Jina banner

An easier way to build neural search on the cloud

Jina Python 3.7 3.8 3.9 PyPI Docker Image Version (latest semver) CI CD codecov

Jina is a deep learning-powered search framework for building cross-/multi-modal search systems (e.g. text, images, video, audio) on the cloud.

Time SaverThe design pattern of neural search systems, from zero to a production-ready system in minutes.

Full-Stack Ownership – Keep an end-to-end stack ownership of your solution, avoid the integration pitfalls with fragmented, multi-vendor, generic legacy tools.

Universal Search – Large-scale indexing and querying of unstructured data: video, image, long/short text, music, source code, etc.

First-Class AI Models – First-class support for state-of-the-art AI models, easily usable and extendable with a Pythonic interface.

Fast & Cloud Ready – Decentralized architecture from day one. Scalabe & cloud-native by design: enjoy containerizing, distributing, sharding, async, REST/gRPC/WebSocket.

Made with Love – Never compromise on quality, actively maintained by a passionate full-time, venture-backed team.

DocsHello WorldQuick StartLearnExamplesContributeJobsWebsiteSlack



x86/64,arm/v6,v7,v8 (Apple M1)

On Linux/macOS & Python 3.7/3.8/3.9 Docker Users
Standard pip install -U jina docker run jinaai/jina:latest
Daemon pip install -U "jina[daemon]" docker run --network=host jinaai/jina:latest-daemon
With Extras pip install -U "jina[devel]" docker run jinaai/jina:latest-devel
Dev/Pre-Release pip install --pre jina docker run jinaai/jina:master

Version identifiers are explained here. To install Jina with extra dependencies please refer to the docs. Jina can run on Windows Subsystem for Linux. We welcome the community to help us with native Windows support.

Jina “Hello, World!”


Just starting out? Try Jina’s “Hello, World” – a simple image neural search demo for Fashion-MNIST. No extra dependencies needed, simply run:

jina hello-world  # more options in --help

…or even easier for Docker users, no install required:

docker run -v "$(pwd)/j:/j" jinaai/jina hello-world --workdir /j && open j/hello-world.html
# replace "open" with "xdg-open" on Linux
Click here to see console output

hello world console output

This downloads the Fashion-MNIST training and test dataset and tells Jina to index 60,000 images from the training set. Then it randomly samples images from the test set as queries and asks Jina to retrieve relevant results. The whole process takes about 1 minute, and after running opens a webpage and shows results:

Covid-19 Chatbot

For NLP engineers, we provide a simple chatbot demo for answering Covid-19 questions. You will need PyTorch and Transformers, which can be installed along with Jina:

pip install "jina[torch,transformers]"
jina hello-world-chatbot

This downloads CovidQA dataset and tells Jina to index 418 question-answer pairs with DistilBERT. The index process takes about 1 minute on CPU. Then it opens a webpage where you can input questions and ask Jina.

Get Started


CRUD FunctionsDocumentFlow


Feed DataFetch ResultAdd LogicInter & Intra ParallelismDecentralizeAsynchronous


Customize EncoderTest EncoderParallelism & BatchingAdd Data IndexerCompose Flow from YAMLSearchEvaluationREST Interface


CRUD Functions

First we look at basic CRUD operations. In Jina, CRUD corresponds to four functions: index (create), search (read), update, and delete. With Documents below as an example:

import numpy as np
from jina import Document
docs = [Document(id='?', embedding=np.array([0, 0]), tags={'guardian': 'Azure Dragon', 'position': 'East'}),
        Document(id='?', embedding=np.array([1, 0]), tags={'guardian': 'Vermilion Bird', 'position': 'South'}),
        Document(id='?', embedding=np.array([0, 1]), tags={'guardian': 'Black Tortoise', 'position': 'North'}),
        Document(id='?', embedding=np.array([1, 1]), tags={'guardian': 'White Tiger', 'position': 'West'})]

Let’s build a Flow with a simple indexer:

from jina import Flow
f = Flow().add(uses='_index')

Document and Flow are basic concepts in Jina, which will be explained later. _index is a built-in embedding + structured storage that one can use out of the box.

# save four docs (both embedding and structured info) into storage
with f:
    f.index(docs, on_done=print)
# retrieve top-3 neighbours of ?, this print ??? with score 0, 1, 1 respectively
with f:
    f.search(docs[0], top_k=3, on_done=lambda x: print(x.docs[0].matches))

{"id": "?", "tags": {"guardian": "Azure Dragon", "position": "East"}, "embedding": {"dense": {"buffer": "AAAAAAAAAAAAAAAAAAAAAA==", "shape": [2], "dtype": "<i8"}}, "score": {"opName": "NumpyIndexer", "refId": "?"}, "adjacency": 1}
{"id": "?", "tags": {"position": "South", "guardian": "Vermilion Bird"}, "embedding": {"dense": {"buffer": "AQAAAAAAAAAAAAAAAAAAAA==", "shape": [2], "dtype": "<i8"}}, "score": {"value": 1.0, "opName": "NumpyIndexer", "refId": "?"}, "adjacency": 1}
{"id": "?", "tags": {"guardian": "Black Tortoise", "position": "North"}, "embedding": {"dense": {"buffer": "AAAAAAAAAAABAAAAAAAAAA==", "shape": [2], "dtype": "<i8"}}, "score": {"value": 1.0, "opName": "NumpyIndexer", "refId": "?"}, "adjacency": 1}

# update ? embedding in the storage
docs[0].embedding = np.array([1, 1])
with f:
# remove ?? Documents from the storage
with f:
    f.delete(['?', '?'])


Document is Jina’s primitive data type. It can contain text, image, array, embedding, URI, and accompanied by rich meta information. To construct a Document, one can use:

import numpy
from jina import Document

doc1 = Document(content=text_from_file, mime_type='text/x-python')  # a text document contains python code
doc2 = Document(content=numpy.random.random([10, 10]))  # a ndarray document

Document can be recurred both vertically and horizontally to have nested documents and matched documents. To better see the recursive structure of a document, one can use .plot() function. If you are using JupyterLab/Notebook, all Document objects will be auto-rendered.

import numpy
from jina import Document

d0 = Document(id='?', embedding=np.array([0, 0]))
d1 = Document(id='?', embedding=np.array([1, 0]))
d2 = Document(id='?', embedding=np.array([0, 1]))
d3 = Document(id='?', embedding=np.array([1, 1]))


d0.plot()  # simply `d0` on JupyterLab
Click here to see more about MultimodalDocument


A MultimodalDocument is a document composed of multiple Document from different modalities (e.g. text, image, audio).

Jina provides multiple ways to build a multimodal Document. For example, one can provide the modality names and the content in a dict:

from jina import MultimodalDocument
document = MultimodalDocument(modality_content_map={
    'title': 'my holiday picture',
    'description': 'the family having fun on the beach',
    'image': PIL.Image.open('path/to/image.jpg')

One can also compose a MultimodalDocument from multiple Document directly:

from jina.types import Document, MultimodalDocument

doc_title = Document(content='my holiday picture', modality='title')
doc_desc = Document(content='the family having fun on the beach', modality='description')
doc_img = Document(content=PIL.Image.open('path/to/image.jpg'), modality='image')
doc_img.tags['date'] = '10/08/2019'

document = MultimodalDocument(chunks=[doc_title, doc_description, doc_img])

Fusion Embeddings from Different Modalities

To extract fusion embeddings from different modalities Jina provides BaseMultiModalEncoder abstract class, which has a unqiue encode interface.

def encode(self, *data: 'numpy.ndarray', **kwargs) -> 'numpy.ndarray':

MultimodalDriver provides data to the MultimodalDocument in the correct expected order. In this example below, image embedding is passed to the endoder as the first argument, and text as the second.

  positional_modality: ['image', 'text']
    [IndexRequest, SearchRequest]:
      - !MultiModalDriver {}

Interested readers can refer to jina-ai/example: how to build a multimodal search engine for image retrieval using TIRG (Composing Text and Image for Image Retrieval) for the usage of MultimodalDriver and BaseMultiModalEncoder in practice.


Jina provides a high-level Flow API to simplify building CRUD workflows. To create a new Flow:

from jina import Flow
f = Flow().add()

This creates a simple Flow with one Pod. You can chain multiple .add()s in a single Flow.

To visualize the Flow, simply chain it with .plot('my-flow.svg'). If you are using a Jupyter notebook, the Flow object will be displayed inline without plot.

Gateway is the entrypoint of the Flow.

Get the vibe? Now we are talking! Let’s learn more about the basic concepts and features in Jina.


CRUD FunctionsDocumentFlow


Feed DataFetch ResultAdd LogicInter & Intra ParallelismDecentralizeAsynchronous


Customize EncoderTest EncoderParallelism & BatchingAdd Data IndexerCompose Flow from YAMLSearchEvaluationREST Interface


Feed Data

To use a Flow, open it via with context manager, like you would open a file in Python. Now let’s create some empty document and index it:

from jina import Document

with Flow().add() as f:
    f.index((Document() for _ in range(10)))

Flow supports CRUD operations: index, search, update, delete. Besides, it also provides sugary syntax on ndarray, csv, ndjson and arbitrary files.

Input Example on index/search Explain

with f:

Input four Document, each document.blob is a ndarray([2])


with f, open('index.csv') as fp:
  f.index_csv(fp1, field_resolver={'pic_url': 'uri'})

Each line in the index.csv is constructed as Document, CSV’s field pic_url is mapped to document.uri.

JSON Lines/ndjson/LDJSON

with f, open('index.ndjson') as fp:
  f.index_ndjson(fp1, field_resolver={'question_id': 'id'})

Each line in index.ndjson is constructed as Document, JSON’s field question_id is mapped to document.id.

Files with wildcard

with f:
  f.index_files(['/tmp/*.mp4', '/tmp/*.pdf'])

Each file captured is constructed as a Document, whose content (text, blob, buffer) is auto-guessed & filled.

Fetch Result

Once a request is done, callback functions are fired. Jina Flow implements Promise-like interface, you can add callback functions on_done, on_error, on_always to hook different events. In the example below, our Flow passes the message then prints the result when successful. If something wrong, it beeps. Finally, the result is written to output.txt.

def beep(*args):
    # make a beep sound
    import os
    os.system('echo -n "\a";')

with Flow().add() as f, open('output.txt', 'w') as fp:
    f.index(numpy.random.random([4, 5, 2]),
            on_done=print, on_error=beep, on_always=lambda x: fp.write(x.json()))

Add Logic

To add logic to the Flow, use the uses parameter to attach a Pod with an Executor. uses accepts multiple value types including class name, Docker image, (inline) YAML or built-in shortcut.

f = (Flow().add(uses='MyBertEncoder')  # class name of a Jina Executor
           .add(uses='docker://jinahub/pod.encoder.dummy_mwu_encoder:0.0.6-0.9.3')  # the image name
           .add(uses='myencoder.yml')  # YAML serialization of a Jina Executor
           .add(uses='!WaveletTransformer | {freq: 20}')  # inline YAML config
           .add(uses='_pass')  # built-in shortcut executor
           .add(uses={'__cls': 'MyBertEncoder', 'with': {'param': 1.23}}))  # dict config object with __cls keyword

The power of Jina lies in its decentralized architecture: each add creates a new Pod, and these Pods can be run as a local thread/process, a remote process, inside a Docker container, or even inside a remote Docker container.

Inter & Intra Parallelism

Chaining .add()s creates a sequential Flow. For parallelism, use the needs parameter:

f = (Flow().add(name='p1', needs='gateway')
           .add(name='p2', needs='gateway')
           .add(name='p3', needs='gateway')
           .needs(['p1','p2', 'p3'], name='r1').plot())

p1, p2, p3 now subscribe to Gateway and conduct their work in parallel. The last .needs() blocks all Pods until they finish their work. Note: parallelism can also be performed inside a Pod using parallel:

f = (Flow().add(name='p1', needs='gateway')
           .add(name='p2', needs='gateway')
           .add(name='p3', parallel=3)
           .needs(['p1','p3'], name='r1').plot())

Decentralized Flow

A Flow does not have to be local-only, one can put any Pod to remote(s). In the example below, with the host keyword gpu-pod is put to a remote machine for parallelization, whereas other pods stay local. Extra file dependencies that need to be uploaded are specified via the upload_files keyword.

# have docker installed
docker run --name=jinad --network=host -v /var/run/docker.sock:/var/run/docker.sock jinaai/jina:latest-daemon --port-expose 8000
# to stop it
docker rm -f jinad
import numpy as np
from jina import Flow

f = (Flow()

with f:
    f.index_ndarray(np.random.random([10, 100]), output=print)

We provide a demo server on cloud.jina.ai:8000, give the following snippet a try!

from jina import Flow

with Flow().add().add(host='cloud.jina.ai:8000') as f:
    f.index(['hello', 'world'])

Asynchronous Flow

Synchronous from outside, Jina runs asynchronously underneath: it manages the eventloop(s) for scheduling the jobs. If the user wants more control over the eventloop, then AsyncFlow comes to use.

Unlike Flow, the CRUD of AsyncFlow accepts input & output functions as async generator. This is useful when your data sources involve other asynchronous libraries (e.g. motor for MongoDB):

from jina import AsyncFlow

async def input_fn():
    for _ in range(10):
        yield Document()
        await asyncio.sleep(0.1)

with AsyncFlow().add() as f:
    async for resp in f.index(input_fn):

AsyncFlow is particular useful when Jina is using as part of the integration, where another heavy-lifting job is running concurrently:

async def run_async_flow_5s():  # WaitDriver pause 5s makes total roundtrip ~5s
    with AsyncFlow().add(uses='- !WaitDriver {}') as f:
        async for resp in f.index_ndarray(numpy.random.random([5, 4])):

async def heavylifting():  # total roundtrip takes ~5s
    print('heavylifting other io-bound jobs, e.g. download, upload, file io')
    await asyncio.sleep(5)
    print('heavylifting done after 5s')

async def concurrent_main():  # about 5s; but some dispatch cost, can't be just 5s, usually at <7s
    await asyncio.gather(run_async_flow_5s(), heavylifting())

if __name__ == '__main__':

AsyncFlow is very useful when using Jina inside the Jupyter Notebook. As Jupyter/ipython already manages an eventloop and thanks to autoawait, AsyncFlow can run out-of-the-box in Jupyter.

That’s all you need to know for understanding the magic behind hello-world. Now let’s dive into it!


CRUD FunctionsDocumentFlow


Feed DataFetch ResultAdd LogicInter & Intra ParallelismDecentralizeAsynchronous


Customize EncoderTest EncoderParallelism & BatchingAdd Data IndexerCompose Flow from YAMLSearchEvaluationREST Interface

Breakdown of hello-world

Customize Encoder

Let’s first build a naive image encoder that embeds images into vectors using an orthogonal projection. To do this, we simply inherit from BaseImageEncoder: a base class from the jina.executors.encoders module. We then override its __init__() and encode() methods.

import numpy as np
from jina.executors.encoders import BaseImageEncoder

class MyEncoder(BaseImageEncoder):

    def __init__(self, *args, **kwargs):
        super().__init__(*args, **kwargs)
        H = np.random.rand(784, 64)
        u, s, vh = np.linalg.svd(H, full_matrices=False)
        self.oth_mat = u @ vh

    def encode(self, data: 'np.ndarray', *args, **kwargs):
        return (data.reshape([-1, 784]) / 255) @ self.oth_mat

Jina provides a family of Executor classes, which summarize frequently-used algorithmic components in neural search. This family consists of encoders, indexers, crafters, evaluators, and classifiers, each with a well-designed interface. You can find the list of all 107 built-in executors here. If they don’t meet your needs, inheriting from one of them is the easiest way to bootstrap your own Executor. Simply use our Jina Hub CLI:

pip install jina[hub] && jina hub new

Test Encoder in Flow

Let’s test our encoder in the Flow with some synthetic data:

def validate(req):
    assert len(req.docs) == 100
    assert NdArray(req.docs[0].embedding).value.shape == (64,)

f = Flow().add(uses='MyEncoder')

with f:
    f.index_ndarray(numpy.random.random([100, 28, 28]), on_done=validate)

All good! Now our validate function confirms that all one hundred 28×28 synthetic images have been embedded into 100×64 vectors.

Parallelism & Batching

By setting a larger input, you can play with batch_size and parallel:

f = Flow().add(uses='MyEncoder', parallel=10)

with f:
    f.index_ndarray(numpy.random.random([60000, 28, 28]), batch_size=1024)

Add Data Indexer

Now we need to add an indexer to store all the embeddings and the image for later retrieval. Jina provides a simple numpy-powered vector indexer NumpyIndexer, and a key-value indexer BinaryPbIndexer. We can combine them in a single YAML file:

  - !NumpyIndexer
      index_filename: vec.gz
  - !BinaryPbIndexer
      index_filename: chunk.gz
  workspace: ./
  • ! tags a structure with a class name
  • with defines arguments for initializing this class object.

Essentially, the above YAML config is equivalent to the following Python code:

from jina.executors.indexers.vector import NumpyIndexer
from jina.executors.indexers.keyvalue import BinaryPbIndexer
from jina.executors.indexers import CompoundIndexer

a = NumpyIndexer(index_filename='vec.gz')
b = BinaryPbIndexer(index_filename='vec.gz')
c = CompoundIndexer()
c.components = lambda: [a, b]

Compose Flow from YAML

Now let’s add our indexer YAML file to the Flow with .add(uses=). Let’s also add two shards to the indexer to improve its scalability:

f = Flow().add(uses='MyEncoder', parallel=2).add(uses='myindexer.yml', shards=2).plot()

When you have many arguments, constructing a Flow in Python can get cumbersome. In that case, you can simply move all arguments into one flow.yml:

version: '1.0'
  - name: encode
    uses: MyEncoder
    parallel: 2
  - name:index
    uses: myindexer.yml
    shards: 2

And then load it in Python:

f = Flow.load_config('flow.yml')


Querying a Flow is similar to what we did with indexing. Simply load the query Flow and switch from f.index to f.search. Say you want to retrieve the top 50 documents that are similar to your query and then plot them in HTML:

f = Flow.load_config('flows/query.yml')
with f:
    f.search_ndarray(numpy.random.random([10, 28, 28]), shuffle=True, on_done=plot_in_html, top_k=50)


To compute precision recall on the retrieved result, you can add _eval_pr, a built-in evaluator for computing precision & recall.

f = (Flow().add(...)

You can construct an iterator of query and groundtruth pairs and feed to the flow f, via:

from jina import Document

def query_generator():
    for _ in range(10):
        q = Document()
        # now construct expect matches as groundtruth
        gt = Document(q, copy=True)  # make sure 'gt' is identical to 'q'
        yield q, gt

f.search(query_iterator, ...)

REST Interface

In practice, the query Flow and the client (i.e. data sender) are often physically separated. Moreover, the client may prefer to use a REST API rather than gRPC when querying. You can set port_expose to a public port and turn on REST support with restful=True:

f = Flow(port_expose=45678, restful=True)

with f:

That is the essence behind jina hello-world. It is merely a taste of what Jina can do. We’re really excited to see what you do with Jina! You can easily create a Jina project from templates with one terminal command:

pip install jina[hub] && jina hub new --type app

This creates a Python entrypoint, YAML configs and a Dockerfile. You can start from there.


Jina 101 Concept Illustration Book, Copyright by Jina AI Limited   

Jina 101: First Things to Learn About Jina

  English日本語FrançaisPortuguêsDeutschРусский язык中文عربية

Examples (View all)

Example code to build your own projects


Semantic Wikipedia Search with Transformers and DistilBERT

Brand new to neural search? See a simple text-search example to understand how Jina works


Add Incremental Indexing to Wikipedia Search

Index more effectively by adding incremental indexing to your Wikipedia search


Build a NLP Semantic Search System with Transformers

Upgrade from plain search to sentence search and practice your Flows and Pods by searching sentences from Wikipedia


Search Lyrics with Transformers and PyTorch

Get a better understanding of chunks by searching a lyrics database. Now with shiny front-end!


Google’s Big Transfer Model in (Poké-)Production

Use SOTA visual representation for searching Pokémon!


Search YouTube audio data with Vggish

A demo of neural search for audio data based Vggish model.


Search Tumblr GIFs with KerasEncoder

Use prefetching and sharding to improve the performance of your index and query flow when searching animated GIFs.

Please check our examples repo for advanced and community-submitted examples.

Want to read more? Check our Founder Han Xiao’s blog and our official blog.


Apart from the learning resources we provided above, We highly recommended you go through our documentation to master Jina.

Our docs are built on every push, merge, and release of Jina’s master branch. Documentation for older versions is archived here.

Are you a “Doc”-star? Join us! We welcome all kinds of improvements on the documentation.


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


All Contributors


  • Code of conduct – play nicely with the Jina community
  • Slack workspace – join #general on our Slack to meet the team and ask questions
  • YouTube channel – subscribe to the latest video tutorials, release demos, webinars and presentations.
  • LinkedIn – get to know Jina AI as a company and find job opportunities
  • Twitter Follow – follow and interact with us using hashtag #JinaSearch
  • Company – know more about our company and how we are fully committed to open-source.

Open Governance

As part of our open governance model, we host Jina’s Engineering All Hands in public. This Zoom meeting recurs monthly on the second Tuesday of each month, at 14:00-15:30 (CET). Everyone can join in via the following calendar invite.

The meeting will also be live-streamed and later published to our YouTube channel.

Join Us

Jina is an open-source project. We are hiring full-stack developers, evangelists, and PMs to build the next neural search ecosystem in open source.


Copyright (c) 2020-2021 Jina AI Limited. All rights reserved.

Jina is licensed under the Apache License, Version 2.0. See LICENSE for the full license text.


GitHub - jina-ai/jina: Cloud-native neural search framework for ??? kind of data
Cloud-native neural search framework for ??? kind of data - GitHub - jina-ai/jina: Cloud-native neural search framework for ??? kind of data