Python库 | jina-2.0.0rc11.dev4.tar.gz

<p align="center"> <img src="https://github.com/jina-ai/jina/blob/master/.github/logo-only.gif?raw=true" alt="Jina banner" width="200px"> </p> <p align="center"> <b>Cloud-Native <ins>Neural Search</ins>^{<a href=".github/2.0/neural-search.md">[?]</a>} Framework for <i>Any</i> Kind of Data</b> </p> <p align=center> <a href="https://pypi.org/project/jina/"><img src="https://github.com/jina-ai/jina/blob/master/.github/badges/python-badge.svg?raw=true" alt="Python 3.7 3.8 3.9" title="Jina supports Python 3.7 and above"></a> <a href="https://hub.docker.com/r/jinaai/jina/tags"><img src="https://img.shields.io/docker/v/jinaai/jina?color=%23099cec&amp;label=Docker&amp;logo=docker&amp;logoColor=white&amp;sort=semver" alt="Docker Image Version (latest semver)"></a> <a href="https://pepy.tech/project/jina"><img src="https://pepy.tech/badge/jina/month"></a> <a href="https://codecov.io/gh/jina-ai/jina"><img src="https://codecov.io/gh/jina-ai/jina/branch/master/graph/badge.svg" alt="codecov"></a> <a href="https://slack.jina.ai"><img src="https://img.shields.io/badge/Slack-600%2B-blueviolet?logo=slack&amp;logoColor=white"></a> </p> <!-- start elevator-pitch --> Jina^{<a href=".github/pronounce-jina.mp3">`🔊`</a>} allows you to build deep learning-powered search-as-a-service in just minutes. <!-- end elevator-pitch --> 🌌 **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](./.github/pages/hello-world.md#-fashion-image-search): `pip install --pre && jina hello fashion` - [🤖 QA chatbot](./.github/pages/hello-world.md#-covid-19-chatbot): `pip install --pre "jina[chatbot]" && jina hello chatbot` - [📰 Multimodal search](./.github/pages/hello-world.md#-multimodal-document-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. ```console $ pip install --pre jina $ jina -v 2.0.0rcN ``` #### via Docker ```console $ docker run jinaai/jina:master -v 2.0.0rcN ``` <details> <summary>📦 More installation options</summary> | <br>_{^{x86/64,arm64,v6,v7,Apple M1}} | On Linux/macOS & Python 3.7/3.8/3.9 | Docker Users| | --- | --- | --- | | Standard | `pip install --pre jina` | `docker run jinaai/jina:master` | | _{<a href="https://api.jina.ai/daemon/">Daemon</a>} | _{`pip install --pre "jina[daemon]"`} | _{`docker run --network=host jinaai/jina:master-daemon`} | | _{With Extras} | _{`pip install --pre "jina[devel]"`} | _{`docker run jinaai/jina:master-devel`} | Version identifiers [are explained here](https://github.com/jina-ai/jina/blob/master/RELEASE.md). Jina can run on [Windows Subsystem for Linux](https://docs.microsoft.com/en-us/windows/wsl/install-win10). We welcome the community to help us with [native Windows support](https://github.com/jina-ai/jina/issues/1252). </details> ## Get Started Document, Executor, and Flow are the three fundamental concepts in Jina. - [📄 **Document**](.github/2.0/cookbooks/Document.md) is the basic data type in Jina; - [⚙️ **Executor**](.github/2.0/cookbooks/Executor.md) is how Jina processes Documents; - [🔀 **Flow**](.github/2.0/cookbooks/Flow.md) is how Jina streamlines and distributes Executors. <a href="https://colab.research.google.com/github/jina-ai/jupyter-notebooks/blob/main/2.0-readme-38l.ipynb"><img align="right" src="https://colab.research.google.com/assets/colab-badge.svg?raw=true"/></a> Copy-paste the minimum example below and run it: ^{💡 Preliminaries: <a href="https://en.wikipedia.org/wiki/Word_embedding">character embedding</a>, <a href="https://computersciencewiki.org/index.php/Max-pooling_/_Pooling">pooling</a>, <a href="https://en.wikipedia.org/wiki/Euclidean_distance">Euclidean distance</a>} <img src="https://github.com/jina-ai/jina/blob/master/.github/2.0/simple-arch.svg" alt="Get started system diagram"> ```python 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).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: ```python 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(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: ```text 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! <a href="https://github.com/jina-ai/jina/issues/new?assignees=&labels=kind%2Fbug&template=---found-a-bug-and-i-solved-it.md&title=">Please report it here.</a>} ## Read Tutorials - 🧠 [What is "Neural Search"?](.github/2.0/neural-search.md) - 📄 `Document` & `DocumentArray`: the basic data type in Jina. - [Minimum Working Example](.github/2.0/cookbooks/Document.md#minimum-working-example) - [`Document` API](.github/2.0/cookbooks/Document.md#document-api) - [`DocumentArray` API](.github/2.0/cookbooks/Document.md#documentar