Closed CZT0 closed 1 month ago
I'm also having the same issue
I'm also having the same issue for answer_correctness
and answer_similarity
.
I'm getting the following error:
Traceback (most recent call last):
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/threading.py", line 1009, in _bootstrap_inner
self.run()
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/executor.py", line 93, in run
results = self.loop.run_until_complete(self._aresults())
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/asyncio/base_events.py", line 646, in run_until_complete
return future.result()
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/executor.py", line 81, in _aresults
raise e
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/executor.py", line 76, in _aresults
r = await future
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/asyncio/tasks.py", line 571, in _wait_for_one
return f.result() # May raise f.exception().
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/executor.py", line 36, in sema_coro
return await coro
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/executor.py", line 109, in wrapped_callable_async
return counter, await callable(*args, **kwargs)
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/metrics/base.py", line 91, in ascore
raise e
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/metrics/base.py", line 87, in ascore
score = await self._ascore(row=row, callbacks=group_cm, is_async=is_async)
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/metrics/_answer_similarity.py", line 65, in _ascore
embedding_1 = np.array(await self.embeddings.embed_text(ground_truth))
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/embeddings/base.py", line 23, in embed_text
embs = await self.embed_texts([text], is_async=is_async)
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/embeddings/base.py", line 33, in embed_texts
return await aembed_documents_with_retry(texts)
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/tenacity/_asyncio.py", line 88, in async_wrapped
return await fn(*args, **kwargs)
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/tenacity/_asyncio.py", line 47, in __call__
do = self.iter(retry_state=retry_state)
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/tenacity/__init__.py", line 325, in iter
raise retry_exc.reraise()
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/tenacity/__init__.py", line 158, in reraise
raise self.last_attempt.result()
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/concurrent/futures/_base.py", line 439, in result
return self.__get_result()
File "/Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/concurrent/futures/_base.py", line 391, in __get_result
raise self._exception
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/tenacity/_asyncio.py", line 50, in __call__
result = await fn(*args, **kwargs)
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/embeddings/base.py", line 66, in aembed_documents
return await self.embeddings.aembed_documents(texts)
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/langchain_openai/embeddings/base.py", line 526, in aembed_documents
return await self._aget_len_safe_embeddings(texts, engine=engine)
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/langchain_openai/embeddings/base.py", line 435, in _aget_len_safe_embeddings
token = encoding.encode(
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/tiktoken/core.py", line 116, in encode
if match := _special_token_regex(disallowed_special).search(text):
TypeError: expected string or buffer
Traceback (most recent call last):
File "/Users/dcast/Documents/GitHub/all-about-rag/src/scripts/evaluate_auto_merging_ragas.py", line 67, in <module>
result = evaluate(
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/evaluation.py", line 228, in evaluate
raise e
File "/Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/evaluation.py", line 210, in evaluate
raise ExceptionInRunner()
ragas.exceptions.ExceptionInRunner: The runner thread which was running the jobs raised an exeception. Read the traceback above to debug it. You can also pass `raise_exceptions=False` incase you want to show only a warning message instead.
2024-03-10 19:28:51,571 ERROR asyncio: Task was destroyed but it is pending!
task: <Task pending name='Task-48' coro=<as_completed.<locals>.sema_coro() running at /Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/executor.py:36> wait_for=<Future pending cb=[Task.task_wakeup()]> cb=[as_completed.<locals>._on_completion() at /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/asyncio/tasks.py:558]>
2024-03-10 19:28:51,571 ERROR asyncio: Task was destroyed but it is pending!
task: <Task pending name='Task-43' coro=<as_completed.<locals>.sema_coro() running at /Users/dcast/Documents/GitHub/all-about-rag/.venv/lib/python3.10/site-packages/ragas/executor.py:36> wait_for=<Future pending cb=[Task.task_wakeup()]> cb=[as_completed.<locals>._on_completion() at /Library/Frameworks/Python.framework/Versions/3.10/lib/python3.10/asyncio/tasks.py:558]>
Just found the issue. This was due to having null values in the ground_truth
column. Interestingly, those NAs are from synthetically generated questions using generate_with_llamaindex_docs
.
@shahules786 might be good to raise a warning in these cases. What do you think?
Happy to help with a PR, if that makes sense.
Hey @dylanjcastillo makes sense. Would love to see the PR bro
Describe the bug When attempting to evaluate
answer_similarity
andanswer_correctness
using the Ragas framework, I encounter a timeout error. While I can successfully retrieve metrics forcontext_relevancy
andcontext_recall
, the progress bar stalls for a long time and eventually times out when evaluatinganswer_similarity
andanswer_correctness
.Ragas version: ragas-0.0.23.dev37+g041b20c Python version: 3.11 DATA: 63521_1.json
Code to Reproduce
Error trace
Expected behavior I expected the
answer_similarity
andanswer_correctness
evaluations to succeed without a timeout error, similar to the other metrics.Additional context In my use of Ragas for evaluation, other metrics like
context_relevancy
andcontext_recall
work normally. The issue arises solely when evaluatinganswer_similarity
andanswer_correctness
.