Scribd
Upload
3 views3 pages

DeepSeek AI Code Generator

The document outlines a Flask application that integrates with the DeepSeek API to generate and execute Python code based on user prompts. It includes functions for generating code, saving it to a file, and executing it, with an endpoint for generating and running code through multiple iterations. Additionally, there is a test endpoint to check the status of the API.

Uploaded by

lalatau75
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
3 views3 pages

DeepSeek AI Code Generator

The document outlines a Flask application that integrates with the DeepSeek API to generate and execute Python code based on user prompts. It includes functions for generating code, saving it to a file, and executing it, with an endpoint for generating and running code through multiple iterations. Additionally, there is a test endpoint to check the status of the API.

Uploaded by

lalatau75
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 3

DeepSeek AI-Powered Code Generator with API

import os
import requests
import json
import subprocess
from flask import Flask, request, jsonify

# DeepSeek API Configuration


DEEPSEEK_API_URL = "https://api.deepseek.com/v1/chat/completions"
API_KEY = "your_deepseek_api_key"

# Flask App Initialization


app = Flask(__name__)

def generate_code(prompt, model="deepseek-coder"):


"""
Uses DeepSeek API to generate Python code based on a given prompt.
"""
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {API_KEY}"
}
data = {
"model": model,
"messages": [
{"role": "system", "content": "You are an expert AI software developer."},
{"role": "user", "content": prompt}
],
"temperature": 0.7
}

response = requests.post(DEEPSEEK_API_URL, headers=headers, json=data)


response_json = response.json()
return response_json["choices"][0]["message"]["content"]

def save_code(filename, code):


"""
Saves generated code to a file.
"""
with open(filename, "w") as f:
f.write(code)
def execute_code(filename):
"""
Executes the generated code file.
"""
result = subprocess.run(["python", filename], capture_output=True, text=True)
return result.stdout, result.stderr

@app.route('/generate-code', methods=['POST'])
def generate_and_run():
"""
API Endpoint to generate and execute AI-generated code.
"""
data = request.get_json()
prompt = data.get("prompt", "Write a fully functional AI-powered microscope camera app
for skin analysis in Python.")

for i in range(5): # AI refines code over 5 iterations


print(f"Iteration {i+1}: Generating code...")
code = generate_code(prompt)
filename = f"generated_code_{i+1}.py"
save_code(filename, code)

print(f"Executing {filename}...")
output, error = execute_code(filename)

if error:
print(f"Error detected:\n{error}")
prompt += f"\nFix the following errors: {error}"
else:
print("Code executed successfully!\nOutput:", output)
return jsonify({"status": "success", "output": output, "generated_code": code})

return jsonify({"status": "error", "message": "Code generation failed after multiple


attempts."})

@app.route('/test-ai', methods=['GET'])
def test_ai():
"""
Simple API Test Endpoint.
"""
return jsonify({"status": "running", "message": "AI Code Generator API is active!"})
if __name__ == "__main__":
app.run(debug=True, host="0.0.0.0", port=5000)

You might also like