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

Add Docker Images for running Haystack #85

Merged
merged 4 commits into from
May 4, 2020
Merged

Add Docker Images for running Haystack #85

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b1f1ff3
Add docker-compose for CPU
tanaysoni Apr 30, 2020
1c36746
Upgrade FARM version
tanaysoni Apr 30, 2020
bf8cdf8
Add script for running API on GPU
tanaysoni Apr 30, 2020
0a9d19a
Rename Docker Images
tanaysoni May 4, 2020
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
19 changes: 19 additions & 0 deletions docker-compose.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,19 @@
version: '3'
services:
haystack-api:
image: "deepset/haystack-api-cpu:0.2.0"
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How about naming the image "deepset/haystack-cpu:0.2.0" without the "api"? Is there anything specific for the API in it? We might also re-use it for training / eval ...

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Yes, that sounds good. The CMD for the image is specific to the API, but that can easily be moved to docker-compose.yml and run_docker_gpu.sh.

ports:
- 8000:8000
environment:
# see haystack/api/config.py for additional variables to configure.
# load reader model from transformers' model hub.
- READER_MODEL_PATH=deepset/roberta-base-squad2
- DB_HOST=elasticsearch
restart: always

elasticsearch:
# This demo image contains Game of Thrones Wikipedia articles indexed.
# For starting a new Elasticsearch instance, replace image with "elasticsearch:7.6.1".
image: "deepset/elasticsearch-game-of-thrones"
environment:
- discovery.type=single-node
3 changes: 1 addition & 2 deletions requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
# FARM pre-0.4.3
-e git://github.com/deepset-ai/FARM.git@ecee40e34781394a805c7dde14e6cc2570372798#egg=farm
farm==0.4.3
fastapi
uvicorn
gunicorn
Expand Down
11 changes: 11 additions & 0 deletions run_docker_gpu.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# Run Haystack API(on GPU) and Elasticsearch using Docker.
#
# docker-compose doesn't support GPUs in the current version. As a workaround,
# this script runs haystack-api and Elasticsearch Docker Images separately.
#
# To use GPU with Docker, ensure nvidia-docker(https://github.com/NVIDIA/nvidia-docker) is installed.

docker run -d -p 9200:9200 -e "discovery.type=single-node" elasticsearch:7.6.1
# wait for Elasticsearch server to start
sleep 30
docker run --net=host --gpus all -e READER_MODEL_PATH=deepset/roberta-base-squad2 -d deepset/haystack-api-gpu:0.2.0