[BUG] TypeError: Feedback.__init__() got an unexpected keyword argument 'groundedness_provider' when using Groundedness

[TedaLIEz]

Bug Description

I tried to evaluate my RAG app with Groundedness, but there is an error: TypeError: Feedback.__init__() got an unexpected keyword argument 'groundedness_provider'

To Reproduce

Following doc: https://www.trulens.org/component_guides/evaluation_benchmarks/groundedness_benchmark/?h=groundedness#benchmarking-various-groundedness-feedback-function-providers-openai-gpt-35-turbo-vs-gpt-4-vs-huggingface

from trulens.core import Feedback
from trulens.apps.llamaindex import TruLlama
from trulens.feedback.v2.feedback import Groundedness
import numpy as np
grounded = Groundedness(groundedness_provider=provider)
f_qa_relevance = Feedback(
    provider.relevance_with_cot_reasons,
    name="Answer Relevance"
).on_input_output()
context_selection = TruLlama.select_source_nodes().node.text
f_qs_relevance = (
    Feedback(provider.relevance_with_cot_reasons,
             name="Context Relevance")
    .on_input()
    .on(context_selection)
    .aggregate(np.mean)
)
f_groundedness = (
    Feedback(grounded.groundedness_measure_with_cot_reasons,
             name="Groundedness"
            )
    .on(context_selection)
    .on_output()
    .aggregate(grounded.grounded_statements_aggregator)
)

Expected behavior

No errors

Relevant Logs/Tracebacks

Traceback (most recent call last):
  File "/Users/JianGuo/VSCodeProject/learning-llm/advanced_rag/rag_eval.py", line 216, in <module>
    grounded = Groundedness(groundedness_provider=provider)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
TypeError: Feedback.__init__() got an unexpected keyword argument 'groundedness_provider'

Environment:

• OS: MacOS
• Python Version: 3.11.11
• TruLens version
  trulens-apps-langchain==1.3.2
  trulens-apps-llamaindex==1.3.2
  trulens-core==1.3.2
  trulens-dashboard==1.3.2
  trulens-feedback==1.3.2
  trulens-otel-semconv==1.3.2
  trulens-providers-openai==1.3.2
• Versions of other relevant installed libraries

[sfc-gh-jreini]

Hey @TedaLIEz - looks like this code is old. I'll get it updated.

Please try:

import numpy as np
from trulens.apps.llamaindex import TruLlama
from trulens.core import Feedback
from trulens.providers.openai import OpenAI

# Initialize provider class
provider = OpenAI()

# select context to be used in feedback. the location of context is app specific.

context = TruLlama.select_context(query_engine)

# Define a groundedness feedback function
f_groundedness = (
    Feedback(
        provider.groundedness_measure_with_cot_reasons, name="Groundedness"
    )
    .on(context.collect())  # collect context chunks into a list
    .on_output()
)

# Question/answer relevance between overall question and answer.
f_answer_relevance = Feedback(
    provider.relevance_with_cot_reasons, name="Answer Relevance"
).on_input_output()

# Question/statement relevance between question and each context chunk.
f_context_relevance = (
    Feedback(
        provider.context_relevance_with_cot_reasons, name="Context Relevance"
    )
    .on_input()
    .on(context)
    .aggregate(np.mean)
)