Cloud-Native Neural Search[?] Framework for Any Kind of Data
Jina๐
allows you to build deep learning-powered search-as-a-service in just minutes.
๐ All data type - Large-scale indexing and querying of any kind of unstructured data: video, image, long/short text, music, source code, PDF, etc.
๐ฉ๏ธ Fast & cloud-native - Distributed architecture from day one, scalable & cloud-native by design: enjoy containerizing, streaming, paralleling, sharding, async scheduling, HTTP/gRPC/WebSocket protocol.
โฑ๏ธ Save time - The design pattern of neural search systems, from zero to a production-ready system in minutes.
๐ฑ Own your stack - Keep an end-to-end stack ownership of your solution, avoid integration pitfalls with fragmented, multi-vendor, generic legacy tools.
- ๐ Fashion image search:
jina hello fashion
- ๐ค QA chatbot:
pip install "jina[chatbot]" && jina hello chatbot
- ๐ฐ Multimodal search:
pip install "jina[multimodal]" && jina hello multimodal
- ๐ด Fork the source of a demo to your folder:
jina hello fork fashion ../my-proj/
- via PyPI:
pip install -U "jina[standard]"
- via Docker:
docker run jinaai/jina:latest
More installation options
x86/64,arm64,v6,v7 | On Linux/macOS & Python 3.7/3.8/3.9 | Docker Users |
---|---|---|
Minimum (no HTTP, WebSocket, Docker support) |
pip install jina |
docker run jinaai/jina:latest |
Daemon | pip install "jina[daemon]" |
docker run --network=host jinaai/jina:latest-daemon |
With Extras | pip install "jina[devel]" |
docker run jinaai/jina:latest-devel |
Version identifiers are explained here. Jina can run on Windows Subsystem for Linux. We welcome the community to help us with native Windows support.
Document, Executor, and Flow are the three fundamental concepts in Jina.
- ๐ Document is the basic data type in Jina;
- โ๏ธ Executor is how Jina processes Documents;
- ๐ Flow is how Jina streamlines and distributes Executors.
1๏ธโฃ Copy-paste the minimum example below and run it:
๐ก 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, scores={'euclid': d}) for idx, d in enumerate(dist)]
query.matches.sort(key=lambda m: m.scores['euclid'].value) # sort matches by their values
f = Flow(port_expose=12345, protocol='http').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
2๏ธโฃ Open http://localhost:12345/docs
(an extended Swagger UI) in your browser, click /search tab and input:
{"data": [{"text": "@requests(on=something)"}]}
That means, we want to find lines from the above code snippet that are most similar to @request(on=something)
. Now click Execute button!
3๏ธโฃ Not a GUI guy? Let's do it in Python then! Keep the above server running and start a simple client:
from jina import Client, Document
from jina.types.request import Response
def print_matches(resp: Response): # the callback function invoked when task is done
for idx, d in enumerate(resp.docs[0].matches[:3]): # print top-3 matches
print(f'[{idx}]{d.scores["euclid"].value:2f}: "{d.text}"')
c = Client(protocol='http', port_expose=12345) # connect to localhost:12345
c.post('/search', Document(text='request(on=something)'), on_done=print_matches)
, which prints the following results:
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)]"
๐ Doesn't work? Our bad! Please report it here.
- ๐ง What is "Neural Search"?
- ๐
Document
&DocumentArray
: the basic data type in Jina. - โ๏ธ
Executor
: how Jina processes Documents. - ๐
Flow
: how Jina streamlines and distributes Executors. - ๐คน Serving Jina
- ๐ Developer References
- ๐งผ Clean & Efficient Coding in Jina
- ๐ 3 Reasons to Use Jina 2.0
- 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.
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.
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