# Predibase

> **Class** in `langchain_community`

📖 [View in docs](https://reference.langchain.com/python/langchain-community/llms/predibase/Predibase)

Use your Predibase models with Langchain.

To use, you should have the ``predibase`` python package installed,
and have your Predibase API key.

The `model` parameter is the Predibase "serverless" base_model ID
(see https://docs.predibase.com/user-guide/inference/models for the catalog).

An optional `adapter_id` parameter is the Predibase ID or HuggingFace ID of a
fine-tuned LLM adapter, whose base model is the `model` parameter; the
fine-tuned adapter must be compatible with its base model;
otherwise, an error is raised.  If the fine-tuned adapter is hosted at Predibase,
then `adapter_version` in the adapter repository must be specified.

An optional `predibase_sdk_version` parameter defaults to latest SDK version.

## Signature

```python
Predibase()
```

## Extends

- `LLM`

## Properties

- `model`
- `predibase_api_key`
- `predibase_sdk_version`
- `adapter_id`
- `adapter_version`
- `model_kwargs`
- `default_options_for_generation`

---

[View source on GitHub](https://github.com/langchain-ai/langchain-community/blob/a6a6079511ac8a5c1293337f88096b8641562e77/libs/community/langchain_community/llms/predibase.py#L9)