|
from datetime import datetime |
|
from io import BytesIO |
|
from pathlib import Path |
|
from typing import Dict, Any, List |
|
|
|
from markdown import markdown |
|
|
|
import site |
|
from fpdf import FPDF |
|
|
|
from open_webui.env import STATIC_DIR, FONTS_DIR |
|
from open_webui.apps.webui.models.chats import ChatTitleMessagesForm |
|
|
|
|
|
class PDFGenerator: |
|
""" |
|
Description: |
|
The `PDFGenerator` class is designed to create PDF documents from chat messages. |
|
The process involves transforming markdown content into HTML and then into a PDF format |
|
|
|
Attributes: |
|
- `form_data`: An instance of `ChatTitleMessagesForm` containing title and messages. |
|
|
|
""" |
|
|
|
def __init__(self, form_data: ChatTitleMessagesForm): |
|
self.html_body = None |
|
self.messages_html = None |
|
self.form_data = form_data |
|
|
|
self.css = Path(STATIC_DIR / "assets" / "pdf-style.css").read_text() |
|
|
|
def format_timestamp(self, timestamp: float) -> str: |
|
"""Convert a UNIX timestamp to a formatted date string.""" |
|
try: |
|
date_time = datetime.fromtimestamp(timestamp) |
|
return date_time.strftime("%Y-%m-%d, %H:%M:%S") |
|
except (ValueError, TypeError) as e: |
|
|
|
return "" |
|
|
|
def _build_html_message(self, message: Dict[str, Any]) -> str: |
|
"""Build HTML for a single message.""" |
|
role = message.get("role", "user") |
|
content = message.get("content", "") |
|
timestamp = message.get("timestamp") |
|
|
|
model = message.get("model") if role == "assistant" else "" |
|
|
|
date_str = self.format_timestamp(timestamp) if timestamp else "" |
|
|
|
|
|
|
|
html_content = markdown(content, extensions=["pymdownx.extra"]) |
|
|
|
html_message = f""" |
|
<div> {date_str} </div> |
|
<div class="message"> |
|
<div> |
|
<h2> |
|
<strong>{role.title()}</strong> |
|
<span style="font-size: 12px; color: #888;">{model}</span> |
|
</h2> |
|
</div> |
|
<pre class="markdown-section"> |
|
{content} |
|
</pre> |
|
</div> |
|
""" |
|
return html_message |
|
|
|
def _generate_html_body(self) -> str: |
|
"""Generate the full HTML body for the PDF.""" |
|
return f""" |
|
<html> |
|
<head> |
|
<meta charset="UTF-8"> |
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"> |
|
</head> |
|
<body> |
|
<div class="container"> |
|
<div class="text-center"> |
|
<h1>{self.form_data.title}</h1> |
|
</div> |
|
<div> |
|
{self.messages_html} |
|
</div> |
|
</div> |
|
</body> |
|
</html> |
|
""" |
|
|
|
def generate_chat_pdf(self) -> bytes: |
|
""" |
|
Generate a PDF from chat messages. |
|
""" |
|
try: |
|
global FONTS_DIR |
|
|
|
pdf = FPDF() |
|
pdf.add_page() |
|
|
|
|
|
if not FONTS_DIR.exists(): |
|
FONTS_DIR = Path(site.getsitepackages()[0]) / "static/fonts" |
|
|
|
|
|
if not FONTS_DIR.exists(): |
|
FONTS_DIR = Path("./backend/static/fonts") |
|
|
|
pdf.add_font("NotoSans", "", f"{FONTS_DIR}/NotoSans-Regular.ttf") |
|
pdf.add_font("NotoSans", "b", f"{FONTS_DIR}/NotoSans-Bold.ttf") |
|
pdf.add_font("NotoSans", "i", f"{FONTS_DIR}/NotoSans-Italic.ttf") |
|
pdf.add_font("NotoSansKR", "", f"{FONTS_DIR}/NotoSansKR-Regular.ttf") |
|
pdf.add_font("NotoSansJP", "", f"{FONTS_DIR}/NotoSansJP-Regular.ttf") |
|
pdf.add_font("NotoSansSC", "", f"{FONTS_DIR}/NotoSansSC-Regular.ttf") |
|
|
|
pdf.set_font("NotoSans", size=12) |
|
pdf.set_fallback_fonts(["NotoSansKR", "NotoSansJP", "NotoSansSC"]) |
|
|
|
pdf.set_auto_page_break(auto=True, margin=15) |
|
|
|
|
|
messages_html_list: List[str] = [ |
|
self._build_html_message(msg) for msg in self.form_data.messages |
|
] |
|
self.messages_html = "<div>" + "".join(messages_html_list) + "</div>" |
|
|
|
|
|
self.html_body = self._generate_html_body() |
|
|
|
pdf.write_html(self.html_body) |
|
|
|
|
|
pdf_bytes = pdf.output() |
|
|
|
return bytes(pdf_bytes) |
|
except Exception as e: |
|
raise e |
|
|
