Responses API: is chaining responses possible?

[pablospe]

Is it possible to Chaining responses together with the current interface introduce for Responses API in this PR: #1520?

Example from here: https://learn.microsoft.com/en-us/azure/ai-foundry/openai/how-to/responses?tabs=python-secure#chaining-responses-together

You can chain responses together by passing the response.id from the previous response to the previous_response_id parameter.

from openai import AzureOpenAI
from azure.identity import DefaultAzureCredential, get_bearer_token_provider

token_provider = get_bearer_token_provider(
    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
)

client = AzureOpenAI(  
  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
  azure_ad_token_provider=token_provider,
  api_version="preview"
)

response = client.responses.create(
    model="gpt-4o",  # replace with your model deployment name
    input="Define and explain the concept of catastrophic forgetting?"
)

second_response = client.responses.create(
    model="gpt-4o",  # replace with your model deployment name
    previous_response_id=response.id,
    input=[{"role": "user", "content": "Explain this at a level that could be understood by a college freshman"}]
)
print(second_response.model_dump_json(indent=2))

Note from the output that even though we never shared the first input question with the second_response API call, by passing the previous_response_id the model has full context of previous question and response to answer the new question.

Output:

{
  "id": "resp_67cbc9705fc08190bbe455c5ba3d6daf",
  "created_at": 1741408624.0,
  "error": null,
  "incomplete_details": null,
  "instructions": null,
  "metadata": {},
  "model": "gpt-4o-2024-08-06",
  "object": "response",
  "output": [
    {
      "id": "msg_67cbc970fd0881908353a4298996b3f6",
      "content": [
        {
          "annotations": [],
          "text": "Sure! Imagine you are studying for exams in different subjects like math, history, and biology. You spend a lot of time studying math first and get really good at it. But then, you switch to studying history. If you spend all your time and focus on history, you might forget some of the math concepts you learned earlier because your brain fills up with all the new history facts. \n\nIn the world of artificial intelligence (AI) and machine learning, a similar thing can happen with computers. We use special programs called neural networks to help computers learn things, sort of like how our brain works. But when a neural network learns a new task, it can forget what it learned before. This is what we call \"catastrophic forgetting.\"\n\nSo, if a neural network learned how to recognize cats in pictures, and then you teach it how to recognize dogs, it might get really good at recognizing dogs but suddenly become worse at recognizing cats. This happens because the process of learning new information can overwrite or mess with the old information in its \"memory.\"\n\nScientists and engineers are working on ways to help computers remember everything they learn, even as they keep learning new things, just like students have to remember math, history, and biology all at the same time for their exams. They use different techniques to make sure the neural network doesn’t forget the important stuff it learned before, even when it gets new information.",
          "type": "output_text"
        }
      ],
      "role": "assistant",
      "status": null,
      "type": "message"
    }
  ],
  "parallel_tool_calls": null,
  "temperature": 1.0,
  "tool_choice": null,
  "tools": [],
  "top_p": 1.0,
  "max_output_tokens": null,
  "previous_response_id": "resp_67cbc96babbc8190b0f69aedc655f173",
  "reasoning": null,
  "status": "completed",
  "text": null,
  "truncation": null,
  "usage": {
    "input_tokens": 405,
    "output_tokens": 285,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 690
  },
  "user": null,
  "reasoning_effort": null
}

@jxnl @ivanleomk I'm not sure if this is currently possible with the existing interface, which unfortunately defeats the purpose of Responsee. Otherwise, if it is possible, please let me know and I will add it to the documentation.