Goal: to run this Auto Labelling Notebook on AWS SageMaker Jupyter Labs.
Kernels tried: conda_pytorch_p36
, conda_python3
, conda_amazonei_mxnet_p27
.
! pip install farm-haystack -q
# Install the latest master of Haystack
!pip install grpcio-tools==1.34.1 -q
!pip install git+https://github.com/deepset-ai/haystack.git -q
!wget --no-check-certificate https://dl.xpdfreader.com/xpdf-tools-linux-4.03.tar.gz
!tar -xvf xpdf-tools-linux-4.03.tar.gz && sudo cp xpdf-tools-linux-4.03/bin64/pdftotext /usr/local/bin
!pip install git+https://github.com/deepset-ai/haystack.git -q
# Here are the imports we need
from haystack.document_stores.elasticsearch import ElasticsearchDocumentStore
from haystack.nodes import PreProcessor, TransformersDocumentClassifier, FARMReader, ElasticsearchRetriever
from haystack.schema import Document
from haystack.utils import convert_files_to_dicts, fetch_archive_from_http, print_answers
Traceback:
02/02/2022 10:36:29 - INFO - faiss.loader - Loading faiss with AVX2 support.
02/02/2022 10:36:29 - INFO - faiss.loader - Could not load library with AVX2 support due to:
ModuleNotFoundError("No module named 'faiss.swigfaiss_avx2'",)
02/02/2022 10:36:29 - INFO - faiss.loader - Loading faiss.
02/02/2022 10:36:29 - INFO - faiss.loader - Successfully loaded faiss.
02/02/2022 10:36:33 - INFO - farm.modeling.prediction_head - Better speed can be achieved with apex installed from https://www.github.com/nvidia/apex .
---------------------------------------------------------------------------
ModuleNotFoundError Traceback (most recent call last)
<ipython-input-4-6ff421127e9c> in <module>
1 # Here are the imports we need
----> 2 from haystack.document_stores.elasticsearch import ElasticsearchDocumentStore
3 from haystack.nodes import PreProcessor, TransformersDocumentClassifier, FARMReader, ElasticsearchRetriever
4 from haystack.schema import Document
5 from haystack.utils import convert_files_to_dicts, fetch_archive_from_http, print_answers
~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/haystack/__init__.py in <module>
3 import pandas as pd
4 from haystack.schema import Document, Label, MultiLabel, BaseComponent
----> 5 from haystack.finder import Finder
6 from haystack.pipeline import Pipeline
7
~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/haystack/finder.py in <module>
6 from collections import defaultdict
7
----> 8 from haystack.reader.base import BaseReader
9 from haystack.retriever.base import BaseRetriever
10 from haystack import MultiLabel
~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/haystack/reader/__init__.py in <module>
----> 1 from haystack.reader.farm import FARMReader
2 from haystack.reader.transformers import TransformersReader
~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/haystack/reader/farm.py in <module>
22
23 from haystack import Document
---> 24 from haystack.document_store.base import BaseDocumentStore
25 from haystack.reader.base import BaseReader
26
~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/haystack/document_store/__init__.py in <module>
2 from haystack.document_store.faiss import FAISSDocumentStore
3 from haystack.document_store.memory import InMemoryDocumentStore
----> 4 from haystack.document_store.milvus import MilvusDocumentStore
5 from haystack.document_store.sql import SQLDocumentStore
~/anaconda3/envs/pytorch_p36/lib/python3.6/site-packages/haystack/document_store/milvus.py in <module>
5 import numpy as np
6
----> 7 from milvus import IndexType, MetricType, Milvus, Status
8 from scipy.special import expit
9 from tqdm import tqdm
ModuleNotFoundError: No module named 'milvus'
pip install milvus
import milvus
Traceback:
---------------------------------------------------------------------------
ModuleNotFoundError Traceback (most recent call last)
<ipython-input-3-91c33e248077> in <module>
----> 1 import milvus
ModuleNotFoundError: No module named 'milvus'
pymilvus
package. – Sycepip install pymilvus
andimport pymilvus
throws the same Traceback ;( – Proprietor