OpenAI LLM

The OpenAI LLM provider enables your agent to use OpenAI's language models (like GPT-4o) for text-based conversations and processing.

Installation

Install the OpenAI-enabled VideoSDK Agents package:

pip install "videosdk-plugins-openai"

Importing

from videosdk.plugins.openai import OpenAILLM

Example Usage

from videosdk.plugins.openai import OpenAILLM
from videosdk.agents import CascadingPipeline

# Initialize the OpenAI LLM model
llm = OpenAILLM(
    model="gpt-4o",
    # When OPENAI_API_KEY is set in .env - DON'T pass api_key parameter
    api_key="your-openai-api-key",
    temperature=0.7,
    tool_choice="auto",
    max_completion_tokens=1000
)

#  Add llm to cascading pipeline
pipeline = CascadingPipeline(llm=llm)

note

When using .env file for credentials, don't pass them as arguments to model instances or context objects. The SDK automatically reads environment variables, so omit api_key, videosdk_auth, and other credential parameters from your code.

Configuration Options

• model: The OpenAI model to use (e.g., "gpt-4o", "gpt-4o-mini", "gpt-3.5-turbo")
• api_key: Your OpenAI API key (can also be set via environment variable)
• base_url: Custom base URL for OpenAI API (optional)
• temperature: (float) Sampling temperature for response randomness (0.0 to 2.0, default: 0.7)
• tool_choice: Tool selection mode (e.g., "auto", "none", or specific tool)
• max_completion_tokens: (int) Maximum number of tokens in the completion response