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
An easier way to build neural search in the cloud
jinad - The Daemon to manage Jina remotely
jinad is a REST + Websockets based server to allow remote workflows in Jina. It is built using FastAPI and deployed using Uvicorn.
Jina Docs: https://docs.jina.ai/
JinaD API Docs: https://api.jina.ai/jinad
Set up:
Pypi:
On Linux/macOS with Python 3.7/3.8:
pip install -U jinad && jinad
Docker Container:
docker run -p 8000:8000 jinaai/jinad
Systemd:
Debian / Ubuntu:
curl -L https://raw.githubusercontent.com/jina-ai/jinad/main/scripts/deb-systemd.sh | bash
RPM:
to be added
Use Cases:
Start jinad on a remote machine - 1.2.3.4:8000
1: Create Remote Pod in a Flow
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)
2: Create Remote Pod using Jina CLI
jina pod --host 1.2.3.4 --port-expose 8000 --uses _logforward
3: Create a Remote Flow
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"
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
jinad-0.0.7.tar.gz
(17.9 kB
view hashes)
