question-answer/README.md

# question-answer

<br />



## Desription

Prompt to answer a question.


<br />



## Code Example

### Example


```python

from towhee import ops, pipe
import requests

towhee_docs = requests.get('https://raw.githubusercontent.com/towhee-io/towhee/main/README.md').content


p = (
    pipe.input('question', 'docs', 'history')
    .map('docs', 'docs', lambda x: x[:2000])
    .map(('question', 'docs', 'history'), 'prompt', ops.prompt.question_answer())
    .map('prompt', 'answer', ops.LLM.OpenAI())
    .output('answer')
)

an1 = p('Tell me something about Towhee', towhee_docs, []).get()[0]
print(an1)

an2 = p('How to use it', towhee_docs, [('Tell me something about Towhee', an1)]).get()[0]
print(an2)

```

## Factory Constructor

Create the operator via the following factory method:

***ops.prompt.question_answer()***

Args:

Args:

**temp: str**

    User-defined prompt, must contain {context} and {question}"

**llm_name: str**

    Pre-defined prompt, currently supports openai and dolly, openai prompt is used by default."

<br />


**Returns:** *List[Dict]*