# `LLMDB.Sources.OpenAI`
[🔗](https://github.com/agentjido/llm_db/blob/main/lib/llm_db/sources/openai.ex#L1)

Remote source for OpenAI models (https://api.openai.com/v1/models).

- `pull/1` fetches data from OpenAI API and caches locally
- `load/1` reads from cached file (no network call)

## Options

- `:url` - API endpoint (default: "https://api.openai.com/v1/models")
- `:api_key` - OpenAI API key (required, or set `OPENAI_API_KEY` env var)
- `:organization` - Optional OpenAI organization ID
- `:project` - Optional OpenAI project ID
- `:req_opts` - Additional Req options for testing

## Configuration

Cache directory can be configured in application config:

    config :llm_db,
      openai_cache_dir: "priv/llm_db/remote"

Default: `"priv/llm_db/remote"`

## Usage

    # Pull remote data and cache (requires API key)
    mix llm_db.pull --source openai

    # Load from cache
    {:ok, data} = OpenAI.load(%{})

# `transform`

Transforms OpenAI API response to canonical Zoi format.

## Input Format (OpenAI)

```json
{
  "object": "list",
  "data": [
    {
      "id": "gpt-4",
      "object": "model",
      "created": 1686935002,
      "owned_by": "openai"
    }
  ]
}
```

## Output Format (Canonical Zoi)

```elixir
%{
  "openai" => %{
    id: :openai,
    name: "OpenAI",
    models: [
      %{
        id: "gpt-4",
        provider: :openai,
        extra: %{
          created: 1686935002,
          owned_by: "openai"
        }
      }
    ]
  }
}
```

---

*Consult [api-reference.md](api-reference.md) for complete listing*