Spaces:
Paused
Paused
| from __future__ import annotations | |
| import os | |
| import re | |
| import subprocess | |
| import zipfile | |
| import json | |
| import torch | |
| from typing import List | |
| os.environ["OMP_NUM_THREADS"] = "1" | |
| os.environ["OPENBLAS_NUM_THREADS"] = "1" | |
| os.environ["MKL_NUM_THREADS"] = "1" | |
| os.environ["NUMEXPR_NUM_THREADS"] = "1" | |
| os.environ["VECLIB_MAXIMUM_THREADS"] = "1" | |
| from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig | |
| import torch | |
| bnb_config = BitsAndBytesConfig( | |
| load_in_4bit=True, | |
| bnb_4bit_compute_dtype=torch.float16, | |
| bnb_4bit_use_double_quant=True, | |
| bnb_4bit_quant_type="nf4" | |
| ) | |
| # --- UPDATED: Using Deepseek-Coder-V2-Lite-Instruct for better performance --- | |
| tokenizer = AutoTokenizer.from_pretrained("deepseek-ai/Deepseek-Coder-V2-Lite-Instruct", trust_remote_code=True) | |
| model = AutoModelForCausalLM.from_pretrained( | |
| "deepseek-ai/Deepseek-Coder-V2-Lite-Instruct", | |
| quantization_config=bnb_config, | |
| device_map="auto", | |
| torch_dtype=torch.bfloat16, | |
| trust_remote_code=True | |
| ) | |
| # =============================== | |
| # Text Extraction (PDF/DOCX) | |
| # =============================== | |
| def extract_text(file_path: str) -> str: | |
| """Extract text from PDF or DOCX resumes.""" | |
| if not file_path or not os.path.isfile(file_path): | |
| return "" | |
| lower_name = file_path.lower() | |
| try: | |
| if lower_name.endswith('.pdf'): | |
| result = subprocess.run( | |
| ['pdftotext', '-layout', file_path, '-'], | |
| stdout=subprocess.PIPE, | |
| stderr=subprocess.PIPE, | |
| check=False | |
| ) | |
| return result.stdout.decode('utf-8', errors='ignore') | |
| elif lower_name.endswith('.docx'): | |
| with zipfile.ZipFile(file_path) as zf: | |
| with zf.open('word/document.xml') as docx_xml: | |
| xml_bytes = docx_xml.read() | |
| xml_text = xml_bytes.decode('utf-8', errors='ignore') | |
| xml_text = re.sub(r'<w:p[^>]*>', '\n', xml_text, flags=re.I) | |
| text = re.sub(r'<[^>]+>', ' ', xml_text) | |
| return re.sub(r'\s+', ' ', text) | |
| else: | |
| return "" | |
| except Exception: | |
| return "" | |
| # =============================== | |
| # Name Extraction (Fallback) | |
| # =============================== | |
| def extract_name(text: str, filename: str) -> str: | |
| """Extract candidate's name from resume text or filename.""" | |
| if text: | |
| lines = [ln.strip() for ln in text.splitlines() if ln.strip()] | |
| for line in lines[:10]: | |
| if re.match(r'(?i)resume|curriculum vitae', line): | |
| continue | |
| words = line.split() | |
| if 1 < len(words) <= 4: | |
| if all(re.match(r'^[A-ZÀ-ÖØ-Þ][\w\-]*', w) for w in words): | |
| return line | |
| base = os.path.basename(filename) | |
| base = re.sub(r'\.(pdf|docx|doc)$', '', base, flags=re.I) | |
| base = re.sub(r'[\._-]+', ' ', base) | |
| base = re.sub(r'(?i)\b(cv|resume)\b', '', base) | |
| return base.title().strip() | |
| # =============================== | |
| # Janus-Pro Parsing | |
| # =============================== | |
| def parse_with_deepseek(text: str) -> dict: | |
| """Use Deepseek-Coder-V2-Lite-Instruct to extract resume details in JSON format.""" | |
| prompt = f""" | |
| Extract the following information from the resume text provided below. Your response should be a valid JSON object. | |
| Information to extract: | |
| - Full Name: The candidate's full name. | |
| - Email: The candidate's email address. | |
| - Phone: The candidate's phone number. | |
| - Skills: A list of technical and soft skills. | |
| - Education: A list of academic degrees and institutions. | |
| - Experience: A list of previous jobs, including company, title, and dates. | |
| Resume Text: | |
| {text} | |
| Return only valid JSON in the following format: | |
| {{ | |
| "name": "Full Name", | |
| "email": "[email protected]", | |
| "phone": "+961-xxx-xxx", | |
| "skills": ["Skill1", "Skill2", "Skill3"], | |
| "education": ["Degree1 - Institution1", "Degree2 - Institution2"], | |
| "experience": ["Job1 - Company1 (Dates)", "Job2 - Company2 (Dates)"] | |
| }} | |
| """ | |
| inputs = tokenizer(prompt, return_tensors="pt").to(model.device) | |
| outputs = model.generate(**inputs, max_new_tokens=512) | |
| response = tokenizer.decode(outputs[0], skip_special_tokens=True) | |
| import re, json | |
| match = re.search(r"\{.*\}", response, re.S) | |
| if match: | |
| try: | |
| return json.loads(match.group()) | |
| except: | |
| pass | |
| return {"name": "", "email": "", "phone": "", "skills": [], "education": [], "experience": []} | |