📓 Text to Text Quickstart¶

In this quickstart you will create a simple text to text application and learn how to log it and get feedback.

Setup¶

Add API keys¶

For this quickstart you will need an OpenAI Key.

In [ ]:

# !pip install trulens trulens-providers-openai openai

# !pip install trulens trulens-providers-openai openai

In [ ]:

import os

os.environ["OPENAI_API_KEY"] = "sk-..."

import os os.environ["OPENAI_API_KEY"] = "sk-..."

Import from TruLens¶

In [ ]:

# Create openai client
from openai import OpenAI

# Imports main tools:
from trulens.core import Feedback
from trulens.core import TruSession
from trulens.providers.openai import OpenAI as fOpenAI

client = OpenAI()
session = TruSession()
session.reset_database()

# Create openai client from openai import OpenAI # Imports main tools: from trulens.core import Feedback from trulens.core import TruSession from trulens.providers.openai import OpenAI as fOpenAI client = OpenAI() session = TruSession() session.reset_database()

Create Simple Text to Text Application¶

This example uses a bare bones OpenAI LLM, and a non-LLM just for demonstration purposes.

In [ ]:

def llm_standalone(prompt):
    return (
        client.chat.completions.create(
            model="gpt-3.5-turbo",
            messages=[
                {
                    "role": "system",
                    "content": "You are a question and answer bot, and you answer super upbeat.",
                },
                {"role": "user", "content": prompt},
            ],
        )
        .choices[0]
        .message.content
    )

def llm_standalone(prompt): return ( client.chat.completions.create( model="gpt-3.5-turbo", messages=[ { "role": "system", "content": "You are a question and answer bot, and you answer super upbeat.", }, {"role": "user", "content": prompt}, ], ) .choices[0] .message.content )

Send your first request¶

In [ ]:

prompt_input = "How good is language AI?"
prompt_output = llm_standalone(prompt_input)
prompt_output

prompt_input = "How good is language AI?" prompt_output = llm_standalone(prompt_input) prompt_output

Initialize Feedback Function(s)¶

In [ ]:

# Initialize OpenAI-based feedback function collection class:
fopenai = fOpenAI()

# Define a relevance function from openai
f_answer_relevance = Feedback(fopenai.relevance).on_input_output()

# Initialize OpenAI-based feedback function collection class: fopenai = fOpenAI() # Define a relevance function from openai f_answer_relevance = Feedback(fopenai.relevance).on_input_output()

Instrument the callable for logging with TruLens¶

In [ ]:

from trulens.apps.basic import TruBasicApp

tru_llm_standalone_recorder = TruBasicApp(
    llm_standalone, app_name="Happy Bot", feedbacks=[f_answer_relevance]
)

from trulens.apps.basic import TruBasicApp tru_llm_standalone_recorder = TruBasicApp( llm_standalone, app_name="Happy Bot", feedbacks=[f_answer_relevance] )

In [ ]:

with tru_llm_standalone_recorder as recording:
    tru_llm_standalone_recorder.app(prompt_input)

with tru_llm_standalone_recorder as recording: tru_llm_standalone_recorder.app(prompt_input)

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

Or view results directly in your notebook¶

In [ ]:

session.get_records_and_feedback()[0]

session.get_records_and_feedback()[0]