Ajout des fonctionnalités d'export Word et PDF pour le chat RAG

- Ajout de python-docx et reportlab aux dépendances
- Création du module utils/word_exporter.py pour l'export Word
- Création du module utils/pdf_exporter.py pour l'export PDF
- Ajout des routes /chat/export-word et /chat/export-pdf dans flask_app.py
- Ajout des boutons d'export (Word et PDF) dans chat.html
- Les boutons apparaissent après chaque réponse de l'assistant
- Support des questions reformulées avec question originale

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
This commit is contained in:
2025-12-30 14:02:11 +01:00
parent ef8cd32711
commit b835cd13ea
5 changed files with 682 additions and 4 deletions

View File

@@ -1430,6 +1430,151 @@ def chat_stream(session_id: str) -> WerkzeugResponse:
)
@app.route("/chat/export-word", methods=["POST"])
def chat_export_word() -> Union[WerkzeugResponse, tuple[Dict[str, Any], int]]:
"""Export a chat exchange to Word format.
Generates a formatted Microsoft Word document (.docx) containing the user's
question and the assistant's response. Supports both original and reformulated
questions.
Request JSON:
user_question (str): The user's question (required).
assistant_response (str): The assistant's complete response (required).
is_reformulated (bool, optional): Whether the question was reformulated.
Default: False.
original_question (str, optional): Original question if reformulated.
Only used when is_reformulated is True.
Returns:
Word document file download (.docx) on success.
JSON error response with 400/500 status on failure.
Example:
POST /chat/export-word
Content-Type: application/json
{
"user_question": "What is phenomenology?",
"assistant_response": "Phenomenology is a philosophical movement...",
"is_reformulated": false
}
Response: chat_export_20250130_143022.docx (download)
"""
try:
data = request.get_json()
if not data:
return jsonify({"error": "No JSON data provided"}), 400
user_question = data.get("user_question")
assistant_response = data.get("assistant_response")
is_reformulated = data.get("is_reformulated", False)
original_question = data.get("original_question")
if not user_question or not assistant_response:
return (
jsonify({"error": "user_question and assistant_response are required"}),
400,
)
# Import word exporter
from utils.word_exporter import create_chat_export
# Generate Word document
filepath = create_chat_export(
user_question=user_question,
assistant_response=assistant_response,
is_reformulated=is_reformulated,
original_question=original_question,
output_dir=app.config["UPLOAD_FOLDER"],
)
# Send file as download
return send_from_directory(
directory=filepath.parent,
path=filepath.name,
as_attachment=True,
download_name=filepath.name,
)
except Exception as e:
return jsonify({"error": f"Export failed: {str(e)}"}), 500
@app.route("/chat/export-pdf", methods=["POST"])
def chat_export_pdf() -> Union[WerkzeugResponse, tuple[Dict[str, Any], int]]:
"""Export a chat exchange to PDF format.
Generates a formatted PDF document containing the user's question and the
assistant's response. Supports both original and reformulated questions.
Request JSON:
user_question (str): The user's question (required).
assistant_response (str): The assistant's complete response (required).
is_reformulated (bool, optional): Whether the question was reformulated.
Default: False.
original_question (str, optional): Original question if reformulated.
Only used when is_reformulated is True.
Returns:
PDF document file download on success.
JSON error response with 400/500 status on failure.
Example:
POST /chat/export-pdf
Content-Type: application/json
{
"user_question": "What is phenomenology?",
"assistant_response": "Phenomenology is a philosophical movement...",
"is_reformulated": false
}
Response: chat_export_20250130_143022.pdf (download)
"""
try:
data = request.get_json()
if not data:
return jsonify({"error": "No JSON data provided"}), 400
user_question = data.get("user_question")
assistant_response = data.get("assistant_response")
is_reformulated = data.get("is_reformulated", False)
original_question = data.get("original_question")
if not user_question or not assistant_response:
return (
jsonify({"error": "user_question and assistant_response are required"}),
400,
)
# Import PDF exporter
from utils.pdf_exporter import create_chat_export_pdf
# Generate PDF document
filepath = create_chat_export_pdf(
user_question=user_question,
assistant_response=assistant_response,
is_reformulated=is_reformulated,
original_question=original_question,
output_dir=app.config["UPLOAD_FOLDER"],
)
# Send file as download
return send_from_directory(
directory=filepath.parent,
path=filepath.name,
as_attachment=True,
download_name=filepath.name,
)
except Exception as e:
return jsonify({"error": f"Export failed: {str(e)}"}), 500
# ═══════════════════════════════════════════════════════════════════════════════
# PDF Upload & Processing
# ═══════════════════════════════════════════════════════════════════════════════

View File

@@ -5,6 +5,8 @@ mistralai>=1.0.0
python-dotenv>=1.0.0
requests>=2.31.0
werkzeug>=3.0.0
python-docx>=1.1.0
reportlab>=4.0.0
# MCP Server dependencies
mcp>=1.0.0

View File

@@ -587,6 +587,44 @@
.sidebar-content::-webkit-scrollbar-thumb:hover {
background: rgba(125, 110, 88, 0.5);
}
/* Export buttons - compact size */
.export-word-btn,
.export-pdf-btn {
display: inline-flex;
align-items: center;
justify-content: center;
gap: 0.4rem;
padding: 0.85rem 1.75rem;
margin-top: 0.75rem;
margin-right: 0.5rem;
border-radius: 8px;
border: 1.5px solid var(--color-accent);
background-color: var(--color-accent);
color: var(--color-bg-main);
font-family: var(--font-body);
font-size: 0.95rem;
font-weight: 500;
cursor: pointer;
text-decoration: none;
white-space: nowrap;
max-width: fit-content;
transition: background-color 0.2s ease, color 0.2s ease, border-color 0.2s ease;
}
.export-word-btn:hover,
.export-pdf-btn:hover {
background-color: var(--color-accent-alt);
border-color: var(--color-accent-alt);
color: var(--color-bg-main);
}
.export-word-btn svg,
.export-pdf-btn svg {
width: 15px;
height: 15px;
flex-shrink: 0;
}
</style>
<div class="chat-container">
@@ -850,6 +888,13 @@
const chosenQuestion = btn.getAttribute('data-question');
const isReformulated = btn.classList.contains('btn-reformulated');
// Store context for export
window.currentChatContext = {
question: chosenQuestion,
isReformulated: isReformulated,
originalQuestion: isReformulated ? original : null
};
// Disable both buttons
buttons.forEach(b => b.disabled = true);
@@ -906,8 +951,8 @@
const data = await response.json();
const sessionId = data.session_id;
// SSE stream
startSSEStream(sessionId, typingId);
// SSE stream with chat context
startSSEStream(sessionId, typingId, window.currentChatContext || {});
} catch (error) {
console.error('Error:', error);
@@ -919,7 +964,7 @@
}
}
function startSSEStream(sessionId, typingId) {
function startSSEStream(sessionId, typingId, chatContext = {}) {
// Close previous EventSource if exists
if (currentEventSource) {
currentEventSource.close();
@@ -930,8 +975,16 @@
let assistantMessageDiv = null;
let assistantContentDiv = null;
let exportWordBtn = null;
let exportPdfBtn = null;
let exportContainer = null;
let accumulatedText = '';
// Get chat context (question, reformulation status)
const currentQuestion = chatContext.question || '';
const isReformulated = chatContext.isReformulated || false;
const originalQuestion = chatContext.originalQuestion || '';
eventSource.onmessage = function(event) {
try {
const data = JSON.parse(event.data);
@@ -951,6 +1004,9 @@
const result = createAssistantMessage();
assistantMessageDiv = result.messageDiv;
assistantContentDiv = result.contentDiv;
exportWordBtn = result.exportWordBtn;
exportPdfBtn = result.exportPdfBtn;
exportContainer = result.exportContainer;
}
// Accumulate text
@@ -969,6 +1025,32 @@
}
else if (data.type === 'complete') {
// Generation complete
// Show export buttons
if (exportContainer && accumulatedText) {
exportContainer.style.display = 'block';
// Add click handler for Word export
exportWordBtn.addEventListener('click', async () => {
await exportToWord(
currentQuestion,
accumulatedText,
isReformulated,
originalQuestion
);
});
// Add click handler for PDF export
exportPdfBtn.addEventListener('click', async () => {
await exportToPdf(
currentQuestion,
accumulatedText,
isReformulated,
originalQuestion
);
});
}
eventSource.close();
currentEventSource = null;
isGenerating = false;
@@ -1033,11 +1115,42 @@
const contentDiv = document.createElement('div');
contentDiv.className = 'message-content';
// Add export buttons container
const exportContainer = document.createElement('div');
exportContainer.style.display = 'none'; // Hidden until response is complete
// Add export Word button
const exportWordBtn = document.createElement('button');
exportWordBtn.className = 'export-word-btn';
exportWordBtn.innerHTML = `
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor">
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8l-6-6z"/>
<path d="M14 2v6h6"/>
<path d="M10.5 13.5l1.5 3 1.5-3"/>
</svg>
Word
`;
// Add export PDF button
const exportPdfBtn = document.createElement('button');
exportPdfBtn.className = 'export-pdf-btn';
exportPdfBtn.innerHTML = `
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="currentColor">
<path d="M14 2H6a2 2 0 0 0-2 2v16a2 2 0 0 0 2 2h12a2 2 0 0 0 2-2V8l-6-6z"/>
<path d="M14 2v6h6"/>
</svg>
PDF
`;
exportContainer.appendChild(exportWordBtn);
exportContainer.appendChild(exportPdfBtn);
messageDiv.appendChild(label);
messageDiv.appendChild(contentDiv);
messageDiv.appendChild(exportContainer);
chatMessages.appendChild(messageDiv);
return { messageDiv, contentDiv };
return { messageDiv, contentDiv, exportWordBtn, exportPdfBtn, exportContainer };
}
function addErrorMessage(message) {
@@ -1165,6 +1278,76 @@
});
}
async function exportToWord(userQuestion, assistantResponse, isReformulated = false, originalQuestion = '') {
try {
const response = await fetch('/chat/export-word', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
user_question: userQuestion,
assistant_response: assistantResponse,
is_reformulated: isReformulated,
original_question: originalQuestion
})
});
if (!response.ok) {
const error = await response.json();
throw new Error(error.error || 'Export failed');
}
// Download file
const blob = await response.blob();
const url = window.URL.createObjectURL(blob);
const a = document.createElement('a');
a.href = url;
a.download = `chat_export_${new Date().getTime()}.docx`;
document.body.appendChild(a);
a.click();
window.URL.revokeObjectURL(url);
document.body.removeChild(a);
} catch (error) {
console.error('Export error:', error);
alert(`Erreur d'export: ${error.message}`);
}
}
async function exportToPdf(userQuestion, assistantResponse, isReformulated = false, originalQuestion = '') {
try {
const response = await fetch('/chat/export-pdf', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
user_question: userQuestion,
assistant_response: assistantResponse,
is_reformulated: isReformulated,
original_question: originalQuestion
})
});
if (!response.ok) {
const error = await response.json();
throw new Error(error.error || 'Export failed');
}
// Download file
const blob = await response.blob();
const url = window.URL.createObjectURL(blob);
const a = document.createElement('a');
a.href = url;
a.download = `chat_export_${new Date().getTime()}.pdf`;
document.body.appendChild(a);
a.click();
window.URL.revokeObjectURL(url);
document.body.removeChild(a);
} catch (error) {
console.error('Export error:', error);
alert(`Erreur d'export: ${error.message}`);
}
}
// Initialize
sendBtn.disabled = true;
</script>

View File

@@ -0,0 +1,204 @@
"""Generate PDF documents from chat exchanges.
This module provides functionality to export chat conversations between users
and the RAG assistant into formatted PDF documents.
Example:
Export a simple chat exchange::
from pathlib import Path
from utils.pdf_exporter import create_chat_export_pdf
filepath = create_chat_export_pdf(
user_question="What is phenomenology?",
assistant_response="Phenomenology is a philosophical movement...",
output_dir=Path("output")
)
Export with reformulated question::
filepath = create_chat_export_pdf(
user_question="What does Husserl mean by phenomenology?",
assistant_response="Husserl defines phenomenology as...",
is_reformulated=True,
original_question="What is phenomenology?",
output_dir=Path("output")
)
"""
from pathlib import Path
from typing import Optional
from datetime import datetime
try:
from reportlab.lib.pagesizes import A4
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import cm
from reportlab.lib.colors import HexColor
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer
from reportlab.lib.enums import TA_CENTER, TA_JUSTIFY
except ImportError:
raise ImportError(
"reportlab is required for PDF export. "
"Install with: pip install reportlab"
)
def create_chat_export_pdf(
user_question: str,
assistant_response: str,
is_reformulated: bool = False,
original_question: Optional[str] = None,
output_dir: Path = Path("output"),
) -> Path:
"""Create a PDF document from a chat exchange.
Args:
user_question: The user's question (or reformulated version).
assistant_response: The assistant's complete response text.
is_reformulated: Whether the question was reformulated by the system.
If True, both original and reformulated questions are included.
original_question: The original user question before reformulation.
Only used when is_reformulated is True.
output_dir: Directory where the PDF file will be saved.
Created if it doesn't exist.
Returns:
Path to the generated PDF file.
Raises:
OSError: If the output directory cannot be created or file cannot be saved.
Example:
>>> from pathlib import Path
>>> filepath = create_chat_export_pdf(
... user_question="Qu'est-ce que la phénoménologie ?",
... assistant_response="La phénoménologie est...",
... output_dir=Path("output/test_exports")
... )
>>> print(filepath)
output/test_exports/chat_export_20250101_123045.pdf
"""
# Generate filename with timestamp
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
filename = f"chat_export_{timestamp}.pdf"
filepath = output_dir / filename
# Create directory if needed
output_dir.mkdir(parents=True, exist_ok=True)
# Create PDF document
doc = SimpleDocTemplate(
str(filepath),
pagesize=A4,
rightMargin=2 * cm,
leftMargin=2 * cm,
topMargin=2.5 * cm,
bottomMargin=2.5 * cm,
)
# Get default styles
styles = getSampleStyleSheet()
# Custom styles
title_style = ParagraphStyle(
"CustomTitle",
parent=styles["Heading1"],
fontSize=18,
textColor=HexColor("#2B2B2B"),
spaceAfter=6,
alignment=TA_CENTER,
fontName="Helvetica-Bold",
)
date_style = ParagraphStyle(
"DateStyle",
parent=styles["Normal"],
fontSize=9,
textColor=HexColor("#808080"),
alignment=TA_CENTER,
spaceAfter=20,
)
heading_style = ParagraphStyle(
"CustomHeading",
parent=styles["Heading2"],
fontSize=12,
textColor=HexColor("#7D6E58"),
spaceAfter=10,
spaceBefore=15,
fontName="Helvetica-Bold",
)
question_style = ParagraphStyle(
"QuestionStyle",
parent=styles["Normal"],
fontSize=11,
textColor=HexColor("#2B2B2B"),
spaceAfter=10,
leftIndent=1 * cm,
rightIndent=1 * cm,
backColor=HexColor("#F8F4EE"),
borderPadding=10,
)
body_style = ParagraphStyle(
"BodyStyle",
parent=styles["Normal"],
fontSize=11,
textColor=HexColor("#2B2B2B"),
spaceAfter=10,
alignment=TA_JUSTIFY,
leading=16,
)
footer_style = ParagraphStyle(
"FooterStyle",
parent=styles["Normal"],
fontSize=8,
textColor=HexColor("#969696"),
alignment=TA_CENTER,
fontName="Helvetica-Oblique",
)
# Build document content
story = []
# Title
story.append(Paragraph("Conversation RAG - Export", title_style))
# Date
date_text = f"Exporté le {datetime.now().strftime('%d/%m/%Y à %H:%M')}"
story.append(Paragraph(date_text, date_style))
# Original question (if reformulated)
if is_reformulated and original_question:
story.append(Paragraph("Question Originale", heading_style))
story.append(Paragraph(original_question, question_style))
story.append(Spacer(1, 0.5 * cm))
# User question
question_label = "Question Reformulée" if is_reformulated else "Question"
story.append(Paragraph(question_label, heading_style))
story.append(Paragraph(user_question, question_style))
story.append(Spacer(1, 0.5 * cm))
# Assistant response
story.append(Paragraph("Réponse de l'Assistant", heading_style))
# Split response into paragraphs
response_paragraphs = assistant_response.split("\n\n")
for para in response_paragraphs:
if para.strip():
story.append(Paragraph(para.strip(), body_style))
# Footer
story.append(Spacer(1, 1 * cm))
story.append(
Paragraph("Généré par Library RAG - Recherche Philosophique", footer_style)
)
# Build PDF
doc.build(story)
return filepath

View File

@@ -0,0 +1,144 @@
"""Generate Word documents from chat exchanges.
This module provides functionality to export chat conversations between users
and the RAG assistant into formatted Microsoft Word documents (.docx).
Example:
Export a simple chat exchange::
from pathlib import Path
from utils.word_exporter import create_chat_export
filepath = create_chat_export(
user_question="What is phenomenology?",
assistant_response="Phenomenology is a philosophical movement...",
output_dir=Path("output")
)
Export with reformulated question::
filepath = create_chat_export(
user_question="What does Husserl mean by phenomenology?",
assistant_response="Husserl defines phenomenology as...",
is_reformulated=True,
original_question="What is phenomenology?",
output_dir=Path("output")
)
"""
from pathlib import Path
from typing import Optional
from datetime import datetime
try:
from docx import Document
from docx.shared import Pt, RGBColor, Inches
from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
except ImportError:
raise ImportError(
"python-docx is required for Word export. "
"Install with: pip install python-docx"
)
def create_chat_export(
user_question: str,
assistant_response: str,
is_reformulated: bool = False,
original_question: Optional[str] = None,
output_dir: Path = Path("output"),
) -> Path:
"""Create a Word document from a chat exchange.
Args:
user_question: The user's question (or reformulated version).
assistant_response: The assistant's complete response text.
is_reformulated: Whether the question was reformulated by the system.
If True, both original and reformulated questions are included.
original_question: The original user question before reformulation.
Only used when is_reformulated is True.
output_dir: Directory where the .docx file will be saved.
Created if it doesn't exist.
Returns:
Path to the generated .docx file.
Raises:
OSError: If the output directory cannot be created or file cannot be saved.
Example:
>>> from pathlib import Path
>>> filepath = create_chat_export(
... user_question="Qu'est-ce que la phénoménologie ?",
... assistant_response="La phénoménologie est...",
... output_dir=Path("output")
... )
>>> print(filepath)
output/chat_export_20250101_123045.docx
"""
# Create document
doc = Document()
# Set margins to 1 inch on all sides
sections = doc.sections
for section in sections:
section.top_margin = Inches(1)
section.bottom_margin = Inches(1)
section.left_margin = Inches(1)
section.right_margin = Inches(1)
# Title
title = doc.add_heading("Conversation RAG - Export", level=1)
title.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
# Date
date_p = doc.add_paragraph()
date_p.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
date_run = date_p.add_run(
f"Exporté le {datetime.now().strftime('%d/%m/%Y à %H:%M')}"
)
date_run.font.size = Pt(10)
date_run.font.color.rgb = RGBColor(128, 128, 128)
doc.add_paragraph() # Spacer
# Original question (if reformulated)
if is_reformulated and original_question:
doc.add_heading("Question Originale", level=2)
original_p = doc.add_paragraph(original_question)
original_p.style = "Intense Quote"
doc.add_paragraph()
# User question
question_label = "Question Reformulée" if is_reformulated else "Question"
doc.add_heading(question_label, level=2)
question_p = doc.add_paragraph(user_question)
question_p.style = "Intense Quote"
doc.add_paragraph() # Spacer
# Assistant response
doc.add_heading("Réponse de l'Assistant", level=2)
response_p = doc.add_paragraph(assistant_response)
# Footer
doc.add_paragraph()
footer_p = doc.add_paragraph()
footer_p.alignment = WD_PARAGRAPH_ALIGNMENT.CENTER
footer_run = footer_p.add_run(
"Généré par Library RAG - Recherche Philosophique"
)
footer_run.font.size = Pt(9)
footer_run.font.color.rgb = RGBColor(150, 150, 150)
footer_run.italic = True
# Generate filename with timestamp
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
filename = f"chat_export_{timestamp}.docx"
filepath = output_dir / filename
# Save document (create directory if needed)
output_dir.mkdir(parents=True, exist_ok=True)
doc.save(str(filepath))
return filepath