jinad 0.0.7

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

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"