Update app.py

app.py

@@ -1,45 +1,51 @@
 import streamlit as st
-import faiss
-import numpy as np
+import pinecone
+import os  # To access environment variables
 from sentence_transformers import SentenceTransformer
-import openai
+import numpy as np
 from datasets import load_dataset
 
-# Load FAISS index
-index = faiss.read_index("faiss_index.bin")
+# 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
 
-# Load embedding model
+# 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")
 
-# Load dataset (only titles for reference)
+# 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]
 
-# OpenAI API Key (store it as a secret in Hugging Face)
-openai.api_key = st.secrets["GROQ_API_KEY"]
-
-# Function to search relevant legal documents
-def search_legal_docs(query, top_k=5):
+# 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])
-    _, idxs = index.search(query_embedding, top_k)
-    return [law_texts[i] for i in idxs[0]]  # Return matching legal documents
-
-# Streamlit UI
+    
+    # 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:
-    results = search_legal_docs(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
-
-    # Generate AI-based legal response
-    response = openai.ChatCompletion.create(
-        model="gpt-4",
-        messages=[{"role": "system", "content": "You are a legal assistant."},
-                  {"role": "user", "content": query}]
-    )
-    st.write("### 🧑‍⚖️ AI Response:")
-    st.write(response['choices'][0]['message']['content'])