2. OpenAI Responses Target - PyRIT Documentation

In this demo, we show an example of the OpenAIResponseTarget. Responses is a newer protocol than chat completions and provides additional functionality with a somewhat modified API. The allowed input types include text, image, web search, file search, functions, reasoning, and computer use.

OpenAI Configuration¶

Like most targets, all OpenAITargets need an endpoint and often also needs a model and a key. These can be passed into the constructor or configured with environment variables (or in .env).

endpoint: The API endpoint (OPENAI_RESPONSES_ENDPOINT environment variable). For OpenAI, these are just “https://api.openai.com/v1/responses”.
auth: The API key for authentication (OPENAI_RESPONSES_KEY environment variable).
model_name: The model to use (OPENAI_RESPONSES_MODEL environment variable). For OpenAI, these are any available model name and are listed here: “https://platform.openai.com/docs/models”.

import os

from pyrit.auth import get_azure_openai_auth
from pyrit.executor.attack import ConsoleAttackResultPrinter, PromptSendingAttack
from pyrit.prompt_target import OpenAIResponseTarget
from pyrit.setup import IN_MEMORY, initialize_pyrit_async

await initialize_pyrit_async(memory_db_type=IN_MEMORY)  # type: ignore

# For Azure OpenAI with Entra ID authentication (no API key needed, run `az login` first):
endpoint = os.environ["OPENAI_RESPONSES_ENDPOINT"]
target = OpenAIResponseTarget(
    endpoint=endpoint,
    api_key=get_azure_openai_auth(endpoint),
)

attack = PromptSendingAttack(objective_target=target)

result = await attack.execute_async(objective="Tell me a joke")  # type: ignore
await ConsoleAttackResultPrinter().print_conversation_async(result=result)  # type: ignore

Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']
Loaded environment file: ./.pyrit/.env
Loaded environment file: ./.pyrit/.env.local

────────────────────────────────────────────────────────────────────────────────────────────────────
🔹 Turn 1 - USER
────────────────────────────────────────────────────────────────────────────────────────────────────
  Tell me a joke

────────────────────────────────────────────────────────────────────────────────────────────────────
🔸 ASSISTANT
────────────────────────────────────────────────────────────────────────────────────────────────────
  Why don’t skeletons fight each other?
  
    They don’t have the guts!

────────────────────────────────────────────────────────────────────────────────────────────────────

Reasoning Configuration¶

Reasoning models (e.g., o1, o3, o4-mini, GPT-5) support a reasoning parameter that controls how much internal reasoning the model performs before responding. You can configure this with two parameters:

reasoning_effort: Controls the depth of reasoning. Accepts "minimal", "low", "medium", or "high". Lower effort favors speed and lower cost; higher effort favors thoroughness. The default (when not set) is typically "medium".
reasoning_summary: Controls whether a summary of the model’s internal reasoning is included in the response. Accepts "auto", "concise", or "detailed". By default, no summary is included.

For more information, see the OpenAI reasoning guide.

import os

from pyrit.auth import get_azure_openai_auth
from pyrit.executor.attack import ConsoleAttackResultPrinter, PromptSendingAttack
from pyrit.prompt_target import OpenAIResponseTarget
from pyrit.setup import IN_MEMORY, initialize_pyrit_async

await initialize_pyrit_async(memory_db_type=IN_MEMORY)  # type: ignore

endpoint = os.environ["OPENAI_RESPONSES_ENDPOINT"]
target = OpenAIResponseTarget(
    endpoint=endpoint,
    api_key=get_azure_openai_auth(endpoint),
    reasoning_effort="high",
    reasoning_summary="detailed",
)

attack = PromptSendingAttack(objective_target=target)
result = await attack.execute_async(objective="What are the most dangerous items in a household?")  # type: ignore
await ConsoleAttackResultPrinter().print_conversation_async(result=result, include_reasoning_trace=True)  # type: ignore

Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']
Loaded environment file: ./.pyrit/.env
Loaded environment file: ./.pyrit/.env.local

────────────────────────────────────────────────────────────────────────────────────────────────────
🔹 Turn 1 - USER
────────────────────────────────────────────────────────────────────────────────────────────────────
  What are the most dangerous items in a household?

────────────────────────────────────────────────────────────────────────────────────────────────────
🔸 ASSISTANT
────────────────────────────────────────────────────────────────────────────────────────────────────
  💭 Reasoning Summary:
  **Listing dangerous household items**
  
    The user is asking about the most dangerous items commonly found in households. It seems they’re
      looking for a list that categorizes these hazards. I think I’ll organize it into sections:
      chemical hazards like cleaning products and pesticides; physical hazards such as power tools and
      knives; medicines including prescriptions and vitamins; small items like button batteries; and
      fire hazards like candles and matches. I also need to include disclaimers and safety tips to
      keep things safe and responsible.
    **Identifying physical hazards in households**
  
    I'm thinking about dangerous items in households, especially physical hazards. This includes
      knives, power tools, and space heaters, which can pose burn or fire risks. I should also
      consider potential fire hazards like candles and lighters, along with electrical concerns such
      as overloaded outlets and frayed wires.
  
    It’s important to emphasize safety measures too, like storing dangerous items securely, keeping
      them in original containers, and ensuring proper ventilation. I want to compile these into a
      clear list with explanations to help guide safety awareness!

  Here is a list of some of the most hazardous items commonly found in homes, grouped by hazard
      type, along with brief safety notes for each:
  
    1. Strong Cleaning Chemicals
      • Bleach, drain cleaners, toilet bowl cleaners (highly caustic; can burn skin and eyes, release
      toxic gases if mixed)
      • Ammonia-based cleaners (irritant; forms chloramine gas if mixed with bleach)
      • Oven cleaners (caustic; extreme burn risk)
  
    2. Pesticides and Insecticides
      • Ant, roach, or rodent baits (toxic if ingested or inhaled)
      • Garden sprays and granules (can contaminate soil and pets)
  
    3. Automotive and Workshop Fluids
      • Gasoline, kerosene, paint thinner, lighter fluid (highly flammable; inhalation hazard)
      • Antifreeze (ethylene glycol is sweet but extremely toxic if swallowed)
      • Motor oil and brake fluid (skin irritants; environmental pollutant)
  
    4. Medications and Supplements
      • Prescription drugs (opioids, sedatives, stimulants—overdose risk)
      • Over-the-counter pain relievers (acetaminophen, NSAIDs—liver/bleeding risk)
      • Iron pills and vitamin supplements (iron overload can be fatal in children)
  
    5. Button Batteries and Small Magnets
      • Watch, hearing-aid, remote-control batteries (if swallowed, can lodge in the esophagus and
      burn through tissue)
      • High-powered rare-earth magnets (can pinch or tear intestines if multiple are swallowed)
  
    6. Sharp Objects and Tools
      • Kitchen knives, box cutters, scissors (cuts and puncture wounds)
      • Power tools (saws, drills—lacerations, amputations if misused)
      • Broken glass, razor blades (deep cuts, infection risk)
  
    7. Fire and Burn Hazards
      • Candles, matches, lighters (open-flame fire risk)
      • Portable space heaters, irons, curling/flat irons (burns, house fires if left unattended)
      • Electrical cords and overloaded outlet strips (electrical fires, shocks)
  
    8. Household Items That Tip Over
      • Unsecured furniture (dressers, bookcases, TVs—serious crush injuries to children)
      • Appliance toppling (microwaves, fruit presses)
  
    9. Carbon Monoxide and Other Gases
      • Gas stoves, furnaces, water heaters (improperly vented appliances can produce CO)
      • Paints, varnishes, nail polish removers (organic solvents—headaches, dizziness, long-term
      organ damage)
  
    10. Common Choking Hazards
      • Small toy parts, coins, marbles, buttons (especially dangerous for toddlers)
      • Food items like whole grapes, nuts, popcorn in young children
  
    Safety Tips
    • Store all chemicals and medications in original, clearly labeled containers.
    • Keep dangerous items locked away or on high shelves, out of reach of children and pets.
    • Never mix chemical products unless the label explicitly says it’s safe.
    • Use protective gear—gloves, goggles, masks—when handling strong chemicals or power tools.
    • Install smoke and carbon monoxide detectors and test them monthly.
    • Secure heavy furniture and TVs to the wall to prevent tip-overs.
    • Dispose of expired medicines, old batteries, and unused chemicals according to local hazardous-
      waste guidelines.
    • Educate all household members—especially children—about the dangers and safe handling of these
      items.
  
    By recognizing these common hazards and adopting safe‐storage and usage practices, you can greatly
      reduce the risk of poisoning, fire, burns, choking, and other serious injuries in your home.

────────────────────────────────────────────────────────────────────────────────────────────────────

JSON Generation¶

We can use the OpenAI Responses API with a JSON schema to produce structured JSON output. In this example, we define a simple JSON schema that describes a person with name and age properties.

For more information about structured outputs with OpenAI, see the OpenAI documentation.

import json
import os

import jsonschema

from pyrit.auth import get_azure_openai_auth
from pyrit.models import Message, MessagePiece
from pyrit.prompt_target import OpenAIResponseTarget
from pyrit.setup import IN_MEMORY, initialize_pyrit_async

await initialize_pyrit_async(memory_db_type=IN_MEMORY)  # type: ignore

# Define a simple JSON schema for a person
person_schema = {
    "type": "object",
    "properties": {
        "name": {"type": "string"},
        "age": {"type": "integer", "minimum": 0, "maximum": 150},
    },
    "required": ["name", "age"],
    "additionalProperties": False,
}

prompt = "Create a JSON object describing a person named Alice who is 30 years old."
# Create the message piece and message
message_piece = MessagePiece(
    role="user",
    original_value=prompt,
    original_value_data_type="text",
    prompt_metadata={
        "response_format": "json",
        "json_schema": json.dumps(person_schema),
    },
)
message = Message(message_pieces=[message_piece])

# Create the OpenAI Responses target
endpoint = os.environ["OPENAI_RESPONSES_ENDPOINT"]
target = OpenAIResponseTarget(
    endpoint=endpoint,
    api_key=get_azure_openai_auth(endpoint),
)

# Send the prompt, requesting JSON output
response = await target.send_prompt_async(message=message)  # type: ignore

# Validate and print the response
response_json = json.loads(response[0].message_pieces[1].converted_value)
print(json.dumps(response_json, indent=2))
jsonschema.validate(instance=response_json, schema=person_schema)

Unclosed client session
client_session: <aiohttp.client.ClientSession object at 0x00000225D550B230>

Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']
Loaded environment file: ./.pyrit/.env
Loaded environment file: ./.pyrit/.env.local
{
  "name": "Alice",
  "age": 30
}

Tool Use with Custom Functions¶

In this example, we demonstrate how the OpenAI Responses API can be used to invoke a custom-defined Python function during a conversation. This is part of OpenAI’s support for “function calling”, where the model decides to call a registered function, and the application executes it and passes the result back into the conversation loop.

We define a simple tool called get_current_weather, which simulates weather information retrieval. A corresponding OpenAI tool schema describes the function name, parameters, and expected input format.

The function is registered in the custom_functions argument of OpenAIResponseTarget. The extra_body_parameters include:

tools: the full OpenAI tool schema for get_current_weather.
tool_choice: "auto": instructs the model to decide when to call the function.

The user prompt explicitly asks the model to use the get_current_weather function. Once the model responds with a function_call, PyRIT executes the function, wraps the output, and the conversation continues until a final answer is produced.

This showcases how agentic function execution works with PyRIT + OpenAI Responses API.

import os

from pyrit.auth import get_azure_openai_auth
from pyrit.models import Message, MessagePiece
from pyrit.prompt_target import OpenAIResponseTarget
from pyrit.setup import IN_MEMORY, initialize_pyrit_async

await initialize_pyrit_async(memory_db_type=IN_MEMORY)  # type: ignore


async def get_current_weather(args):
    return {
        "weather": "Sunny",
        "temp_c": 22,
        "location": args["location"],
        "unit": args["unit"],
    }


# Responses API function tool schema (flat, no nested "function" key)
function_tool = {
    "type": "function",
    "name": "get_current_weather",
    "description": "Get the current weather in a given location",
    "parameters": {
        "type": "object",
        "properties": {
            "location": {"type": "string", "description": "City and state"},
            "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
        },
        "required": ["location", "unit"],
        "additionalProperties": False,
    },
    "strict": True,
}

endpoint = os.environ["OPENAI_RESPONSES_ENDPOINT"]
# Let the model auto-select tools
target = OpenAIResponseTarget(
    endpoint=endpoint,
    api_key=get_azure_openai_auth(endpoint),
    custom_functions={"get_current_weather": get_current_weather},
    extra_body_parameters={
        "tools": [function_tool],
        "tool_choice": "auto",
    },
    httpx_client_kwargs={"timeout": 60.0},
)

# Build the user prompt
message_piece = MessagePiece(
    role="user",
    original_value="What is the weather in Boston in celsius? Use the get_current_weather function.",
    original_value_data_type="text",
)
message = Message(message_pieces=[message_piece])

response = await target.send_prompt_async(message=message)  # type: ignore

for response_msg in response:
    for idx, piece in enumerate(response_msg.message_pieces):
        print(f"{idx} | {piece.api_role}: {piece.original_value}")

Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']
Loaded environment file: ./.pyrit/.env
Loaded environment file: ./.pyrit/.env.local

Unclosed client session
client_session: <aiohttp.client.ClientSession object at 0x00000225D58C2C10>

0 | assistant: {"id":"rs_0afd72292ac98d280069dd36e1e8208190ab1a31ea799afdf2","summary":[],"type":"reasoning","content":null,"encrypted_content":null,"status":null}
1 | assistant: {"type":"function_call","call_id":"call_FRaBo4Rpp69xjg2d4AghxcCr","name":"get_current_weather","arguments":"{\"location\":\"Boston, MA\",\"unit\":\"celsius\"}"}
0 | tool: {"type":"function_call_output","call_id":"call_FRaBo4Rpp69xjg2d4AghxcCr","output":"{\"weather\":\"Sunny\",\"temp_c\":22,\"location\":\"Boston, MA\",\"unit\":\"celsius\"}"}
0 | assistant: The current weather in Boston, MA is:

- Conditions: Sunny
- Temperature: 22°C

Using the Built-in Web Search Tool¶

In this example, we use a built-in PyRIT helper function web_search_tool() to register a web search tool with OpenAI’s Responses API. This allows the model to issue web search queries during a conversation to supplement its responses with fresh information.

The tool is added to the extra_body_parameters passed into the OpenAIResponseTarget. As before, tool_choice="auto" enables the model to decide when to invoke the tool.

The user prompt asks for a recent positive news story — an open-ended question that may prompt the model to issue a web search tool call. PyRIT will automatically execute the tool and return the output to the model as part of the response.

This example demonstrates how retrieval-augmented generation (RAG) can be enabled in PyRIT through OpenAI’s Responses API and integrated tool schema.

NOTE that web search is NOT supported through an Azure OpenAI endpoint, only through the OpenAI platform endpoint (i.e. api.openai.com)

import os

from pyrit.auth import get_azure_openai_auth
from pyrit.common.tool_configs import web_search_tool
from pyrit.models import Message, MessagePiece
from pyrit.prompt_target import OpenAIResponseTarget
from pyrit.setup import IN_MEMORY, initialize_pyrit_async

await initialize_pyrit_async(memory_db_type=IN_MEMORY)  # type: ignore

# Note: web search is only supported on a limited set of models.
responses_endpoint = os.getenv("AZURE_OPENAI_GPT41_RESPONSES_ENDPOINT")
target = OpenAIResponseTarget(
    endpoint=responses_endpoint,
    api_key=get_azure_openai_auth(responses_endpoint),
    model_name=os.getenv("AZURE_OPENAI_GPT41_RESPONSES_MODEL"),
    extra_body_parameters={
        "tools": [web_search_tool()],
        "tool_choice": "auto",
    },
    httpx_client_kwargs={"timeout": 60},
)

message_piece = MessagePiece(
    role="user", original_value="Briefly, what is one positive news story from today?", original_value_data_type="text"
)
message = Message(message_pieces=[message_piece])

response = await target.send_prompt_async(message=message)  # type: ignore

for response_msg in response:
    for idx, piece in enumerate(response_msg.message_pieces):
        print(f"{idx} | {piece.api_role}: {piece.original_value}")

Found default environment files: ['./.pyrit/.env', './.pyrit/.env.local']
Loaded environment file: ./.pyrit/.env
Loaded environment file: ./.pyrit/.env.local
0 | assistant: {"type":"web_search_call","id":"ws_0147db6c4a2995450069dd36f0dc0081938bdb6e41d697464c"}
1 | assistant: One positive news story from today is that Portugal has introduced a new deposit system to tackle low recycling rates, aiming to boost recycling and reduce waste across the country. This initiative is expected to make a significant positive environmental impact by encouraging more people to recycle their bottles and cans, helping move towards a cleaner, greener future [Good News Europe](https://goodnews.eu/en/).