Download modules/user_modeling/extractor.py from recommender-system/llmproccrs: direct link, hf CLI and curl.
- Browser
- Download file 3.92 kB
-
https://huggingface.co/recommender-system/llmproccrs/resolve/main/modules/user_modeling/extractor.py
- Command line
-
hf download hf://recommender-system/llmproccrs/modules/user_modeling/extractor.py
-
curl -L -o extractor.py https://huggingface.co/recommender-system/llmproccrs/resolve/main/modules/user_modeling/extractor.py
3.92 kB
| import json | |
| from langchain_core.prompts import PromptTemplate | |
| from config import Config | |
| class EntityExtractor: | |
| def __init__(self): | |
| # Temperature 0 agar output konsisten | |
| self.llm = Config.get_llm(temperature=0.0) | |
| self.template = """ | |
| Kamu adalah sistem NER (Named Entity Recognition) e-Procurement yang cerdas. | |
| Tugas: Ekstrak entitas dari input user ke dalam format JSON yang terstruktur secara ketat. | |
| Input User: "{user_text}" | |
| Panduan Ekstraksi: | |
| 1. Product: Nama barang/jasa. | |
| 2. Brand : Merek (contoh: "ASUS", "Epson"). | |
| 3. Location: Kota/Provinsi. | |
| 4. Supplier: Nama toko/PT/CV. | |
| 5. Price: HARUS berupa objek dengan field: | |
| - "text": Teks asli (misal: "di bawah 10 juta") | |
| - "value": Angka numerik (integer), contoh: 10000000. Jika rentang, ambil batas atas. | |
| - "operator": Simbol matematika ("<" untuk kurang dari/murah, ">" untuk lebih dari, "=" untuk sekitar/pas). | |
| - jika tidak maka tidak perlu di ekstrak. | |
| 6. Category: Kategori produk. | |
| 7. Specs : Spesifikasi teknis/detail. | |
| - AMBIL kata kunci teknisnya saja. | |
| - Hapus kata sambung (yang, minimal, harus, dll). | |
| - Contoh Input: "yang ramnya minimal 8 GB" -> Output Specs: "RAM 8GB". | |
| - Contoh Input: "warna merah" -> Output Specs: "Merah". | |
| Aturan Output: | |
| - KEMBALIKAN HANYA JSON VALID. | |
| - Jangan ada teks pengantar. | |
| - Jika entitas tidak ditemukan, isi dengan null atau string kosong. | |
| - DILARANG memberikan komentar (// atau #) di dalam JSON. | |
| - DILARANG memberikan penjelasan tambahan di luar JSON. | |
| CONTOH OUTPUT YANG DIHARAPKAN (Strict JSON): | |
| {{ | |
| "product": "Laptop", | |
| "brand": "Lenovo", | |
| "specs": "RAM 8GB Core i5", | |
| "location": "Bali", | |
| "price": {{ | |
| "text": "di bawah 10 juta", | |
| "value": 10000000, | |
| "operator": "<" | |
| }}, | |
| "supplier": "PT SFJ", | |
| "category": "Elektronik" | |
| }} | |
| """ | |
| self.prompt = PromptTemplate(input_variables=["user_text"], template=self.template) | |
| # --- PERUBAHAN: MENGGUNAKAN LCEL (Pipe Syntax) --- | |
| # Ini menggantikan LLMChain | |
| self.chain = self.prompt | self.llm | |
| def run(self, state: dict) -> dict: | |
| user_text = state.get("user_text", "") | |
| current_constraints = state.get("collected_constraints", {}) | |
| if not user_text: | |
| return state | |
| try: | |
| # --- PERUBAHAN: EXECUTION --- | |
| # invoke() mengembalikan object AIMessage, kita ambil .content nya | |
| response = self.chain.invoke({"user_text": user_text}) | |
| raw_response = response.content.strip() | |
| # Cleaning JSON | |
| cleaned_json = raw_response.replace("```json", "").replace("```", "").strip() | |
| new_entities = json.loads(cleaned_json) | |
| # Merging Logic | |
| updated_constraints = current_constraints.copy() | |
| extracted_this_turn = [] | |
| for key, value in new_entities.items(): | |
| if value and str(value).lower() != "null": | |
| updated_constraints[key] = value | |
| extracted_this_turn.append({"type": key, "text": value}) | |
| # Update State | |
| state["collected_constraints"] = updated_constraints | |
| state["entities"] = extracted_this_turn | |
| # print(f"[UMS] Extracted: {extracted_this_turn}") | |
| except json.JSONDecodeError: | |
| print(f"[UMS] Error Parsing JSON: {raw_response}") | |
| except Exception as e: | |
| print(f"[UMS] General Error: {e}") | |
| return state |