Spaces:
Sleeping
Sleeping
| import os | |
| import gradio as gr | |
| from openai import OpenAI | |
| if not (key := os.getenv("NVIDIA_API_KEY")): | |
| raise ValueError("NVIDIA_API_KEY не найден") | |
| client = OpenAI(base_url="https://integrate.api.nvidia.com/v1", api_key=key) | |
| def respond(message, history): | |
| # В Gradio 4.x история уже в формате OpenAI (список словарей) | |
| messages = history + [{"role": "user", "content": message}] | |
| try: | |
| stream = client.chat.completions.create( | |
| model="stepfun-ai/step-3.5-flash", | |
| messages=messages, | |
| temperature=0.9, | |
| max_tokens=16096, | |
| stream=True | |
| ) | |
| response = "" | |
| for chunk in stream: | |
| if chunk.choices and (text := chunk.choices[0].delta.content): | |
| response += text | |
| yield response | |
| except Exception as e: | |
| yield f"Ошибка: {e}" | |
| if __name__ == "__main__": | |
| gr.ChatInterface(respond, title="Step 3.5 Flash").launch() |