marie-ai
marie-ai copied to clipboard
Published
20 hours ago •
marieai
marieai
RuntimeFailToStart - Max retries exceeded with url: /fairseq/gpt2_bpe/vocab.bpe
Describe the feature
Your proposal Implement proper caching of FAISEQ models.
raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='dl.fbaipublicfiles.com', port=443): Max retries exceeded with url:
/fairseq/gpt2_bpe/vocab.bpe (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get
local issuer certificate (_ssl.c:1007)')))
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/venv/lib/python3.10/site-packages/marie/serve/executors/run.py", line 144, in run
runtime = AsyncNewLoopRuntime(
File "/opt/venv/lib/python3.10/site-packages/marie/serve/runtimes/asyncio.py", line 92, in __init__
self._loop.run_until_complete(self.async_setup())
File "/usr/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
return future.result()
File "/opt/venv/lib/python3.10/site-packages/marie/serve/runtimes/asyncio.py", line 309, in async_setup
self.server = self._get_server()
File "/opt/venv/lib/python3.10/site-packages/marie/serve/runtimes/asyncio.py", line 214, in _get_server
return GRPCServer(
File "/opt/venv/lib/python3.10/site-packages/marie/serve/runtimes/servers/grpc.py", line 34, in __init__
super().__init__(**kwargs)
File "/opt/venv/lib/python3.10/site-packages/marie/serve/runtimes/servers/__init__.py", line 70, in __init__
] = (req_handler or self._get_request_handler())
File "/opt/venv/lib/python3.10/site-packages/marie/serve/runtimes/servers/__init__.py", line 95, in _get_request_handler
return self.req_handler_cls(
File "/opt/venv/lib/python3.10/site-packages/marie/serve/runtimes/worker/request_handling.py", line 140, in __init__
self._load_executor(
File "/opt/venv/lib/python3.10/site-packages/marie/serve/runtimes/worker/request_handling.py", line 379, in _load_executor
self._executor: BaseExecutor = BaseExecutor.load_config(
File "/opt/venv/lib/python3.10/site-packages/marie/jaml/__init__.py", line 792, in load_config
obj = JAML.load(tag_yml, substitute=False, runtime_args=runtime_args)
File "/opt/venv/lib/python3.10/site-packages/marie/jaml/__init__.py", line 174, in load
r = yaml.load(stream, Loader=get_jina_loader_with_runtime(runtime_args))
File "/opt/venv/lib/python3.10/site-packages/yaml/__init__.py", line 81, in load
return loader.get_single_data()
File "/opt/venv/lib/python3.10/site-packages/yaml/constructor.py", line 51, in get_single_data
return self.construct_document(node)
File "/opt/venv/lib/python3.10/site-packages/yaml/constructor.py", line 55, in construct_document
data = self.construct_object(node)
File "/opt/venv/lib/python3.10/site-packages/yaml/constructor.py", line 100, in construct_object
data = constructor(self, node)
File "/opt/venv/lib/python3.10/site-packages/marie/jaml/__init__.py", line 582, in _from_yaml
return get_parser(cls, version=data.get('version', None)).parse(
File "/opt/venv/lib/python3.10/site-packages/marie/jaml/parsers/executor/legacy.py", line 46, in parse
obj = cls(
File "/opt/venv/lib/python3.10/site-packages/marie/serve/executors/decorators.py", line 58, in arg_wrapper
f = func(self, *args, **kwargs)
File "/opt/venv/lib/python3.10/site-packages/marie/serve/helper.py", line 75, in arg_wrapper
f = func(self, *args, **kwargs)
File "/opt/venv/lib/python3.10/site-packages/marie/executor/text/text_extraction_executor.py", line 104, in __init__
self.pipeline = ExtractPipeline(pipeline_config=pipeline, cuda=has_cuda)
File "/opt/venv/lib/python3.10/site-packages/marie/pipe/extract_pipeline.py", line 98, in __init__
self.ocr_engines = get_known_ocr_engines(device=device, engine=self.engine_name)
File "/opt/venv/lib/python3.10/site-packages/marie/ocr/util.py", line 118, in get_known_ocr_engines
trocr_processor = TrOcrProcessor(work_dir=ensure_exists("/tmp/icr"), cuda=use_cuda)
File "/opt/venv/lib/python3.10/site-packages/marie/document/trocr_ocr_processor.py", line 237, in __init__
) = init(model_path, beam, device)
File "/opt/venv/lib/python3.10/site-packages/marie/document/trocr_ocr_processor.py", line 59, in init
model, cfg, inference_task = fairseq.checkpoint_utils.load_model_ensemble_and_task(
File "/opt/venv/lib/python3.10/site-packages/fairseq/checkpoint_utils.py", line 502, in load_model_ensemble_and_task
model = task.build_model(cfg.model, from_checkpoint=True)
File "/opt/venv/lib/python3.10/site-packages/fairseq/tasks/fairseq_task.py", line 691, in build_model
model = models.build_model(args, self, from_checkpoint)
File "/opt/venv/lib/python3.10/site-packages/fairseq/models/__init__.py", line 106, in build_model
return model.build_model(cfg, task)
File "/opt/venv/lib/python3.10/site-packages/marie/models/unilm/trocr/trocr_models.py", line 169, in build_model
roberta = torch.hub.load('pytorch/fairseq:main', 'roberta.large')
File "/opt/venv/lib/python3.10/site-packages/torch/hub.py", line 568, in load
model = _load_local(repo_or_dir, model, *args, **kwargs)
File "/opt/venv/lib/python3.10/site-packages/torch/hub.py", line 597, in _load_local
model = entry(*args, **kwargs)
File "/opt/venv/lib/python3.10/site-packages/fairseq/models/roberta/model.py", line 380, in from_pretrained
return RobertaHubInterface(x["args"], x["task"], x["models"][0])
File "/opt/venv/lib/python3.10/site-packages/fairseq/models/roberta/hub_interface.py", line 26, in __init__
self.bpe = encoders.build_bpe(cfg.bpe)
File "/opt/venv/lib/python3.10/site-packages/fairseq/registry.py", line 65, in build_x
return builder(cfg, *extra_args, **extra_kwargs)
File "/opt/venv/lib/python3.10/site-packages/fairseq/data/encoders/gpt2_bpe.py", line 33, in __init__
vocab_bpe = file_utils.cached_path(cfg.gpt2_vocab_bpe)
File "/opt/venv/lib/python3.10/site-packages/fairseq/file_utils.py", line 174, in cached_path
return get_from_cache(url_or_filename, cache_dir)
File "/opt/venv/lib/python3.10/site-packages/fairseq/file_utils.py", line 299, in get_from_cache
response = request_wrap_timeout(
File "/opt/venv/lib/python3.10/site-packages/fairseq/file_utils.py", line 251, in request_wrap_timeout
return func(timeout=timeout)
File "/opt/venv/lib/python3.10/site-packages/requests/api.py", line 100, in head
return request("head", url, **kwargs)
File "/opt/venv/lib/python3.10/site-packages/requests/api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
File "/opt/venv/lib/python3.10/site-packages/requests/sessions.py", line 589, in request
resp = self.send(prep, **send_kwargs)
File "/opt/venv/lib/python3.10/site-packages/requests/sessions.py", line 703, in send
r = adapter.send(request, **kwargs)
File "/opt/venv/lib/python3.10/site-packages/requests/adapters.py", line 517, in send
raise SSLError(e, request=request)
requests.exceptions.SSLError: HTTPSConnectionPool(host='dl.fbaipublicfiles.com', port=443): Max retries exceeded with url: /fairseq/gpt2_bpe/vocab.bpe
(Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate
