OpenAI

The OpenAI SDK covers GPT-4, GPT-4o, and the wider ecosystem of OpenAI-compatible endpoints. agentfootprint's openai() factory wraps it as an LLMProvider — same shape as anthropic() and mock().

Install

npm install openai

Peer dep, lazy-required, optional in peerDependenciesMeta. Friendly install hint at first call if missing.

Use

openai() is a vendor-SDK provider, so it lives at the agentfootprint/llm-providers subpath (this keeps the lazy openai peer-dep require out of the main barrel). Agent comes from the main barrel as usual:

import { Agent } from 'agentfootprint';
import { openai } from 'agentfootprint/llm-providers';

const provider = openai({
  apiKey: process.env.OPENAI_API_KEY!,
});

const agent = Agent.create({
  provider,
  model: 'gpt-4o',
}).build();

OpenAI-compatible endpoints (Ollama, Together, Groq, vLLM, LM Studio)

The baseURL option points the SDK at any OpenAI-compatible endpoint. No separate adapter needed:

const provider = openai({
  apiKey: 'not-needed-for-local',
  baseURL: 'http://localhost:11434/v1',  // Ollama
});

// Or:
const groq = openai({
  apiKey: process.env.GROQ_API_KEY!,
  baseURL: 'https://api.groq.com/openai/v1',
});

For Ollama specifically, the convenience factory (also from agentfootprint/llm-providers). It defaults baseURL to http://localhost:11434/v1 and names the provider ollama; set the model via defaultModel (or pass a custom host):

import { ollama } from 'agentfootprint/llm-providers';

const provider = ollama({ defaultModel: 'llama3.1' });

Tools (function calling)

OpenAI's Chat Completions API has native function calling. The provider translates Tool[] into the API's tools format and round-trips assistant tool_calls.

Streaming

provider.stream(req) uses the SDK's native SSE streaming; tokens land as they arrive. Final chunk carries the full LLMResponse.

Browser variant

BrowserOpenAIProvider — fetch-based, zero peer deps. CORS depends on the endpoint; OpenAI requires the user-supplied key in the Authorization header, which the consumer must set explicitly.

Limitations

• Multi-modal not exposed yet (LLMMessage.content is string).
• responseFormat (JSON-mode) not exposed yet — pass schema instructions via systemPrompt.

Next steps

• Resilience — wrap with withRetry / withFallback
• Streaming — token-by-token UI rendering
• Ollama — local models via OpenAI-compatible endpoint