Create app.py

app.py

@@ -0,0 +1,126 @@
+# app.py
+import streamlit as st
+from rag_pipeline import load_and_process_documents, ask_question
+
+st.set_page_config(page_title="Bangladesh Law QA", layout="wide")
+st.title("📚 Bangladesh Law RAG QA System")
+st.markdown("Ask legal questions based on the Constitution, ICT Act, Labour Law, and more.")
+
+# Load and process PDFs
+@st.cache_resource
+def setup():
+    pdfs = [
+        "./pdfs/Bangladesh-ICT-Act-2006.pdf",
+        "./pdfs/Bangladesh-Labour-Act-2006_English-Upto-2018.pdf",
+        "./pdfs/bangladesh_rti_act_2009_summary.pdf",
+        "./pdfs/bgd-gbv-19-03-law-1860-eng-the-penal-code-1860.pdf",
+        "./pdfs/constitution.pdf",
+        "./pdfs/gazette.pdf",
+        "./pdfs/unicef.pdf",
+    ]
+    return load_and_process_documents(pdfs)
+
+chunks, retriever, qa_chain = setup()
+
+query = st.text_input("🔍 Enter your legal question")
+law_options = ["All", "ICT Act", "Labour Act", "Penal Code", "Constitution"]
+law_filter = st.selectbox("📘 Filter by Law (optional)", law_options)
+if law_filter == "All": law_filter = None
+
+if query:
+    with st.spinner("Answering..."):
+        answer, sources = ask_question(query, retriever, qa_chain, law_filter)
+        st.success(answer)
+        with st.expander("📎 Source Documents"):
+            for doc in sources:
+                st.markdown(f"**{doc.metadata.get('law_name', '')} - {doc.metadata.get('section_heading', '')}**")
+                st.text(doc.page_content[:500])
+
+# BONUS: Predefined sample questions
+st.markdown("---")
+st.markdown("### 🧪 Try Sample Legal Questions:")
+sample_questions = [
+    ("What does the Constitution say about freedom of expression?", "Constitution"),
+    ("Under ICT Act, is cyberbullying a crime?", "ICT Act"),
+    ("How many hours can a laborer work in a day?", "Labour Act"),
+    ("What are the punishments under the Digital Security Act for hacking?", "ICT Act"),
+    ("Is digital evidence allowed in court?", "ICT Act"),
+]
+
+for q, lf in sample_questions:
+    if st.button(f"▶️ {q}"):
+        with st.spinner("Running..."):
+            answer, sources = ask_question(q, retriever, qa_chain, law_filter=lf)
+            st.success(answer)
+            with st.expander("📎 Source Documents"):
+                for doc in sources:
+                    st.markdown(f"**{doc.metadata.get('law_name', '')} - {doc.metadata.get('section_heading', '')}**")
+                    st.text(doc.page_content[:500])
+
+
+# rag_pipeline.py
+import os, re
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.schema import Document
+from langchain_google_genai import GoogleGenerativeAIEmbeddings, ChatGoogleGenerativeAI
+from langchain.vectorstores import Chroma
+from langchain.chains import RetrievalQA
+
+def load_and_process_documents(pdf_paths):
+    all_docs = []
+    for path in pdf_paths:
+        loader = PyPDFLoader(path)
+        pages = loader.load()
+        for p in pages:
+            p.metadata["source"] = os.path.basename(path)
+        all_docs.extend(pages)
+
+    # Add metadata
+    for doc in all_docs:
+        src = doc.metadata.get("source", "").lower()
+        if "ict" in src:
+            doc.metadata.update({"law_name": "ICT Act", "year": 2006, "law_type": "ICT"})
+        elif "labour" in src:
+            doc.metadata.update({"law_name": "Labour Act", "year": 2018, "law_type": "Labour"})
+        elif "penal" in src:
+            doc.metadata.update({"law_name": "Penal Code", "year": 1860, "law_type": "Criminal"})
+        elif "constitution" in src:
+            doc.metadata.update({"law_name": "Constitution", "year": 1972, "law_type": "Constitutional"})
+
+    # Section splitting
+    section_pattern = re.compile(r"(Section\\s\\d+\\.?\\d*|Article\\s\\d+\\.?\\d*|Chapter\\s\\d+\\.?\\d*)", re.IGNORECASE)
+    section_chunks = []
+    for doc in all_docs:
+        text = doc.page_content or ""
+        splits = section_pattern.split(text)
+        for i in range(1, len(splits), 2):
+            heading = splits[i].strip()
+            body = splits[i+1].strip() if i+1 < len(splits) else ""
+            chunk_text = f"{heading}\n{body}"
+            meta = doc.metadata.copy()
+            meta.update({"section_heading": heading})
+            section_chunks.append(Document(page_content=chunk_text, metadata=meta))
+
+    # Embedding + Vector store
+    embedding = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+    vectorstore = Chroma.from_documents(section_chunks, embedding=embedding, persist_directory="./chroma_db")
+    vectorstore.persist()
+
+    retriever = vectorstore.as_retriever(search_type="similarity", search_kwargs={"k": 5})
+    llm = ChatGoogleGenerativeAI(model="gemini-1.5-flash-latest", temperature=0)
+    qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=retriever, return_source_documents=True, chain_type="stuff")
+
+    return section_chunks, retriever, qa_chain
+
+def ask_question(query, retriever, qa_chain, law_filter=None, year_filter=None):
+    docs = retriever.get_relevant_documents(query)
+    if law_filter:
+        docs = [d for d in docs if d.metadata.get("law_name") == law_filter]
+    if year_filter:
+        docs = [d for d in docs if d.metadata.get("year") == year_filter]
+
+    if not docs:
+        return "No relevant information found.", []
+
+    result = qa_chain({"input_documents": docs, "query": query})
+    return result["result"], result["source_documents"]