# load_qa_chain

> **Function** in `langchain_classic`

📖 [View in docs](https://reference.langchain.com/python/langchain-classic/chains/question_answering/chain/load_qa_chain)

Load question answering chain.

## Signature

```python
load_qa_chain(
    llm: BaseLanguageModel,
    chain_type: str = 'stuff',
    verbose: bool | None = None,
    callback_manager: BaseCallbackManager | None = None,
    **kwargs: Any = {},
) -> BaseCombineDocumentsChain
```

## Parameters

| Name | Type | Required | Description |
|------|------|----------|-------------|
| `llm` | `BaseLanguageModel` | Yes | Language Model to use in the chain. |
| `chain_type` | `str` | No | Type of document combining chain to use. Should be one of "stuff", "map_reduce", "map_rerank", and "refine". (default: `'stuff'`) |
| `verbose` | `bool \| None` | No | Whether chains should be run in verbose mode or not. Note that this applies to all chains that make up the final chain. (default: `None`) |
| `callback_manager` | `BaseCallbackManager \| None` | No | Callback manager to use for the chain. (default: `None`) |
| `**kwargs` | `Any` | No | Additional keyword arguments. (default: `{}`) |

## Returns

`BaseCombineDocumentsChain`

A chain to use for question answering.

## ⚠️ Deprecated

Deprecated since version 0.2.13.

---

[View source on GitHub](https://github.com/langchain-ai/langchain/blob/311675a517f51ec6c77454124293c58df517e952/libs/langchain/langchain_classic/chains/question_answering/chain.py#L232)