import gradio as gr
import pandas as pd
from langchain_core.prompts import PromptTemplate
from langchain_openai import ChatOpenAI
from langchain_core.output_parsers import StrOutputParser
from pydantic import BaseModel, Field, field_validator
from langchain_community.document_loaders import PyPDFLoader, Docx2txtLoader
from langchain.output_parsers import PydanticOutputParser
from docx import Document
from datetime import datetime
import os
import tempfile
theme = gr.themes.Default(
primary_hue="green",
neutral_hue="gray",
font=[gr.themes.GoogleFont("Inter"), "sans-serif"]
).set(
button_primary_background_fill="#f1f1e8", # jasny beż
button_primary_border_color="#014421", # ciemna zieleń
button_primary_text_color="black",
block_background_fill="#ffffff", # białe tło bloków
block_border_color="#014421", # ciemnozielona ramka
block_label_text_color="black"
)
# Model danych
class QuestionAnswer(BaseModel):
question_number: int = Field(..., description="Numer pytania")
answer: str = Field(..., description="Odpowiedź, tylko TAK lub NIE")
citation: str = Field(..., description="Fragment cytatu")
@field_validator("answer")
def validate_answer(cls, v):
if v not in {"TAK", "NIE"}:
raise ValueError("Odpowiedź musi być TAK lub NIE")
return v
class JobAdAnalysis(BaseModel):
answers: list[QuestionAnswer]
parser = PydanticOutputParser(pydantic_object=JobAdAnalysis)
# Wczytanie matrycy danych
matryca_df = pd.read_csv('matryca.csv', header=None,
names=['area', 'prompt', 'true', 'false', 'more', 'hint'])
question_to_area_map = {}
def prepare_questions(df):
global question_to_area_map
question_to_area_map = {}
questions_text = ""
for index, row in df.iterrows():
question_number = index + 1
questions_text += f"{question_number} {row['prompt']}\n"
question_to_area_map[question_number] = {
'area': row['area'],
'true': row['true'],
'false': row['false'],
'hint': row['hint'],
'more': row['more']
}
return questions_text
def doc_to_text(file):
extension = os.path.splitext(file.name)[1].lower()
if extension == ".docx":
loader = Docx2txtLoader(file.name)
elif extension == ".pdf":
loader = PyPDFLoader(file.name)
else:
return "error"
pages = loader.load()
return "\n".join(page.page_content for page in pages)
def create_html_inline(result: pd.DataFrame) -> str:
html = "Raport analizy ogłoszenia o pracę
"
html += f"Data wygenerowania: {datetime.now().strftime('%d.%m.%Y %H:%M')}
"
for _, row in result.iterrows():
html += f"{row['area']}
"
html += f"{row['citation']}
"
for line in str(row['content']).split('\n'):
if line.strip():
html += f"{line}
"
if pd.notna(row['more']):
html += "Dodatkowe informacje
"
for line in str(row['more']).split('\n'):
if line.strip():
html += f"{line}
"
html += "