Comprehend Moderation 0.2 (#11730)

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>

libs/experimental/langchain_experimental/comprehend_moderation/base_moderation.py

@@ -6,8 +6,10 @@ from langchain.prompts.base import StringPromptValue
 from langchain.prompts.chat import ChatPromptValue
 from langchain.schema import AIMessage, HumanMessage
 
-from langchain_experimental.comprehend_moderation.intent import ComprehendIntent
 from langchain_experimental.comprehend_moderation.pii import ComprehendPII
+from langchain_experimental.comprehend_moderation.prompt_safety import (
+    ComprehendPromptSafety,
+)
 from langchain_experimental.comprehend_moderation.toxicity import ComprehendToxicity
 
 
@@ -109,13 +111,13 @@ class BaseModeration:
 
     def moderate(self, prompt: Any) -> str:
         from langchain_experimental.comprehend_moderation.base_moderation_config import (  # noqa: E501
-            ModerationIntentConfig,
             ModerationPiiConfig,
+            ModerationPromptSafetyConfig,
             ModerationToxicityConfig,
         )
         from langchain_experimental.comprehend_moderation.base_moderation_exceptions import (  # noqa: E501
-            ModerationIntentionError,
             ModerationPiiError,
+            ModerationPromptSafetyError,
             ModerationToxicityError,
         )
 
@@ -128,7 +130,7 @@ class BaseModeration:
             filter_functions = {
                 "pii": ComprehendPII,
                 "toxicity": ComprehendToxicity,
-                "intent": ComprehendIntent,
+                "prompt_safety": ComprehendPromptSafety,
             }
 
             filters = self.config.filters  # type: ignore
@@ -141,8 +143,8 @@ class BaseModeration:
                         "toxicity"
                         if isinstance(_filter, ModerationToxicityConfig)
                         else (
-                            "intent"
-                            if isinstance(_filter, ModerationIntentConfig)
+                            "prompt_safety"
+                            if isinstance(_filter, ModerationPromptSafetyConfig)
                             else None
                         )
                     )
@@ -171,7 +173,7 @@ class BaseModeration:
                 f"Found Toxic content..stopping..\n{str(e)}\n"
             )
             raise e
-        except ModerationIntentionError as e:
+        except ModerationPromptSafetyError as e:
             self._log_message_for_verbose(
                 f"Found Harmful intention..stopping..\n{str(e)}\n"
             )