search

facebookresearch / DrQA

Reading Wikipedia to Answer Open-Domain Questions
Other
4.48k stars 898 forks source link

Error in Interactive session #116

Closed augmen closed 6 years ago

augmen commented 6 years ago

after running the python3 scripts/pipeline/interactive.py i got this error

Traceback (most recent call last): File "scripts/pipeline/interactive.py", line 16, in <module> from drqa import pipeline ImportError: No module named 'drqa'

After copy and paste the entire interactive.py file in python3 console the interactive session to start. Then i type the Questions as 👍

process('What is the answer to life, the universe, and everything?') I got this error

File "/usr/lib/python3.5/code.py", line 91, in runcode exec(code, self.locals) File "<console>", line 1, in <module> File "<stdin>", line 2, in process NameError: name 'DrQA' is not defined

Please guide

I am currently using Linux 4GB ram machine. Any guidance would it be sufficient for the DrQA ?

With 8GB ram and 4CPU cores. i got this error Traceback (most recent call last): File "<stdin>", line 7, in <module> File "/root/DrQA/drqa/pipeline/drqa.py", line 109, in __init__ self.ranker = ranker_class(**ranker_opts) File "/root/DrQA/drqa/retriever/tfidf_doc_ranker.py", line 37, in __init__ matrix, metadata = utils.load_sparse_csr(tfidf_path) File "/root/DrQA/drqa/retriever/utils.py", line 34, in load_sparse_csr matrix = sp.csr_matrix((loader['data'], loader['indices'], File "/root/pt/local/lib/python3.5/site-packages/numpy/lib/npyio.py", line 235, in __getitem__ pickle_kwargs=self.pickle_kwargs) File "/root/pt/local/lib/python3.5/site-packages/numpy/lib/format.py", line 674, in read_array array = numpy.ndarray(count, dtype=dtype) MemoryError

I don't no why numpy gove me error ?

ajfisch commented 6 years ago

Please see the readme on how to run setup.py and setup your development environment. The readme also gives guidelines on resource requirements, 8GB of RAM is not enough to run the full Wikipedia queries.