from flask import Flask, render_template, request, jsonify, Response, stream_with_context from google import genai from google.genai import types import os from PIL import Image import io import base64 import json import re app = Flask(__name__) GOOGLE_API_KEY = os.environ.get("GEMINI_API_KEY") client = genai.Client( api_key=GOOGLE_API_KEY, ) @app.route('/') def index(): return render_template('index.html') @app.route('/free') def indexx(): return render_template('maj.html') def process_markdown_and_code(text): """Traite le texte pour identifier et formater le code et le markdown""" # Convertit le texte en HTML formaté # Cette fonction pourrait être étendue pour utiliser une bibliothèque de markdown return text def format_code_execution_result(response_parts): """Formate les résultats d'exécution de code pour l'affichage HTML""" result = [] for part in response_parts: # Traitement du texte (équivalent à display(Markdown(part.text))) if hasattr(part, 'text') and part.text is not None: result.append({ 'type': 'markdown', 'content': part.text }) # Traitement du code exécutable if hasattr(part, 'executable_code') and part.executable_code is not None: result.append({ 'type': 'code', 'content': part.executable_code.code }) # Traitement des résultats d'exécution if hasattr(part, 'code_execution_result') and part.code_execution_result is not None: result.append({ 'type': 'execution_result', 'content': part.code_execution_result.output }) # Traitement des images (équivalent à display(Image(data=part.inline_data.data))) if hasattr(part, 'inline_data') and part.inline_data is not None: # Encodage de l'image en base64 pour l'affichage HTML img_data = base64.b64encode(part.inline_data.data).decode('utf-8') result.append({ 'type': 'image', 'content': img_data, 'format': 'png' # Supposé comme png par défaut }) return result @app.route('/solve', methods=['POST']) def solve(): try: image_data = request.files['image'].read() img = Image.open(io.BytesIO(image_data)) buffered = io.BytesIO() img.save(buffered, format="PNG") img_str = base64.b64encode(buffered.getvalue()).decode() def generate(): mode = 'starting' try: response = client.models.generate_content_stream( model="gemini-2.5-pro-exp-03-25", contents=[ {'inline_data': {'mime_type': 'image/png', 'data': img_str}}, """Résous ça en français with rendering latex""" ], config=types.GenerateContentConfig( thinking_config=types.ThinkingConfig( thinking_budget=8000 ), # Ajouter l'outil d'exécution de code tools=[types.Tool( code_execution=types.ToolCodeExecution )] ) ) for chunk in response: for part in chunk.candidates[0].content.parts: if hasattr(part, 'thought') and part.thought: if mode != "thinking": yield f'data: {json.dumps({"mode": "thinking"})}\n\n' mode = "thinking" else: if mode != "answering": yield f'data: {json.dumps({"mode": "answering"})}\n\n' mode = "answering" # Gestion des différents types de contenu if hasattr(part, 'text') and part.text is not None: yield f'data: {json.dumps({"content": part.text, "type": "text"})}\n\n' if hasattr(part, 'executable_code') and part.executable_code is not None: yield f'data: {json.dumps({"content": part.executable_code.code, "type": "code"})}\n\n' if hasattr(part, 'code_execution_result') and part.code_execution_result is not None: yield f'data: {json.dumps({"content": part.code_execution_result.output, "type": "result"})}\n\n' if hasattr(part, 'inline_data') and part.inline_data is not None: img_data = base64.b64encode(part.inline_data.data).decode('utf-8') yield f'data: {json.dumps({"content": img_data, "type": "image"})}\n\n' except Exception as e: print(f"Error during generation: {e}") yield f'data: {json.dumps({"error": str(e)})}\n\n' return Response( stream_with_context(generate()), mimetype='text/event-stream', headers={ 'Cache-Control': 'no-cache', 'X-Accel-Buffering': 'no' } ) except Exception as e: return jsonify({'error': str(e)}), 500 @app.route('/solved', methods=['POST']) def solved(): try: image_data = request.files['image'].read() img = Image.open(io.BytesIO(image_data)) buffered = io.BytesIO() img.save(buffered, format="PNG") img_str = base64.b64encode(buffered.getvalue()).decode() def generate(): mode = 'starting' try: response = client.models.generate_content_stream( model="gemini-2.5-flash-preview-04-17", contents=[ {'inline_data': {'mime_type': 'image/png', 'data': img_str}}, """Résous ça en français with rendering latex. utilise python pour les calculs""" ], config=types.GenerateContentConfig( # Ajouter l'outil d'exécution de code tools=[types.Tool( code_execution=types.ToolCodeExecution )] ) ) for chunk in response: for part in chunk.candidates[0].content.parts: if hasattr(part, 'thought') and part.thought: if mode != "thinking": yield f'data: {json.dumps({"mode": "thinking"})}\n\n' mode = "thinking" else: if mode != "answering": yield f'data: {json.dumps({"mode": "answering"})}\n\n' mode = "answering" # Gestion des différents types de contenu if hasattr(part, 'text') and part.text is not None: yield f'data: {json.dumps({"content": part.text, "type": "text"})}\n\n' if hasattr(part, 'executable_code') and part.executable_code is not None: yield f'data: {json.dumps({"content": part.executable_code.code, "type": "code"})}\n\n' if hasattr(part, 'code_execution_result') and part.code_execution_result is not None: yield f'data: {json.dumps({"content": part.code_execution_result.output, "type": "result"})}\n\n' if hasattr(part, 'inline_data') and part.inline_data is not None: img_data = base64.b64encode(part.inline_data.data).decode('utf-8') yield f'data: {json.dumps({"content": img_data, "type": "image"})}\n\n' except Exception as e: print(f"Error during generation: {e}") yield f'data: {json.dumps({"error": str(e)})}\n\n' return Response( stream_with_context(generate()), mimetype='text/event-stream', headers={ 'Cache-Control': 'no-cache', 'X-Accel-Buffering': 'no' } ) except Exception as e: return jsonify({'error': str(e)}), 500 if __name__ == '__main__': app.run(debug=True)