Spaces:
Running
Running
File size: 1,921 Bytes
1710972 5a16bc2 1710972 5a16bc2 4e8cbc3 1710972 5a16bc2 1710972 5a16bc2 1710972 5a16bc2 4e8cbc3 5a16bc2 1710972 5a16bc2 4e8cbc3 1710972 5a16bc2 1710972 4e8cbc3 |
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 |
import streamlit as st
import pinecone
import os # To access environment variables
from sentence_transformers import SentenceTransformer
import numpy as np
from datasets import load_dataset
# Step 1: Get the Pinecone API key from the environment variable (Hugging Face secret)
pinecone_api_key = os.getenv('PINECONE_API_KEY') # Fetch Pinecone API key from Hugging Face secrets
if not pinecone_api_key:
st.error("Pinecone API key not found! Make sure to set the secret in Hugging Face settings.")
st.stop()
# Initialize Pinecone client using the API key
pinecone.init(api_key=pinecone_api_key, environment="us-west1-gcp") # Change the environment if needed
# Connect to your Pinecone index
index_name = "legal-docs-index-dji2ip8" # Your Pinecone index name
index = pinecone.Index(index_name)
# Step 2: Load the sentence-transformers model for embeddings
model = SentenceTransformer("all-MiniLM-L6-v2")
# Step 3: Load dataset (for reference in your app)
dataset = load_dataset("macadeliccc/US-LegalKit", split="train")
law_texts = [item['text'] for item in dataset if 'text' in item]
# Step 4: Function to search Pinecone index
def search_pinecone(query, top_k=5):
# Create an embedding for the user's query
query_embedding = model.encode([query])
# Query the Pinecone index for similar documents
results = index.query(query_embedding, top_k=top_k, include_metadata=True)
# Extract the text of the top-k results
return [match['metadata']['text'] for match in results['matches']]
# Step 5: Streamlit UI
st.title("🔍 Legal AI Assistant (US-LegalKit)")
query = st.text_input("📌 Enter your legal query:")
if query:
# Get the top results from Pinecone
results = search_pinecone(query)
st.write("### 📄 Relevant Legal Documents:")
for i, doc in enumerate(results, 1):
st.write(f"**{i}.** {doc[:500]}...") # Show preview of the document
|