mirror of
https://github.com/hwchase17/langchain
synced 2024-11-10 01:10:59 +00:00
d57d08fd01
This PR implements a custom chain that wraps Amazon Comprehend API
calls. The custom chain is aimed to be used with LLM chains to provide
moderation capability that let’s you detect and redact PII, Toxic and
Intent content in the LLM prompt, or the LLM response. The
implementation accepts a configuration object to control what checks
will be performed on a LLM prompt and can be used in a variety of setups
using the LangChain expression language to not only detect the
configured info in chains, but also other constructs such as a
retriever.
The included sample notebook goes over the different configuration
options and how to use it with other chains.
### Usage sample
```python
from langchain_experimental.comprehend_moderation import BaseModerationActions, BaseModerationFilters
moderation_config = {
"filters":[
BaseModerationFilters.PII,
BaseModerationFilters.TOXICITY,
BaseModerationFilters.INTENT
],
"pii":{
"action": BaseModerationActions.ALLOW,
"threshold":0.5,
"labels":["SSN"],
"mask_character": "X"
},
"toxicity":{
"action": BaseModerationActions.STOP,
"threshold":0.5
},
"intent":{
"action": BaseModerationActions.STOP,
"threshold":0.5
}
}
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
)
response = chain.invoke({"question": "A sample SSN number looks like this 123-456-7890. Can you give me some more samples?"})
print(response['output'])
```
### Output
```
> Entering new AmazonComprehendModerationChain chain...
Running AmazonComprehendModerationChain...
Running pii validation...
Found PII content..stopping..
The prompt contains PII entities and cannot be processed
```
---------
Co-authored-by: Piyush Jain <piyushjain@duck.com>
Co-authored-by: Anjan Biswas <anjanavb@amazon.com>
Co-authored-by: Jha <nikjha@amazon.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
44 lines
1.1 KiB
Python
44 lines
1.1 KiB
Python
class ModerationPiiError(Exception):
|
|
"""Exception raised if PII entities are detected.
|
|
|
|
Attributes:
|
|
message -- explanation of the error
|
|
"""
|
|
|
|
def __init__(
|
|
self, message: str = "The prompt contains PII entities and cannot be processed"
|
|
):
|
|
self.message = message
|
|
super().__init__(self.message)
|
|
|
|
|
|
class ModerationToxicityError(Exception):
|
|
"""Exception raised if Toxic entities are detected.
|
|
|
|
Attributes:
|
|
message -- explanation of the error
|
|
"""
|
|
|
|
def __init__(
|
|
self, message: str = "The prompt contains toxic content and cannot be processed"
|
|
):
|
|
self.message = message
|
|
super().__init__(self.message)
|
|
|
|
|
|
class ModerationIntentionError(Exception):
|
|
"""Exception raised if Intention entities are detected.
|
|
|
|
Attributes:
|
|
message -- explanation of the error
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
message: str = (
|
|
"The prompt indicates an un-desired intent and " "cannot be processed"
|
|
),
|
|
):
|
|
self.message = message
|
|
super().__init__(self.message)
|