IVYXSTUDIO · IVY NODE

OpenAI Client

ivy.node.open-ai-client · v0.0.0

ivyx✓

Generates text responses using OpenAI's chat completion API. Supports various models including GPT-4, GPT-4o, and o1 series. This node requires an OpenAI API key and accepts both a prompt object (from prompt-generator) and direct system/user messages. Use this for high-quality text generation, summarization, or conversational AI tasks. Note: This is a high-risk node requiring step-by-step approval due to API costs.

#OpenAI#API#Chat Completion

Inputs

Field	Type	Description
modelrequired	string	The OpenAI model to use (e.g., "gpt-4o-mini").
api_keyrequired	string	The API key for authenticating with OpenAI.
promptrequired	string	The prompt content. (Node reference)
system_messagerequired	string	The system's initial message for context.
user_contentrequired	string	The user's input content.
features	object	Features
labels	object	Labels

Outputs

Field	Type	Description
openai_resultrequired	string	Not declared
features	object	Features
labels	object	Labels

Source

python

# Input preparation
inp = __ivy_ctx__["nodes"][__ivy_node_id__]["input"]
model = inp["model"]
api_key = inp["api_key"]
prompt = inp["prompt"]
system_message = inp["system_message"]
user_content = inp["user_content"]

# Compute
from openai import OpenAI

class OpenAIClient:
    """
    A class to interact with OpenAI's API for generating chat completions.
    """

    def __init__(self, api_key: str):
        """
        Initialize the OpenAIClient with the provided API key.

        :param api_key: The API key for authenticating with OpenAI.
        """
        self.api_key=api_key
        self.client=OpenAI(api_key=api_key)

    def generate_response(self, model: str, system_message: str, user_content: str) -> str:
        """
        Generate a chat completion response using the specified model and messages.

        :param model: The OpenAI model to use (e.g., "gpt-4o-mini").
        :param system_message: The system's initial message for context.
        :param user_content: The user's input content.
        :return: The response content generated by OpenAI.
        """
        response=self.client.chat.completions.create(
            model=model,
            messages=[
                {"role": "system", "content": system_message},
                {"role": "user", "content": user_content},
            ]
        )
        return response.choices[0].message.content

openai_client = OpenAIClient(api_key=api_key)

openai_result = openai_client.generate_response(
    model=model,
    system_message=system_message,
    user_content=user_content
)

# Output collection (runner reads __ivy_ctx__)
out = __ivy_ctx__["nodes"][__ivy_node_id__]["output"]
out["openai_result"] = openai_result

Tests

Requires: python:3.11

basic-generation
Generate response with valid inputs (should succeed).
openaillmgenerationbasic
error-invalid-api-key
Invalid API key should handle error gracefully.
error-handlingauthentication