A prompt template refers to a reproducible way to generate a prompt. It contains a text string ("the template"), that can take in a set of parameters from the end user and generate a prompt.
You can create simple hardcoded prompts using the `PromptTemplate` class. Prompt templates can take any number of input variables, and can be formatted to generate a prompt.
```python
from langchain import PromptTemplate
# An example prompt with no input variables
no_input_prompt = PromptTemplate(input_variables=[], template="Tell me a joke.")
no_input_prompt.format()
# -> "Tell me a joke."
# An example prompt with one input variable
one_input_prompt = PromptTemplate(input_variables=["adjective"], template="Tell me a {adjective} joke.")
one_input_prompt.format(adjective="funny")
# -> "Tell me a funny joke."
# An example prompt with multiple input variables
multiple_input_prompt = PromptTemplate(
input_variables=["adjective", "content"],
template="Tell me a {adjective} joke about {content}."
If you do not wish to specify `input_variables` manually, you can also create a `PromptTemplate` using `from_template` class method. `langchain` will automatically infer the `input_variables` based on the `template` passed.
You can create custom prompt templates that format the prompt in any way you want. For more information, see [Custom Prompt Templates](examples/custom_prompt_template.ipynb).
By default, `PromptTemplate` will treat the provided template as a Python f-string. You can specify other template format through `template_format` argument:
Currently, `PromptTemplate` only supports `jinja2` and `f-string` templating format. If there is any other templating format that you would like to use, feel free to open an issue in the [Github](https://github.com/hwchase17/langchain/issues) page.
By default, `PromptTemplate` will validate the `template` string by checking whether the `input_variables` match the variables defined in `template`. You can disable this behavior by setting `validate_template` to `False`
```python
template = "I am learning langchain because {reason}."
You can save your `PromptTemplate` into a file in your local filesystem. `langchain` will automatically infer the file format through the file extension name. Currently, `langchain` supports saving template to YAML and JSON file.
```python
prompt_template.save("awesome_prompt.json") # Save to JSON file
`langchain` also supports loading prompt template from LangChainHub, which contains a collection of useful prompts you can use in your project. You can read more about LangChainHub and the prompts available with it [here](https://github.com/hwchase17/langchain-hub).
Few shot examples are a set of examples that can be used to help the language model generate a better response.
To generate a prompt with few shot examples, you can use the `FewShotPromptTemplate`. This class takes in a `PromptTemplate` and a list of few shot examples. It then formats the prompt template with the few shot examples.
In this example, we'll create a prompt to generate word antonyms.
```python
from langchain import PromptTemplate, FewShotPromptTemplate
# First, create the list of few shot examples.
examples = [
{"word": "happy", "antonym": "sad"},
{"word": "tall", "antonym": "short"},
]
# Next, we specify the template to format the examples we have provided.
# We use the `PromptTemplate` class for this.
example_formatter_template = """
Word: {word}
Antonym: {antonym}\n
"""
example_prompt = PromptTemplate(
input_variables=["word", "antonym"],
template=example_formatter_template,
)
# Finally, we create the `FewShotPromptTemplate` object.
few_shot_prompt = FewShotPromptTemplate(
# These are the examples we want to insert into the prompt.
examples=examples,
# This is how we want to format the examples when we insert them into the prompt.
example_prompt=example_prompt,
# The prefix is some text that goes before the examples in the prompt.
# Usually, this consists of intructions.
prefix="Give the antonym of every input",
# The suffix is some text that goes after the examples in the prompt.
# Usually, this is where the user input will go
suffix="Word: {input}\nAntonym:",
# The input variables are the variables that the overall prompt expects.
input_variables=["input"],
# The example_separator is the string we will use to join the prefix, examples, and suffix together with.
example_separator="\n\n",
)
# We can now generate a prompt using the `format` method.
print(few_shot_prompt.format(input="big"))
# -> Give the antonym of every input
# ->
# -> Word: happy
# -> Antonym: sad
# ->
# -> Word: tall
# -> Antonym: short
# ->
# -> Word: big
# -> Antonym:
```
## Select examples for a prompt template
If you have a large number of examples, you can use the `ExampleSelector` to select a subset of examples that will be most informative for the Language Model. This will help you generate a prompt that is more likely to generate a good response.
Below, we'll use the `LengthBasedExampleSelector`, which selects examples based on the length of the input. This is useful when you are worried about constructing a prompt that will go over the length of the context window. For longer inputs, it will select fewer examples to include, while for shorter inputs it will select more.
We'll continue with the example from the previous section, but this time we'll use the `LengthBasedExampleSelector` to select the examples.
```python
from langchain.prompts.example_selector import LengthBasedExampleSelector
# These are a lot of examples of a pretend task of creating antonyms.
You can create custom example selectors that select examples based on any criteria you want. For more details on how to do this, see [Creating a custom example selector](../example_selectors/examples/custom_example_selector.md).
