How to build a chat with the Responses API

Get API authentication credentials as described in Authentication with the Yandex Cloud AI Studio API.

1. Create a file named index.py and add the following code to it:

   import openai
   
   YANDEX_CLOUD_MODEL = "yandexgpt-lite"
   
   client = openai.OpenAI(
       api_key=YANDEX_CLOUD_API_KEY,
       base_url="https://rest-assistant.api.cloud.yandex.net/v1",
       project=YANDEX_CLOUD_FOLDER
   )
   
   previous_id = None # Saving the last response ID
   
   print("💬 Chat with GPT (enter 'exit' to exit)\n")
   
   while True:
       user_input = input("You: ")
       if user_input.lower() in ("exit", "quit"):
           print("Chat session ended.")
           break
   
       response = client.responses.create(
           model=f"gpt://{YANDEX_CLOUD_FOLDER}/{YANDEX_CLOUD_MODEL}",
           input=[{"role": "user", "content": user_input}],
           previous_response_id=previous_id  # Providing context, if any
       )
   
       # Saving the ID for the next step
       previous_id = response.id
   
       # Printing the agent's response
       print("Agent:", response.output_text)
   

2. Save authentication data to environment variables:

   export YANDEX_CLOUD_FOLDER=<folder_ID>
   export YANDEX_CLOUD_API_KEY=<API_key>
   

3. Run the file you created:

   python index.py
   

   Response example:

   💬 Chat with GPT (enter 'exit' to exit)
   
   You: Hi!
   Agent: Hi there! How can I help you?
   You: What exactly can you do?
   Agent: I can answer questions, help solve various problems, and provide information on various topics. For example, I can tell you about the weather, help with translating a text, suggest ideas, or just keep the conversation going. What are you interested in?
   You: Tell me a joke
   Agent: Why do programmers always have a cup of coffee? Because when they are working on a hard problem, they need to overclock their central processing unit... and the coffee helps them do it!
   You: Exit
   Chat session ended.