2024-10-13 00:12:31 +08:00
|
|
|
from datetime import datetime
|
|
|
|
|
from io import BytesIO
|
|
|
|
|
from pathlib import Path
|
|
|
|
|
from typing import Dict, Any, List
|
2025-02-10 10:35:10 +08:00
|
|
|
from html import escape
|
2024-10-13 00:12:31 +08:00
|
|
|
|
|
|
|
|
from markdown import markdown
|
|
|
|
|
|
2024-10-13 15:05:28 +08:00
|
|
|
import site
|
|
|
|
|
from fpdf import FPDF
|
|
|
|
|
|
|
|
|
|
from open_webui.env import STATIC_DIR, FONTS_DIR
|
2024-12-10 16:54:13 +08:00
|
|
|
from open_webui.models.chats import ChatTitleMessagesForm
|
2024-10-13 00:12:31 +08:00
|
|
|
|
2025-02-10 14:20:47 +08:00
|
|
|
|
2024-10-13 00:12:31 +08:00
|
|
|
class PDFGenerator:
|
|
|
|
|
"""
|
|
|
|
|
Description:
|
|
|
|
|
The `PDFGenerator` class is designed to create PDF documents from chat messages.
|
2024-10-13 15:21:06 +08:00
|
|
|
The process involves transforming markdown content into HTML and then into a PDF format
|
2024-10-13 00:12:31 +08:00
|
|
|
|
|
|
|
|
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
|
|
|
|
|
|
2024-10-13 15:05:28 +08:00
|
|
|
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:
|
|
|
|
|
# Log the error if necessary
|
|
|
|
|
return ""
|
|
|
|
|
|
|
|
|
|
def _build_html_message(self, message: Dict[str, Any]) -> str:
|
2024-10-13 00:12:31 +08:00
|
|
|
"""Build HTML for a single message."""
|
2025-02-10 10:35:10 +08:00
|
|
|
role = escape(message.get("role", "user"))
|
|
|
|
|
content = escape(message.get("content", ""))
|
2024-10-13 15:05:28 +08:00
|
|
|
timestamp = message.get("timestamp")
|
2024-10-13 00:12:31 +08:00
|
|
|
|
2025-02-10 10:35:10 +08:00
|
|
|
model = escape(message.get("model") if role == "assistant" else "")
|
2024-10-13 00:12:31 +08:00
|
|
|
|
2025-02-10 10:35:10 +08:00
|
|
|
date_str = escape(self.format_timestamp(timestamp) if timestamp else "")
|
2024-10-13 00:12:31 +08:00
|
|
|
|
|
|
|
|
# extends pymdownx extension to convert markdown to html.
|
|
|
|
|
# - https://facelessuser.github.io/pymdown-extensions/usage_notes/
|
2024-12-08 06:28:17 +08:00
|
|
|
# html_content = markdown(content, extensions=["pymdownx.extra"])
|
2024-10-13 00:12:31 +08:00
|
|
|
|
2025-01-08 23:49:53 +08:00
|
|
|
content = content.replace("\n", "<br/>")
|
2024-10-13 00:12:31 +08:00
|
|
|
html_message = f"""
|
2024-12-08 06:28:17 +08:00
|
|
|
<div>
|
2024-10-28 20:47:53 +08:00
|
|
|
<div>
|
2024-12-08 06:28:17 +08:00
|
|
|
<h4>
|
2024-10-28 20:47:53 +08:00
|
|
|
<strong>{role.title()}</strong>
|
2024-12-08 06:28:17 +08:00
|
|
|
<span style="font-size: 12px;">{model}</span>
|
|
|
|
|
</h4>
|
|
|
|
|
<div> {date_str} </div>
|
2024-10-28 20:47:53 +08:00
|
|
|
</div>
|
2024-12-08 06:28:17 +08:00
|
|
|
<br/>
|
|
|
|
|
<br/>
|
|
|
|
|
|
|
|
|
|
<div>
|
2024-10-28 20:47:53 +08:00
|
|
|
{content}
|
2024-12-08 06:28:17 +08:00
|
|
|
</div>
|
2024-10-28 20:47:53 +08:00
|
|
|
</div>
|
2024-12-08 06:28:17 +08:00
|
|
|
<br/>
|
2024-10-13 00:12:31 +08:00
|
|
|
"""
|
|
|
|
|
return html_message
|
|
|
|
|
|
2024-10-13 15:05:28 +08:00
|
|
|
def _generate_html_body(self) -> str:
|
2024-10-13 00:12:31 +08:00
|
|
|
"""Generate the full HTML body for the PDF."""
|
2025-02-10 10:35:10 +08:00
|
|
|
escaped_title = escape(self.form_data.title)
|
2024-10-13 00:12:31 +08:00
|
|
|
return f"""
|
|
|
|
|
<html>
|
|
|
|
|
<head>
|
2024-12-08 06:28:17 +08:00
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
|
2024-10-13 00:12:31 +08:00
|
|
|
</head>
|
|
|
|
|
<body>
|
2024-12-08 06:28:17 +08:00
|
|
|
<div>
|
|
|
|
|
<div>
|
2025-02-10 10:35:10 +08:00
|
|
|
<h2>{escaped_title}</h2>
|
2024-12-08 06:28:17 +08:00
|
|
|
{self.messages_html}
|
2024-10-13 00:12:31 +08:00
|
|
|
</div>
|
2024-12-08 06:28:17 +08:00
|
|
|
</div>
|
2024-10-13 00:12:31 +08:00
|
|
|
</body>
|
|
|
|
|
</html>
|
|
|
|
|
"""
|
2024-10-13 15:05:28 +08:00
|
|
|
|
|
|
|
|
def generate_chat_pdf(self) -> bytes:
|
|
|
|
|
"""
|
|
|
|
|
Generate a PDF from chat messages.
|
|
|
|
|
"""
|
|
|
|
|
try:
|
|
|
|
|
global FONTS_DIR
|
|
|
|
|
|
|
|
|
|
pdf = FPDF()
|
|
|
|
|
pdf.add_page()
|
|
|
|
|
|
|
|
|
|
# When running using `pip install` the static directory is in the site packages.
|
|
|
|
|
if not FONTS_DIR.exists():
|
|
|
|
|
FONTS_DIR = Path(site.getsitepackages()[0]) / "static/fonts"
|
|
|
|
|
# When running using `pip install -e .` the static directory is in the site packages.
|
|
|
|
|
# This path only works if `open-webui serve` is run from the root of this project.
|
|
|
|
|
if not FONTS_DIR.exists():
|
2025-03-05 01:53:52 +08:00
|
|
|
FONTS_DIR = Path(".") / "backend" / "static" / "fonts"
|
2024-10-13 15:05:28 +08:00
|
|
|
|
|
|
|
|
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")
|
2024-12-08 06:28:17 +08:00
|
|
|
pdf.add_font("Twemoji", "", f"{FONTS_DIR}/Twemoji.ttf")
|
2024-10-13 15:05:28 +08:00
|
|
|
|
|
|
|
|
pdf.set_font("NotoSans", size=12)
|
2024-12-08 06:28:17 +08:00
|
|
|
pdf.set_fallback_fonts(
|
|
|
|
|
["NotoSansKR", "NotoSansJP", "NotoSansSC", "Twemoji"]
|
|
|
|
|
)
|
2024-10-13 15:05:28 +08:00
|
|
|
|
|
|
|
|
pdf.set_auto_page_break(auto=True, margin=15)
|
|
|
|
|
|
2024-10-13 15:21:06 +08:00
|
|
|
# Build HTML messages
|
|
|
|
|
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>"
|
|
|
|
|
|
|
|
|
|
# Generate full HTML body
|
|
|
|
|
self.html_body = self._generate_html_body()
|
|
|
|
|
|
|
|
|
|
pdf.write_html(self.html_body)
|
2024-10-13 15:05:28 +08:00
|
|
|
|
|
|
|
|
# Save the pdf with name .pdf
|
|
|
|
|
pdf_bytes = pdf.output()
|
|
|
|
|
|
|
|
|
|
return bytes(pdf_bytes)
|
|
|
|
|
except Exception as e:
|
|
|
|
|
raise e
|
