Skip to content
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

enhance multihop dataset accuracy #62

Merged
merged 2 commits into from
Aug 21, 2024
Merged

enhance multihop dataset accuracy #62

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3b80da5
add rerank.
sys-lpot-val Aug 12, 2024
5d23a97
update gaudi base docker image.
Aug 21, 2024
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
22 changes: 22 additions & 0 deletions evals/evaluation/rag_eval/examples/eval_multihop.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,22 @@ def get_document(self, data: dict):
)
return document

def get_reranked_documents(self, query, docs, arguments):
data = {
"initial_query": query,
"retrieved_docs": [{"text": doc} for doc in docs],
"top_n": 10,
}
headers = {"Content-Type": "application/json"}

response = requests.post(arguments.reranking_endpoint, data=json.dumps(data), headers=headers)
if response.ok:
reranked_documents = response.json()["documents"]
return reranked_documents
else:
print(f"Request for retrieval failed due to {response.text}.")
return []

def get_retrieved_documents(self, query, arguments):
data = {"text": query}
headers = {"Content-Type": "application/json"}
Expand Down Expand Up @@ -77,6 +93,8 @@ def get_retrieval_metrics(self, all_queries, arguments):
continue
query = data["query"]
retrieved_documents = self.get_retrieved_documents(query, arguments)
if arguments.rerank:
retrieved_documents = self.get_reranked_documents(query, retrieved_documents, arguments)
golden_context = [each["fact"] for each in data["evidence_list"]]
test_case = {
"input": query,
Expand Down Expand Up @@ -212,6 +230,10 @@ def args_parser():
parser.add_argument(
"--retrieval_endpoint", type=str, default="http://localhost:7000/v1/retrieval", help="Service URL address."
)
parser.add_argument("--rerank", action="store_true", help="Whether to use rerank microservice.")
parser.add_argument(
"--reranking_endpoint", type=str, default="http://localhost:8000/v1/reranking", help="Service URL address."
)
parser.add_argument("--llm_endpoint", type=str, default=None, help="Service URL address.")
parser.add_argument(
"--show_progress_bar", action="store", default=True, type=bool, help="Whether to show a progress bar"
Expand Down
2 changes: 1 addition & 1 deletion evals/metrics/ragas/ragas.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,7 +31,7 @@ def __init__(
self.model = model
self.embeddings = embeddings
self.metrics = metrics
self.validated_list = ["answer_relevancy", "faithfulness"]
self.validated_list = ["answer_relevancy", "faithfulness", "answer_correctness"]

async def a_measure(self, test_case: Dict):
return self.measure(test_case)
Expand Down
Loading