Upload 4 files

README.md

@@ -1,13 +1,17 @@
----
-title: Faq Chatbot
-emoji: 📊
-colorFrom: blue
-colorTo: gray
-sdk: gradio
-sdk_version: 5.49.1
-app_file: app.py
-pinned: false
-license: lgpl-2.1
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+# IPLM FAQ Chatbot (Non‑LLM)
+
+A simple FAQ chatbot for IPLM using TF‑IDF + fuzzy matching. Built with **Gradio** (no LLM).
+
+## How to run locally
+```bash
+pip install -r requirements.txt
+python app.py
+```
+
+## Dataset
+Put your JSONL under `data/iplm_qna.jsonl` with keys:
+- `question`: main question
+- `q_variants`: list of alternative phrasings (optional)
+- `answer`: the short authoritative answer
+- `source`: source string (optional)

app.py

@@ -0,0 +1,67 @@
+
+import json, numpy as np, gradio as gr
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import linear_kernel
+from rapidfuzz import fuzz
+
+DATA_PATH = "data/iplm_qna.jsonl"
+
+def load_qa(path):
+    qa_list = []
+    with open(path, "r", encoding="utf-8") as f:
+        for line in f:
+            obj = json.loads(line)
+            q = (obj.get("question") or "").strip()
+            qvars = obj.get("q_variants") or []
+            ans = (obj.get("answer") or "").strip()
+            src = (obj.get("source") or "").strip()
+            all_q = [q] + qvars
+            for qq in all_q:
+                if qq:
+                    qa_list.append({"question": qq, "answer": ans, "source": src})
+    return qa_list
+
+qa_data = load_qa(DATA_PATH)
+questions = [d["question"] for d in qa_data]
+vectorizer = TfidfVectorizer(analyzer="char_wb", ngram_range=(3,5), lowercase=True)
+X = vectorizer.fit_transform(questions)
+
+def search_answer(query, alpha=0.6, threshold=55):
+    if not query.strip():
+        return "Silakan ketik pertanyaan."
+    qv = vectorizer.transform([query])
+    cos = linear_kernel(qv, X).ravel()
+    cos_scaled = 100 * (cos - cos.min()) / (cos.max() - cos.min() + 1e-12)
+    idx = np.argsort(-cos)[:50]
+    hybrid_scores = []
+    for j in idx:
+        fz = fuzz.ratio(query.lower(), questions[j].lower())
+        score = alpha * cos_scaled[j] + (1 - alpha) * fz
+        hybrid_scores.append((j, score))
+    hybrid_scores.sort(key=lambda x: -x[1])
+    best_idx, best_score = hybrid_scores[0]
+    best = qa_data[best_idx]
+    if best_score < threshold:
+        suggestions = "\n".join([f"- {qa_data[i]['question']} (skor {round(s,1)})" for i, s in hybrid_scores[:3]])
+        return f"❓ Maaf, saya belum yakin.\nMungkin maksud Anda salah satu dari ini:\n{suggestions}"
+    src = best.get("source", "")
+    src_line = f"\n\n📚 Sumber: {src}" if src else ""
+    return best['answer'] + src_line
+
+def chatbot_response(message, history):
+    return search_answer(message)
+
+with gr.Blocks(title="IPLM FAQ Chatbot (Non‑LLM)") as demo:
+    gr.Markdown("## 🤖 Chatbot IPLM (Non‑LLM)\nChatbot ini menjawab berdasarkan data Q&A IPLM resmi.")
+    chat = gr.Chatbot(height=420, bubble_full_width=False, show_copy_button=True, show_label=False)
+    with gr.Row():
+        user_input = gr.Textbox(label="Ketik pertanyaan…", placeholder="Contoh: Apa itu IPLM?", lines=2, scale=8)
+        send_btn = gr.Button("💬 Kirim", scale=1)
+    def on_submit(msg, chat_history):
+        reply = chatbot_response(msg, chat_history)
+        chat_history = chat_history + [(msg, reply)]
+        return "", chat_history
+    send_btn.click(on_submit, inputs=[user_input, chat], outputs=[user_input, chat])
+    user_input.submit(on_submit, inputs=[user_input, chat], outputs=[user_input, chat])
+    gr.Markdown("---\nDikembangkan dengan 💡 TF‑IDF + Fuzzy Matching (tanpa LLM).")
+demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio>=4.0.0,<5
+scikit-learn>=1.2
+rapidfuzz>=3.0
+numpy>=1.23

runtime.txt

@@ -0,0 +1 @@
+python-3.10