Skip to content

Osai 96/evaluate improve new qa metrics #40

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 5 commits into from
Oct 15, 2025
Merged

Osai 96/evaluate improve new qa metrics #40

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
2e673bf
Change metrics on Ragas
Ana-ScottLogic Oct 15, 2025
1726456
OSAI-96/evaluate-improve-new-metrics
Ana-ScottLogic Oct 15, 2025
ceb95c6
run ruff
Ana-ScottLogic Oct 15, 2025
35fc71a
Break metrics in lines
Ana-ScottLogic Oct 15, 2025
6a16270
new changes with ruff
Ana-ScottLogic Oct 15, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
0 ...straZeneca-Sustainability-Report-2023.pdf → ...straZeneca-Sustainability-Report-2023.pdf
View file
Open in desktop
File renamed without changes.
22 changes: 13 additions & 9 deletions backend/tests/Ragas/utils/modules/ragas_evaluation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,9 +10,8 @@
import pandas as pd
from ragas import evaluate, EvaluationDataset, SingleTurnSample
from ragas.llms import LangchainLLMWrapper
from langchain_openai import ChatOpenAI
from ragas.metrics import FactualCorrectness, SemanticSimilarity
from ragas.metrics._nv_metrics import AnswerAccuracy
from langchain_openai.chat_models import ChatOpenAI
from ragas.metrics import answer_relevancy, ContextRelevance, SemanticSimilarity, context_precision
from ragas.embeddings import LangchainEmbeddingsWrapper
from langchain_openai import OpenAIEmbeddings
from dotenv import load_dotenv
Expand Down Expand Up @@ -151,11 +150,15 @@ async def evaluate_with_ragas(
dataset, samples, processed_data = create_ragas_dataset(data)

# Define metrics to use for evaluation
print("Configuring default RAGAS metrics: factual_correctness, semantic_similarity, answer_accuracy")
print(
"Configuring default RAGAS metrics: semantic_similarity, "
"answer_relevancy, context_relevance, context_precision"
)
metrics = [
FactualCorrectness(llm=llm),
SemanticSimilarity(embeddings=embeddings_wrapper),
AnswerAccuracy(llm=llm),
SemanticSimilarity(),
answer_relevancy,
context_precision,
ContextRelevance(llm=llm),
]

# Run the evaluation
Expand All @@ -166,9 +169,10 @@ async def evaluate_with_ragas(
print("Processing evaluation results including llm_usage if present...")
# Define expected metrics for alignment and output naming
expected_metrics = [
("factual_correctness(mode=f1)", "factual_correctness"),
("nv_context_relevance", "recontext_relevance"),
("context_precision", "context_precision"),
("answer_relevancy", "answer_relevancy"),
("semantic_similarity", "semantic_similarity"),
("nv_accuracy", "answer_accuracy"),
]

df = results.to_pandas()
Expand Down
Loading