DeepEval

In [ ]:

!pip install -q -q llama-index
!pip install -U -q deepeval

!pip install -q -q llama-index !pip install -U -q deepeval

In [8]:

import os
from getpass import getpass
import openai
import nest_asyncio
nest_asyncio.apply() 

if not (openai_api_key := os.getenv("OPENAI_API_KEY")):
    openai_api_key = getpass("🔑 Enter your OpenAI API key: ")
openai.api_key = openai_api_key
os.environ["OPENAI_API_KEY"] = openai_api_key

import os from getpass import getpass import openai import nest_asyncio nest_asyncio.apply() if not (openai_api_key := os.getenv("OPENAI_API_KEY")): openai_api_key = getpass("🔑 Enter your OpenAI API key: ") openai.api_key = openai_api_key os.environ["OPENAI_API_KEY"] = openai_api_key

In [5]:

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader

# Read LlamaIndex's quickstart on more details, you will need to store your data in "YOUR_DATA_DIRECTORY" beforehand
documents = SimpleDirectoryReader("../data").load_data()
index = VectorStoreIndex.from_documents(documents)
rag_application = index.as_query_engine()

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader # Read LlamaIndex's quickstart on more details, you will need to store your data in "YOUR_DATA_DIRECTORY" beforehand documents = SimpleDirectoryReader("../data").load_data() index = VectorStoreIndex.from_documents(documents) rag_application = index.as_query_engine()

In [ ]:

from deepeval.integrations.llama_index import DeepEvalFaithfulnessEvaluator

# An example input to your RAG application
user_input = "What is LlamaIndex?"

# LlamaIndex returns a response object that contains
# both the output string and retrieved nodes
response_object = rag_application.query(user_input)

evaluator = DeepEvalFaithfulnessEvaluator()
evaluation_result = evaluator.evaluate_response(
    query=user_input, response=response_object
)
print(evaluation_result)

from deepeval.integrations.llama_index import DeepEvalFaithfulnessEvaluator # An example input to your RAG application user_input = "What is LlamaIndex?" # LlamaIndex returns a response object that contains # both the output string and retrieved nodes response_object = rag_application.query(user_input) evaluator = DeepEvalFaithfulnessEvaluator() evaluation_result = evaluator.evaluate_response( query=user_input, response=response_object ) print(evaluation_result)

In [ ]:

from deepeval.integrations.llama_index import (
    DeepEvalAnswerRelevancyEvaluator,
    DeepEvalFaithfulnessEvaluator,
    DeepEvalContextualRelevancyEvaluator,
    DeepEvalSummarizationEvaluator,
    DeepEvalBiasEvaluator,
    DeepEvalToxicityEvaluator,
)

from deepeval.integrations.llama_index import ( DeepEvalAnswerRelevancyEvaluator, DeepEvalFaithfulnessEvaluator, DeepEvalContextualRelevancyEvaluator, DeepEvalSummarizationEvaluator, DeepEvalBiasEvaluator, DeepEvalToxicityEvaluator, )

In [ ]:

evaluator = DeepEvalAnswerRelevancyEvaluator()
evaluation_result = evaluator.evaluate_response(
    query=user_input, response=response_object
)
print(evaluation_result)

evaluator = DeepEvalAnswerRelevancyEvaluator() evaluation_result = evaluator.evaluate_response( query=user_input, response=response_object ) print(evaluation_result)