny")
# Load data and model
data_file = "processed_kodeksy.json"
if not os.path.exists(data_file):
st.error(f"Plik {data_file} nie istnieje. Najpierw przetw贸rz dane kodeks贸w.")
return
chunks = load_data(data_file)
model = load_model()
# Initialize chat history
if "messages" not in st.session_state:
st.session_state.messages = []
# Display chat history
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.markdown(message["content"])
# User input
if prompt := st.chat_input("Zadaj pytanie dotycz膮ce prawa..."):
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.markdown(prompt)
# Search for relevant chunks
relevant_chunks = search_relevant_chunks(prompt, chunks, model)
# Generate response
response = "Oto co znalaz艂em w kodeksie:\n\n"
for chunk in relevant_chunks:
response += f"**{chunk['metadata']['nazwa']} - Artyku艂 {chunk['metadata']['article']}**\n"
response += f"{chunk['text']}\n\n"
# Display assistant response
with st.chat_message("assistant"):
st.markdown(response)
st.session_state.messages.append({"role": "assistant", "content": response})
# Sidebar for additional options
with st.sidebar:
st.subheader("Opcje")
if st.button("Wyczy艣膰 histori臋 czatu"):
st.session_state.messages = []
st.experimental_rerun()
st.subheader("Informacje o bazie danych")
st.write(f"Liczba chunk贸w: {len(chunks)}")
st.write(f"Przyk艂adowy chunk:")
st.json(chunks[0] if chunks else {})
if __name__ == "__main__":
main() |