PII Detection¶

In this example you will learn how to implement PII detection with TruLens.

In [ ]:

# !pip install trulens trulens-providers-huggingface trulens-apps-langchain 'langchain>=0.0.263' langchain_community

# !pip install trulens trulens-providers-huggingface trulens-apps-langchain 'langchain>=0.0.263' langchain_community

Setup¶

Add API keys¶

For this quickstart you will need Open AI and Huggingface keys

In [ ]:

import os

os.environ["OPENAI_API_KEY"] = "..."
os.environ["HUGGINGFACE_API_KEY"] = "..."

import os os.environ["OPENAI_API_KEY"] = "..." os.environ["HUGGINGFACE_API_KEY"] = "..."

Import from LangChain and TruLens¶

In [ ]:

# Imports from langchain to build app. You may need to install langchain first
# with the following:
# !pip install langchain>=0.0.170
from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
from langchain.prompts.chat import ChatPromptTemplate
from langchain.prompts.chat import HumanMessagePromptTemplate
from langchain_community.llms import OpenAI
from trulens.core import Feedback
from trulens.core import TruSession
from trulens.apps.langchain import TruChain
from trulens.providers.huggingface import Huggingface

session = TruSession()
session.reset_database()

# Imports from langchain to build app. You may need to install langchain first # with the following: # !pip install langchain>=0.0.170 from langchain.chains import LLMChain from langchain.prompts import PromptTemplate from langchain.prompts.chat import ChatPromptTemplate from langchain.prompts.chat import HumanMessagePromptTemplate from langchain_community.llms import OpenAI from trulens.core import Feedback from trulens.core import TruSession from trulens.apps.langchain import TruChain from trulens.providers.huggingface import Huggingface session = TruSession() session.reset_database()

Create Simple LLM Application¶

This example uses a LangChain framework and OpenAI LLM

In [ ]:

full_prompt = HumanMessagePromptTemplate(
    prompt=PromptTemplate(
        template="Provide a helpful response with relevant background information for the following: {prompt}",
        input_variables=["prompt"],
    )
)

chat_prompt_template = ChatPromptTemplate.from_messages([full_prompt])

llm = OpenAI(temperature=0.9, max_tokens=128)

chain = LLMChain(llm=llm, prompt=chat_prompt_template, verbose=True)

full_prompt = HumanMessagePromptTemplate( prompt=PromptTemplate( template="Provide a helpful response with relevant background information for the following: {prompt}", input_variables=["prompt"], ) ) chat_prompt_template = ChatPromptTemplate.from_messages([full_prompt]) llm = OpenAI(temperature=0.9, max_tokens=128) chain = LLMChain(llm=llm, prompt=chat_prompt_template, verbose=True)

In [ ]:

prompt_input = (
    "Sam Altman is the CEO at OpenAI, and uses the password: password1234 ."
)

prompt_input = ( "Sam Altman is the CEO at OpenAI, and uses the password: password1234 ." )

Initialize Feedback Function(s)¶

In [ ]:

hugs = Huggingface()

# Define a pii_detection feedback function using HuggingFace.
f_pii_detection = Feedback(hugs.pii_detection_with_cot_reasons).on_input()
# By default this will check language match on the main app input

hugs = Huggingface() # Define a pii_detection feedback function using HuggingFace. f_pii_detection = Feedback(hugs.pii_detection_with_cot_reasons).on_input() # By default this will check language match on the main app input

Instrument chain for logging with TruLens¶

In [ ]:

tru_recorder = TruChain(
    chain, app_name="Chain1_ChatApplication", feedbacks=[f_pii_detection]
)

tru_recorder = TruChain( chain, app_name="Chain1_ChatApplication", feedbacks=[f_pii_detection] )

In [ ]:

with tru_recorder as recording:
    llm_response = chain(prompt_input)

display(llm_response)

with tru_recorder as recording: llm_response = chain(prompt_input) display(llm_response)

Explore in a Dashboard¶

In [ ]:

from trulens.dashboard import run_dashboard

run_dashboard(session)  # open a local streamlit app to explore

# stop_dashboard(session) # stop if needed

from trulens.dashboard import run_dashboard run_dashboard(session) # open a local streamlit app to explore # stop_dashboard(session) # stop if needed

Note: Feedback functions evaluated in the deferred manner can be seen in the "Progress" page of the TruLens dashboard.

Or view results directly in your notebook¶

In [ ]:

session.get_records_and_feedback()[0]

session.get_records_and_feedback()[0]