commit 05a37dd9562ae1f22d5af0b62529c4ddfc199694
Author: Biema Putra Indra <biema-p.inf25@ukwms.ac.id>
Date:   Sun Nov 1 22:27:07 2026 -0500

    Upload files to "/"

diff --git a/Buku Pedoman Akademik.pdf b/Buku Pedoman Akademik.pdf
new file mode 100644
index 0000000..39d68d7
Binary files /dev/null and b/Buku Pedoman Akademik.pdf differ
diff --git a/tugas week 10..py b/tugas week 10..py
new file mode 100644
index 0000000..dc8747d
--- /dev/null
+++ b/tugas week 10..py	
@@ -0,0 +1,91 @@
+import os
+import chromadb
+from chromadb.utils import embedding_functions
+from pypdf import PdfReader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+
+# 1. Persiapan Dokumen
+pdf_path = "dokumen_akademik.pdf" # Ganti dengan nama file PDF yang disiapkan
+print(f"Membaca file: {pdf_path}")
+
+reader = PdfReader('Buku Pedoman Akademik.pdf')
+raw_text = ""
+for page in reader.pages:
+    # Menggabungkan seluruh teks dari PDF
+    raw_text += page.extract_text() + "\n"
+
+# 2. Setup Embedding Function
+# Menggunakan model multilingual lokal agar performa pencarian untuk Bahasa Indonesia lebih akurat
+print("Menyiapkan model embedding (ini akan mengunduh model pada run pertama)...")
+emb_fn = embedding_functions.SentenceTransformerEmbeddingFunction(
+    model_name="paraphrase-multilingual-MiniLM-L12-v2"
+)
+
+# 3. Inisialisasi ChromaDB Client
+# PersistentClient akan membuat folder 'chroma_db_data' untuk menyimpan vektor secara lokal
+client = chromadb.PersistentClient(path="./chroma_db_data")
+
+# Eksperimen 3 ukuran chunk sesuai instruksi modul
+chunk_sizes = [500, 1000, 1500]
+
+for size in chunk_sizes:
+    print(f"\n--- Memproses ukuran chunk: {size} karakter ---")
+    collection_name = f"rag_koleksi_chunk_{size}"
+    
+    # Hapus collection jika sebelumnya sudah ada saat di-run ulang
+    try:
+        client.delete_collection(name=collection_name)
+    except Exception:
+        pass
+        
+    # Buat collection baru di vector DB
+    collection = client.create_collection(
+        name=collection_name, 
+        embedding_function=emb_fn
+    )
+    
+    # 4. Setup Text Splitter
+    # Overlap disetel 10% dari ukuran chunk untuk mencegah konteks terpotong mendadak
+    text_splitter = RecursiveCharacterTextSplitter(
+        chunk_size=size,
+        chunk_overlap=int(size * 0.1), 
+        length_function=len,
+    )
+    
+    # Potong teks menjadi list of chunks
+    chunks = text_splitter.split_text(raw_text)
+    print(f"Total chunk yang dihasilkan: {len(chunks)} chunks")
+    
+    # 5. Persiapkan ID dan Metadata
+    ids = [f"id_chunk_{size}_{i}" for i in range(len(chunks))]
+    metadatas = [{"source": pdf_path, "chunk_size": size, "chunk_index": i} for i in range(len(chunks))]
+    
+    # 6. Masukkan Vektor, Teks, dan Metadata ke Vector Database
+    collection.add(
+        documents=chunks,
+        metadatas=metadatas,
+        ids=ids
+    )
+    print(f"Data chunk {size} berhasil di-index ke ChromaDB!")
+
+# ==========================================
+# CONTOH PENCARIAN (QUERY)
+# ==========================================
+print("\n--- Menguji Pencarian (Query Retrieval) ---")
+query_text = "Apa syarat untuk mengajukan cuti akademik?" # Sesuaikan dengan isi PDF yang di-load
+
+# Kita uji pencarian di collection yang ukuran chunk-nya 1000
+test_collection = client.get_collection(name="rag_koleksi_chunk_1000", embedding_function=emb_fn)
+
+# Retrieve Top-K (K=2)
+results = test_collection.query(
+    query_texts=[query_text],
+    n_results=2
+)
+
+print(f"Pertanyaan: '{query_text}'\n")
+
+# Hasil dibungkus di dalam list of lists oleh chromadb, maka kita akses index [0]
+for i, (doc, dist) in enumerate(zip(results['documents'][0], results['distances'][0])):
+    print(f"--- Top {i+1} (Jarak Vektor: {dist:.4f}) ---")
+    print(f"{doc}\n")
\ No newline at end of file