Update app.py

app.py

@@ -1,47 +1,21 @@
-import json
+# app.py
+
+import os
 import gradio as gr
-from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.vectorstores import FAISS
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.schema import Document
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
 from huggingface_hub import InferenceClient
-import os
-
-# ✅ Step 1: Load and Chunk JSON with Metadata
-file_path = "pdf_data.json"
-documents = []
-
-splitter = RecursiveCharacterTextSplitter(chunk_size=512, chunk_overlap=50)
 
-try:
-    with open(file_path, "r", encoding="utf-8") as f:
-        data = json.load(f)
-        for item in data:
-            if "text" in item:
-                section = "PPC" if "punishment" in item["text"].lower() or "section" in item["text"].lower() else "other"
-                law_type = "criminal" if section == "PPC" else "general"
-                chunks = splitter.split_text(item["text"])
-                for chunk in chunks:
-                    documents.append(Document(
-                        page_content=chunk,
-                        metadata={"section": section, "law_type": law_type}
-                    ))
-except Exception as e:
-    print(f"❌ Failed to load: {e}")
-
-print(f"✅ Loaded {len(documents)} chunks with metadata")
-
-# ✅ Step 2: Create Embeddings & FAISS Vector Store
+# Load FAISS index and embedding model
 embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-db = FAISS.from_documents(documents, embedding_model)
+db = FAISS.load_local("faiss_index", embedding_model)
 
-# ✅ Step 3: Load Zephyr-7B via Hugging Face Inference API
+# Load Hugging Face Inference API client
 client = InferenceClient(
     model="HuggingFaceH4/zephyr-7b-beta",
-    token=os.getenv("HF_TOKEN")  # set your token in environment variable
+    token=os.getenv("HF_TOKEN")  # Make sure this is set in your environment
 )
 
-# ✅ Step 4: QA Function using chat_completion with formatting
 def ask_law_bot(query):
     try:
         results = db.similarity_search(query, k=5, filter={"section": "PPC"})
@@ -56,10 +30,8 @@ Respond to the question using the given legal context. Your answer must follow t
 - Reference relevant law sections like (section 220(b))
 - Be concise, clear, and avoid repetition
 - Use "YES" or "NO" if the question requires binary response
-
 Context:
 {context}
-
 Question: {query}
 Answer:"""
 
@@ -76,7 +48,7 @@ Answer:"""
     except Exception as e:
         return f"❌ Error: {e}"
 
-# ✅ Step 5: Gradio UI
+# Gradio UI
 gr.Interface(
     fn=ask_law_bot,
     inputs=gr.Textbox(lines=2, placeholder="e.g., What is the punishment for theft?"),