mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
dff24285ea
This PR replaces the previous `Intent` check with the new `Prompt
Safety` check. The logic and steps to enable chain moderation via the
Amazon Comprehend service, allowing you to detect and redact PII, Toxic,
and Prompt Safety information in the LLM prompt or answer remains
unchanged.
This implementation updates the code and configuration types with
respect to `Prompt Safety`.
### Usage sample
```python
from langchain_experimental.comprehend_moderation import (BaseModerationConfig,
ModerationPromptSafetyConfig,
ModerationPiiConfig,
ModerationToxicityConfig
)
pii_config = ModerationPiiConfig(
labels=["SSN"],
redact=True,
mask_character="X"
)
toxicity_config = ModerationToxicityConfig(
threshold=0.5
)
prompt_safety_config = ModerationPromptSafetyConfig(
threshold=0.5
)
moderation_config = BaseModerationConfig(
filters=[pii_config, toxicity_config, prompt_safety_config]
)
comp_moderation_with_config = AmazonComprehendModerationChain(
moderation_config=moderation_config, #specify the configuration
client=comprehend_client, #optionally pass the Boto3 Client
verbose=True
)
template = """Question: {question}
Answer:"""
prompt = PromptTemplate(template=template, input_variables=["question"])
responses = [
"Final Answer: A credit card number looks like 1289-2321-1123-2387. A fake SSN number looks like 323-22-9980. John Doe's phone number is (999)253-9876.",
"Final Answer: This is a really shitty way of constructing a birdhouse. This is fucking insane to think that any birds would actually create their motherfucking nests here."
]
llm = FakeListLLM(responses=responses)
llm_chain = LLMChain(prompt=prompt, llm=llm)
chain = (
prompt
| comp_moderation_with_config
| {llm_chain.input_keys[0]: lambda x: x['output'] }
| llm_chain
| { "input": lambda x: x['text'] }
| comp_moderation_with_config
)
try:
response = chain.invoke({"question": "A sample SSN number looks like this 123-456-7890. Can you give me some more samples?"})
except Exception as e:
print(str(e))
else:
print(response['output'])
```
### Output
```python
> Entering new AmazonComprehendModerationChain chain...
Running AmazonComprehendModerationChain...
Running pii Validation...
Running toxicity Validation...
Running prompt safety Validation...
> Finished chain.
> Entering new AmazonComprehendModerationChain chain...
Running AmazonComprehendModerationChain...
Running pii Validation...
Running toxicity Validation...
Running prompt safety Validation...
> Finished chain.
Final Answer: A credit card number looks like 1289-2321-1123-2387. A fake SSN number looks like XXXXXXXXXXXX John Doe's phone number is (999)253-9876.
```
---------
Co-authored-by: Jha <nikjha@amazon.com>
Co-authored-by: Anjan Biswas <anjanavb@amazon.com>
Co-authored-by: Anjan Biswas <84933469+anjanvb@users.noreply.github.com>
66 lines
2.1 KiB
Python
66 lines
2.1 KiB
Python
from typing import Any, Callable, Dict
|
|
|
|
|
|
class BaseModerationCallbackHandler:
|
|
def __init__(self) -> None:
|
|
if (
|
|
self._is_method_unchanged(
|
|
BaseModerationCallbackHandler.on_after_pii, self.on_after_pii
|
|
)
|
|
and self._is_method_unchanged(
|
|
BaseModerationCallbackHandler.on_after_toxicity, self.on_after_toxicity
|
|
)
|
|
and self._is_method_unchanged(
|
|
BaseModerationCallbackHandler.on_after_prompt_safety,
|
|
self.on_after_prompt_safety,
|
|
)
|
|
):
|
|
raise NotImplementedError(
|
|
"Subclasses must override at least one of on_after_pii(), "
|
|
"on_after_toxicity(), or on_after_prompt_safety() functions."
|
|
)
|
|
|
|
def _is_method_unchanged(
|
|
self, base_method: Callable, derived_method: Callable
|
|
) -> bool:
|
|
return base_method.__qualname__ == derived_method.__qualname__
|
|
|
|
async def on_after_pii(
|
|
self, moderation_beacon: Dict[str, Any], unique_id: str, **kwargs: Any
|
|
) -> None:
|
|
"""Run after PII validation is complete."""
|
|
pass
|
|
|
|
async def on_after_toxicity(
|
|
self, moderation_beacon: Dict[str, Any], unique_id: str, **kwargs: Any
|
|
) -> None:
|
|
"""Run after Toxicity validation is complete."""
|
|
pass
|
|
|
|
async def on_after_prompt_safety(
|
|
self, moderation_beacon: Dict[str, Any], unique_id: str, **kwargs: Any
|
|
) -> None:
|
|
"""Run after Prompt Safety validation is complete."""
|
|
pass
|
|
|
|
@property
|
|
def pii_callback(self) -> bool:
|
|
return (
|
|
self.on_after_pii.__func__ # type: ignore
|
|
is not BaseModerationCallbackHandler.on_after_pii
|
|
)
|
|
|
|
@property
|
|
def toxicity_callback(self) -> bool:
|
|
return (
|
|
self.on_after_toxicity.__func__ # type: ignore
|
|
is not BaseModerationCallbackHandler.on_after_toxicity
|
|
)
|
|
|
|
@property
|
|
def prompt_safety_callback(self) -> bool:
|
|
return (
|
|
self.on_after_prompt_safety.__func__ # type: ignore
|
|
is not BaseModerationCallbackHandler.on_after_prompt_safety
|
|
)
|