Spaces:
Sleeping
Sleeping
| import PyPDF2 | |
| import os | |
| import io | |
| import csv | |
| import pandas as pd | |
| from openpyxl import load_workbook | |
| def read_pdf(file): | |
| reader = PyPDF2.PdfReader(file) | |
| text = "" | |
| for page in reader.pages: | |
| text += page.extract_text() or "" | |
| return text | |
| def load_children_data(source=None): | |
| if source is None: | |
| path = os.path.join(os.path.dirname(__file__), "children_requirements.xlsx") | |
| if not os.path.exists(path): | |
| return [] | |
| else: | |
| path = None | |
| if path: | |
| if path.endswith(".csv"): | |
| return pd.read_csv(path) | |
| return pd.read_excel(path) | |
| file_bytes = source.getvalue() | |
| name = source.name.lower() | |
| if name.endswith(".csv"): | |
| return pd.read_csv(io.StringIO(file_bytes.decode("utf-8"))) | |
| wb = load_workbook(io.BytesIO(file_bytes)) | |
| ws = wb.active | |
| rows = list(ws.iter_rows(values_only=True)) | |
| headers = rows[0] | |
| return [dict(zip(headers, r)) for r in rows[1:]] | |
| def build_prompt(resume_text, child_profile): | |
| return f""" | |
| You are an HR assistant for an autism therapy company. | |
| Resume: | |
| {resume_text} | |
| Child Requirements: | |
| {child_profile} | |
| Answer clearly: | |
| 1. Is the therapist suitable? (Yes or No) | |
| 2. Short reason | |
| 3. Interview recommendation | |
| """ | |