An easier way to build neural search on the cloud

Cloud-Native Neural Search^[?] Framework for Any Kind of Data

Jina allows you to build deep learning-powered search-as-a-service in just minutes.

🌌 All data type - Large-scale indexing and querying of any kind of unstructured data: video, image, long/short text, music, source code, PDF, etc.

🌩️ Fast & cloud-native - Distributed architecture from day one. Scalable & cloud-native by design: enjoy containerizing, distributing, streaming, paralleling, sharding, async scheduling with REST/gRPC/WebSocket.

⏱️ Save time - The design pattern of neural search systems, from zero to a production-ready system in minutes.

🍱 Own your stack - Keep an end-to-end stack ownership of your solution, avoid integration pitfalls with fragmented, multi-vendor, generic legacy tools.

Run Quick Demo

• 👗 Fashion image search: pip install --pre && jina hello fashion
• 🤖 QA chatbot: pip install --pre "jina[chatbot]" && jina hello chatbot
• 📰 Multimodal search: pip install --pre "jina[multimodal]" && jina hello multimodal
• 🍴 Fork the source of a demo to your folder: jina hello fork fashion ../my-proj/

Install

2.0 is in pre-release, add --pre to install it. Why 2.0?

$ pip install --pre jina
$ jina -v
2.0.0rcN

via Docker

$ docker run jinaai/jina:master -v
2.0.0rcN

Get Started

Document, Executor, and Flow are the three fundamental concepts in Jina.

• 📄 Document is the basic data type in Jina;
• ⚙️ Executor is how Jina processes Documents;
• 🔀 Flow is how Jina streamlines and distributes Executors.

Copy-paste the minimum example below and run it:

^{💡 Preliminaries: character embedding, pooling, Euclidean distance}

import numpy as np
from jina import Document, DocumentArray, Executor, Flow, requests

class CharEmbed(Executor):  # a simple character embedding with mean-pooling
    offset = 32  # letter `a`
    dim = 127 - offset + 1  # last pos reserved for `UNK`
    char_embd = np.eye(dim) * 1  # one-hot embedding for all chars

    @requests
    def foo(self, docs: DocumentArray, **kwargs):
        for d in docs:
            r_emb = [ord(c) - self.offset if self.offset <= ord(c) <= 127 else (self.dim - 1) for c in d.text]
            d.embedding = self.char_embd[r_emb, :].mean(axis=0)  # average pooling

class Indexer(Executor):
    _docs = DocumentArray()  # for storing all documents in memory

    @requests(on='/index')
    def foo(self, docs: DocumentArray, **kwargs):
        self._docs.extend(docs)  # extend stored `docs`

    @requests(on='/search')
    def bar(self, docs: DocumentArray, **kwargs):
        q = np.stack(docs.get_attributes('embedding'))  # get all embeddings from query docs
        d = np.stack(self._docs.get_attributes('embedding'))  # get all embeddings from stored docs
        euclidean_dist = np.linalg.norm(q[:, None, :] - d[None, :, :], axis=-1)  # pairwise euclidean distance
        for dist, query in zip(euclidean_dist, docs):  # add & sort match
            query.matches = [Document(self._docs[int(idx)], copy=True, score=d) for idx, d in enumerate(dist)]
            query.matches.sort(key=lambda m: m.score.value)  # sort matches by their values

f = Flow(port_expose=12345).add(uses=CharEmbed, parallel=2).add(uses=Indexer)  # build a Flow, with 2 parallel CharEmbed, tho unnecessary
with f:
    f.post('/index', (Document(text=t.strip()) for t in open(__file__) if t.strip()))  # index all lines of this file
    f.block()  # block for listening request

Keep the above running and start a simple client:

from jina import Client, Document

def print_matches(req):  # the callback function invoked when task is done
    for idx, d in enumerate(req.docs[0].matches[:3]):  # print top-3 matches
        print(f'[{idx}]{d.score.value:2f}: "{d.text}"')
        
c = Client(host='localhost', port_expose=12345)  # connect to localhost:12345
c.post('/search', Document(text='request(on=something)'), on_done=print_matches)

It finds the lines most similar to "request(on=something)" from the server code snippet and prints the following:

         Client@1608[S]:connected to the gateway at localhost:12345!
[0]0.168526: "@requests(on='/index')"
[1]0.181676: "@requests(on='/search')"
[2]0.192049: "query.matches = [Document(self._docs[int(idx)], copy=True, score=d) for idx, d in enumerate(dist)]"

^{😔 Doesn't work? Our bad! Please report it here.}

Read Tutorials

• 🧠 What is "Neural Search"?
• 📄 Document & DocumentArray: the basic data type in Jina.
  • Minimum working example
  • Document API
  • DocumentArray API
• ⚙️ Executor: how Jina processes Documents.
  • Minimum working example
  • Executor API
  • Executor Built-in Features
  • Use Tensorflow, Pytorch, Pytorch Lightning, Fastai, Mindspore, PaddlePaddle, Scikit-learn in Executor
• 🔀 Flow: how Jina streamlines and distributes Executors.
  • Minimum working example
  • Flow API
  • Flow-as-a-Service
• 🧼 Write clean code in Jina
• 📓 Developer References
• 😎 3 Reasons to use Jina 2.0

Support

• Join our Slack community to chat to our engineers about your use cases, questions, and support queries.
• Join our Engineering All Hands meet-up to discuss your use case and learn Jina's new features.
  • When? The second Tuesday of every month
  • Where? Zoom (see our public events calendar/.ical) and live stream on YouTube
• Subscribe to the latest video tutorials on our YouTube channel.

Join Us

Jina is backed by Jina AI. We are actively hiring full-stack developers, solution engineers to build the next neural search ecosystem in open source.

Contributing

We welcome all kinds of contributions from the open-source community, individuals and partners. We owe our success to your active involvement.

• Contributing guidelines
• Code of conduct - play nicely with the Jina community
• Good first issues
• Release cycles and development stages