Jinad is the daemon tool for running Jina on remote machines. Jina is the cloud-native neural search solution powered by the state-of-the-art AI and deep learning
Project description
jinad - The Daemon to manage Jina remotely
Set up jinad on remote machines
The easist way of running jinad
is to use the docker image,
sudo docker run --rm -d --network host jinaai/jinad
You can verify whether it running properly by
export JINAD_IP=1.2.3.4
export JINAD_PORT=8000
curl -s -o /dev/null -w "%{http_code}" http://$JINAD_IP:$JINAD_PORT/v1/alive
1.2.3.4
is the public ip of your instance. By default, jinad is listening to the port8000
Use Case 1: Create Pods on remote machines
After having jinad
running on the remote machine, you can directly create and use the remote pods from your local machine
f = (Flow()
.add(name='p1', uses='_logforward')
.add(name='p2', host='1.2.3.4', port_expose='8000', uses='_logforward')
with f:
f.search_lines(lines=['jina', 'is', 'cute'], output_fn=print)
Use Case 2: Create Pods on remote using Jina CLI
jina pod --host 1.2.3.4 --port-expose 8000 --uses _logforward
Make sure
jinad
is running inpod
context
we need to pass a valid
role
for this (pydantic issue to be fixed)
Use Case 3: Create a Flow on remote
curl -s --request PUT "http://1.2.3.4:8000/v1/flow/yaml" -H "accept: application/json" -H "Content-Type: multipart/form-data" -F "uses_files=@helloworld.encoder.yml" -F "uses_files=@helloworld.indexer.yml" -F "pymodules_files=@components.py" -F "yamlspec=@helloworld.flow.index.yml"
Make sure
jinad
is running inflow
context
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
jinad-0.0.5.tar.gz
(16.7 kB
view hashes)