Custom Model Name for Open AI APIs

[mohammadaghanoori]

How can I use my own model name when using the OpenAPI component in Langflow? I want to use my custom model with an API and need to ensure it is correctly recognized within Langflow.

[dosubot[bot]]

@mohammadaghanoori Hello there! I'm here to assist you with bugs, questions, and contributions while you wait for a human maintainer.

To use your own model name with the OpenAPI component in Langflow, make sure your model object has one of the following attributes: model_name, model, model_id, or deployment_name. The get_model_name function in Langflow will check these attributes in order and use the first one it finds. If none of these attributes are present, it will default to using the class name or a provided display name. Here's the relevant code snippet:

def get_model_name(llm, display_name: str | None = "Custom"):
    attributes_to_check = ["model_name", "model", "model_id", "deployment_name"]

    # Use a generator expression with next() to find the first matching attribute
    model_name = next((getattr(llm, attr) for attr in attributes_to_check if hasattr(llm, attr)), None)

    # If no matching attribute is found, return the class name as a fallback
    return model_name if model_name is not None else display_name

Ensure your model object has one of these attributes set to your desired model name ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[mohammadaghanoori]

@dosu I Build my own model and deploy it using an openAi api. i want to use my own base api( which we have this option) and also my own model name
but when i scroll down I just see some openai popular models

[dosubot[bot]]

To use your own base API and custom model name with the OpenAI API in Langflow, you can configure the OpenAIEmbeddingsComponent with your custom settings. Here's how you can do it:

# Set your custom API base URL
custom_api_base = "https://your-custom-api-base-url.com"

# Set your custom model name
custom_model_name = "your-custom-model-name"

# Example of how to configure the OpenAIEmbeddingsComponent
openai_embeddings_component = OpenAIEmbeddingsComponent(
    openai_api_base=custom_api_base,
    model=custom_model_name,
    openai_api_key="your-openai-api-key"
)

This setup allows you to specify a custom API base and model name, even if only popular OpenAI models are visible by default ^[1].

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}