Create app.py

app.py

@@ -0,0 +1,350 @@
+# ============================================================
+# RAG Chatbot — Hugging Face Spaces
+# Upload PDFs and ask questions!
+# ============================================================
+
+import os, warnings
+warnings.filterwarnings("ignore")
+
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.vectorstores import FAISS
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_groq import ChatGroq
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+from langchain_core.messages import HumanMessage, AIMessage
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough, RunnableLambda
+import gradio as gr
+
+# API Key from HF Secrets
+GROQ_API_KEY = os.environ.get("GROQ_API_KEY", "")
+
+# ── Load PDFs ─────────────────────────────────────────────────
+def load_pdfs(files):
+    all_docs = []
+    names = []
+    for file in files:
+        try:
+            loader = PyPDFLoader(file.name)
+            docs = loader.load()
+            for doc in docs:
+                doc.metadata["source"] = os.path.basename(file.name)
+            all_docs.extend(docs)
+            names.append(os.path.basename(file.name))
+            print(f"  ✅ {os.path.basename(file.name)} — {len(docs)} pages")
+        except Exception as e:
+            print(f"  ❌ Error: {e}")
+    return all_docs, names
+
+# ── Build RAG ─────────────────────────────────────────────────
+def build_rag(all_docs):
+    chunks = RecursiveCharacterTextSplitter(
+        chunk_size=600,
+        chunk_overlap=100,
+        separators=["\n\n", "\n", ". ", " ", ""]
+    ).split_documents(all_docs)
+    print(f"  ✂️ {len(chunks)} chunks")
+
+    emb = HuggingFaceEmbeddings(
+        model_name="all-MiniLM-L6-v2",
+        model_kwargs={"device": "cpu"},
+        encode_kwargs={"normalize_embeddings": True}
+    )
+    vs = FAISS.from_documents(chunks, emb)
+
+    llm = ChatGroq(
+        groq_api_key=GROQ_API_KEY,
+        model_name="llama-3.3-70b-versatile",
+        temperature=0.3,
+        max_tokens=1500
+    )
+
+    retriever = vs.as_retriever(search_kwargs={"k": 4})
+
+    prompt = ChatPromptTemplate.from_messages([
+        ("system", """You are an expert AI assistant.
+Answer using ONLY the context below.
+Always mention the source document.
+If answer not found, say: I don't have that information in the provided documents.
+
+Context:
+{context}"""),
+        MessagesPlaceholder(variable_name="chat_history"),
+        ("human", "{question}")
+    ])
+
+    def fmt(docs):
+        return "\n\n---\n\n".join(
+            f"[Source: {d.metadata.get('source','?')} | Page {d.metadata.get('page',0)+1}]:\n{d.page_content}"
+            for d in docs
+        )
+
+    chain = (
+        RunnablePassthrough.assign(
+            context=RunnableLambda(
+                lambda x: fmt(retriever.invoke(x["question"]))
+            )
+        )
+        | prompt | llm | StrOutputParser()
+    )
+    return chain, len(chunks)
+
+# ── Global State ──────────────────────────────────────────────
+rag_chain = None
+ui_history = []
+
+# ── Gradio Functions ──────────────────────────────────────────
+def process_files(files):
+    global rag_chain
+    if not files:
+        return "⚠️ Koi file select nahi ki!", ""
+
+    print(f"\n📁 Processing {len(files)} file(s)...")
+    docs, names = load_pdfs(files)
+
+    if not docs:
+        return "❌ PDFs se content extract nahi hua!", ""
+
+    try:
+        chain, n_chunks = build_rag(docs)
+        rag_chain = chain
+        chars = sum(len(d.page_content) for d in docs)
+        names_list = "\n".join([f"• {n}" for n in names])
+        return (
+            f"✅ **{len(names)} file(s) loaded!**\n\n{names_list}\n\n"
+            f"📊 {len(docs)} pages | {n_chunks} chunks | {chars:,} chars\n\n"
+            f"💬 **Ab sawal poochho!**"
+        ), f"{len(names)} docs"
+    except Exception as e:
+        return f"❌ Error: {str(e)}", ""
+
+
+def chat_fn(msg, history):
+    global rag_chain, ui_history
+    if not msg.strip():
+        return "", history
+    if rag_chain is None:
+        history.append({
+            "role": "assistant",
+            "content": "⚠️ Pehle PDF upload karo aur Process karo!"
+        })
+        return "", history
+    try:
+        ans = rag_chain.invoke({
+            "question": msg,
+            "chat_history": ui_history
+        })
+        ui_history.append(HumanMessage(content=msg))
+        ui_history.append(AIMessage(content=ans))
+    except Exception as e:
+        ans = f"❌ Error: {str(e)}"
+        print(f"ERROR: {e}")
+
+    history.append({"role": "user", "content": msg})
+    history.append({"role": "assistant", "content": ans})
+    return "", history
+
+
+def clear_fn():
+    global ui_history
+    ui_history = []
+    return []
+
+# ── CSS ───────────────────────────────────────────────────────
+css = """
+@import url('https://fonts.googleapis.com/css2?family=Syne:wght@700;800&family=DM+Sans:wght@300;400;500&display=swap');
+
+* { box-sizing: border-box; }
+
+body, .gradio-container {
+    font-family: 'DM Sans', sans-serif !important;
+    background: #0a0a0f !important;
+    color: #e8e6f0 !important;
+}
+.gradio-container {
+    max-width: 960px !important;
+    margin: 0 auto !important;
+}
+.app-title {
+    font-family: 'Syne', sans-serif !important;
+    font-size: 2.4rem !important;
+    font-weight: 800 !important;
+    background: linear-gradient(135deg, #a78bfa, #60a5fa, #34d399) !important;
+    -webkit-background-clip: text !important;
+    -webkit-text-fill-color: transparent !important;
+    background-clip: text !important;
+    text-align: center !important;
+    padding: 32px 0 8px !important;
+}
+.badge {
+    display: inline-flex; align-items: center; gap: 5px;
+    background: rgba(139,92,246,0.1);
+    border: 1px solid rgba(139,92,246,0.25);
+    border-radius: 20px; padding: 4px 12px;
+    font-size: 0.72rem; color: #a78bfa; font-weight: 500; margin: 3px;
+}
+.section-label {
+    font-family: 'Syne', sans-serif !important;
+    font-size: 0.7rem !important; font-weight: 700 !important;
+    letter-spacing: 2.5px !important; text-transform: uppercase !important;
+    color: #a78bfa !important; margin: 20px 0 12px !important;
+}
+textarea, input[type=text] {
+    background: #0d0d14 !important;
+    border: 1px solid #1f1f2e !important;
+    border-radius: 10px !important;
+    color: #e8e6f0 !important;
+    font-family: 'DM Sans', sans-serif !important;
+    font-size: 0.9rem !important;
+    transition: border-color 0.2s, box-shadow 0.2s !important;
+    scrollbar-width: thin !important;
+    scrollbar-color: #2d2d45 transparent !important;
+}
+textarea:focus, input[type=text]:focus {
+    border-color: #a78bfa !important;
+    box-shadow: 0 0 0 3px rgba(139,92,246,0.12) !important;
+    outline: none !important;
+}
+textarea::-webkit-scrollbar { width: 4px !important; }
+textarea::-webkit-scrollbar-thumb {
+    background: #2d2d45 !important; border-radius: 10px !important;
+}
+textarea::-webkit-scrollbar-thumb:hover { background: #a78bfa !important; }
+button.primary {
+    background: linear-gradient(135deg, #7c3aed, #4f46e5) !important;
+    border: none !important; border-radius: 10px !important;
+    color: white !important; font-family: 'Syne', sans-serif !important;
+    font-weight: 600 !important;
+    box-shadow: 0 4px 15px rgba(124,58,237,0.3) !important;
+    transition: all 0.2s ease !important;
+}
+button.primary:hover {
+    transform: translateY(-1px) !important;
+    box-shadow: 0 6px 20px rgba(124,58,237,0.4) !important;
+}
+button.secondary {
+    background: #13131a !important;
+    border: 1px solid #2d2d45 !important;
+    border-radius: 10px !important;
+    color: #9ca3af !important; transition: all 0.2s !important;
+}
+button.secondary:hover {
+    border-color: #a78bfa !important; color: #a78bfa !important;
+}
+label span { color: #6b7280 !important; font-size: 0.8rem !important; }
+.examples-table td, .examples td {
+    background: #13131a !important;
+    border: 1px solid #1f1f2e !important;
+    border-radius: 8px !important; color: #9ca3af !important;
+    font-size: 0.8rem !important; cursor: pointer !important;
+    transition: all 0.2s !important;
+}
+.examples-table td:hover, .examples td:hover {
+    background: #1e1e30 !important;
+    color: #a78bfa !important; border-color: #a78bfa !important;
+}
+"""
+
+# ── UI ────────────────────────────────────────────────────────
+with gr.Blocks(
+    css=css,
+    title="RAG Intelligence",
+    theme=gr.themes.Base(
+        primary_hue="violet",
+        neutral_hue="slate"
+    )
+) as demo:
+
+    gr.HTML("""
+    <div class="app-title">⚡ RAG Intelligence</div>
+    <div style="text-align:center; color:#6b7280; margin-bottom:16px;">
+        Multi-Document AI · FAISS · Groq LLaMA 3.3
+    </div>
+    <div style="text-align:center; margin-bottom:24px;">
+        <span class="badge">🧠 HuggingFace</span>
+        <span class="badge">⚡ Groq LLM</span>
+        <span class="badge">🔍 FAISS</span>
+        <span class="badge">📄 Multi-PDF</span>
+    </div>
+    """)
+
+    gr.HTML('<div class="section-label">📥 &nbsp; Upload Your PDFs</div>')
+
+    with gr.Row():
+        with gr.Column(scale=3):
+            file_input = gr.File(
+                label="PDF files select karo (multiple ho sakti hain)",
+                file_types=[".pdf"],
+                file_count="multiple",
+            )
+            process_btn = gr.Button(
+                "⚙️  Process Documents",
+                variant="primary"
+            )
+        with gr.Column(scale=2):
+            status_out = gr.Markdown(
+                "📋 **Status:** Waiting for documents..."
+            )
+            badge_out = gr.Markdown("**0 docs loaded**")
+
+    gr.HTML('<hr style="border:none;border-top:1px solid #1a1a28;margin:20px 0;">')
+    gr.HTML('<div class="section-label">💬 &nbsp; Chat With Documents</div>')
+
+    chatbot = gr.Chatbot(
+        label="",
+        height=480,
+        type="messages",
+        show_label=False,
+        placeholder="<div style='text-align:center;color:#374151;padding:40px;'>Load documents first, then ask anything! ✦</div>",
+    )
+
+    with gr.Row():
+        msg_box = gr.Textbox(
+            placeholder="✦  Apne documents ke baare mein kuch bhi poochho...",
+            label="", lines=2, max_lines=5,
+            scale=5, show_label=False, container=False,
+        )
+        with gr.Column(scale=1, min_width=110):
+            send_btn = gr.Button("Send ➤", variant="primary")
+            clear_btn = gr.Button("Clear 🗑", variant="secondary")
+
+    gr.Examples(
+        examples=[
+            "Is document ka summary do",
+            "Main topics kya hain?",
+            "Important points bullet mein batao",
+            "Koi definition explain karo",
+            "Key concepts list karo",
+        ],
+        inputs=msg_box,
+        label="✦  Quick Questions",
+    )
+
+    gr.HTML("""
+    <div style="text-align:center;padding:20px 0 8px;
+                color:#2d2d45;font-size:0.72rem;letter-spacing:1.5px;">
+        RAG INTELLIGENCE · FAISS · GROQ · HUGGINGFACE
+    </div>
+    """)
+
+    # Events
+    process_btn.click(
+        fn=process_files,
+        inputs=[file_input],
+        outputs=[status_out, badge_out]
+    )
+    send_btn.click(
+        fn=chat_fn,
+        inputs=[msg_box, chatbot],
+        outputs=[msg_box, chatbot]
+    )
+    msg_box.submit(
+        fn=chat_fn,
+        inputs=[msg_box, chatbot],
+        outputs=[msg_box, chatbot]
+    )
+    clear_btn.click(fn=clear_fn, outputs=[chatbot])
+
+if __name__ == "__main__":
+    demo.launch()