Spaces:
Runtime error
Runtime error
File size: 6,393 Bytes
58d33f0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 |
"""BasePrompt schema definition."""
from __future__ import annotations
import json
from abc import ABC, abstractmethod
from pathlib import Path
from typing import Any, Callable, Dict, List, Mapping, Optional, Union
import yaml
from pydantic import BaseModel, Extra, Field, root_validator
from langchain.formatting import formatter
from langchain.schema import BaseMessage, BaseOutputParser, HumanMessage, PromptValue
def jinja2_formatter(template: str, **kwargs: Any) -> str:
"""Format a template using jinja2."""
try:
from jinja2 import Template
except ImportError:
raise ValueError(
"jinja2 not installed, which is needed to use the jinja2_formatter. "
"Please install it with `pip install jinja2`."
)
return Template(template).render(**kwargs)
DEFAULT_FORMATTER_MAPPING: Dict[str, Callable] = {
"f-string": formatter.format,
"jinja2": jinja2_formatter,
}
def check_valid_template(
template: str, template_format: str, input_variables: List[str]
) -> None:
"""Check that template string is valid."""
if template_format not in DEFAULT_FORMATTER_MAPPING:
valid_formats = list(DEFAULT_FORMATTER_MAPPING)
raise ValueError(
f"Invalid template format. Got `{template_format}`;"
f" should be one of {valid_formats}"
)
dummy_inputs = {input_variable: "foo" for input_variable in input_variables}
try:
formatter_func = DEFAULT_FORMATTER_MAPPING[template_format]
formatter_func(template, **dummy_inputs)
except KeyError as e:
raise ValueError(
"Invalid prompt schema; check for mismatched or missing input parameters. "
+ str(e)
)
class StringPromptValue(PromptValue):
text: str
def to_string(self) -> str:
"""Return prompt as string."""
return self.text
def to_messages(self) -> List[BaseMessage]:
"""Return prompt as messages."""
return [HumanMessage(content=self.text)]
class BasePromptTemplate(BaseModel, ABC):
"""Base class for all prompt templates, returning a prompt."""
input_variables: List[str]
"""A list of the names of the variables the prompt template expects."""
output_parser: Optional[BaseOutputParser] = None
"""How to parse the output of calling an LLM on this formatted prompt."""
partial_variables: Mapping[str, Union[str, Callable[[], str]]] = Field(
default_factory=dict
)
class Config:
"""Configuration for this pydantic object."""
extra = Extra.forbid
arbitrary_types_allowed = True
@abstractmethod
def format_prompt(self, **kwargs: Any) -> PromptValue:
"""Create Chat Messages."""
@root_validator()
def validate_variable_names(cls, values: Dict) -> Dict:
"""Validate variable names do not include restricted names."""
if "stop" in values["input_variables"]:
raise ValueError(
"Cannot have an input variable named 'stop', as it is used internally,"
" please rename."
)
if "stop" in values["partial_variables"]:
raise ValueError(
"Cannot have an partial variable named 'stop', as it is used "
"internally, please rename."
)
overall = set(values["input_variables"]).intersection(
values["partial_variables"]
)
if overall:
raise ValueError(
f"Found overlapping input and partial variables: {overall}"
)
return values
def partial(self, **kwargs: Union[str, Callable[[], str]]) -> BasePromptTemplate:
"""Return a partial of the prompt template."""
prompt_dict = self.__dict__.copy()
prompt_dict["input_variables"] = list(
set(self.input_variables).difference(kwargs)
)
prompt_dict["partial_variables"] = {**self.partial_variables, **kwargs}
return type(self)(**prompt_dict)
def _merge_partial_and_user_variables(self, **kwargs: Any) -> Dict[str, Any]:
# Get partial params:
partial_kwargs = {
k: v if isinstance(v, str) else v()
for k, v in self.partial_variables.items()
}
return {**partial_kwargs, **kwargs}
@abstractmethod
def format(self, **kwargs: Any) -> str:
"""Format the prompt with the inputs.
Args:
kwargs: Any arguments to be passed to the prompt template.
Returns:
A formatted string.
Example:
.. code-block:: python
prompt.format(variable1="foo")
"""
@property
@abstractmethod
def _prompt_type(self) -> str:
"""Return the prompt type key."""
def dict(self, **kwargs: Any) -> Dict:
"""Return dictionary representation of prompt."""
prompt_dict = super().dict(**kwargs)
prompt_dict["_type"] = self._prompt_type
return prompt_dict
def save(self, file_path: Union[Path, str]) -> None:
"""Save the prompt.
Args:
file_path: Path to directory to save prompt to.
Example:
.. code-block:: python
prompt.save(file_path="path/prompt.yaml")
"""
if self.partial_variables:
raise ValueError("Cannot save prompt with partial variables.")
# Convert file to Path object.
if isinstance(file_path, str):
save_path = Path(file_path)
else:
save_path = file_path
directory_path = save_path.parent
directory_path.mkdir(parents=True, exist_ok=True)
# Fetch dictionary to save
prompt_dict = self.dict()
if save_path.suffix == ".json":
with open(file_path, "w") as f:
json.dump(prompt_dict, f, indent=4)
elif save_path.suffix == ".yaml":
with open(file_path, "w") as f:
yaml.dump(prompt_dict, f, default_flow_style=False)
else:
raise ValueError(f"{save_path} must be json or yaml")
class StringPromptTemplate(BasePromptTemplate, ABC):
"""String prompt should expose the format method, returning a prompt."""
def format_prompt(self, **kwargs: Any) -> PromptValue:
"""Create Chat Messages."""
return StringPromptValue(text=self.format(**kwargs))
|