Predictive AI layer for existing databases.

Overview

MindsDB

MindsDB workflow Python supported PyPi Version PyPi Downloads MindsDB Community MindsDB Website

MindsDB is an open-source AI layer for existing databases that allows you to effortlessly develop, train and deploy state-of-the-art machine learning models using SQL queries. Tweet

Predictive AI layer for existing databases
MindsDB

Try it out

Contributing

To contribute to mindsdb, please check out our Contribution guide.

Current contributors

Made with contributors-img.

Report Issues

Please help us by reporting any issues you may have while using MindsDB.

License

Comments
  • [Bug]: Exception

    [Bug]: Exception "Lightgbm mixer not supported for type: tags" when following process plant tutorial

    Is there an existing issue for this?

    • [x] I have searched the existing issues

    Current Behaviour

    I'm following the Manufacturing process quality tutorial and during training I get the error Exception: Lightgbm mixer not supported for type: tags, raised at: /opt/conda/lib/python3.7/site-packages/mindsdb/interfaces/model/learn_process.py#177.

    Expected Behaviour

    I'd expect AutoML to train the model successfully

    Steps To Reproduce

    Follow the tutorial steps until training.
    

    Anything else?

    The tutorials seem to be of mixed quality, some resulting in errors, some in low model performance or "null" predictions (for the bus ride tutorial).

    bug documentation 
    opened by philfuchs 22
  • install issues on windows 10

    install issues on windows 10

    Describe the bug When installing mindsdb, the following error message is output with the following command.

    command: pip install --requirement reqs.txt

    error message: ERROR: Could not find a version that satisfies the requirement torch>=1.0.1.post2 (from lightwood==0.6.4->-r reqs.txt (line 25)) (from versions: 0.1.2, 0.1.2.post1, 0.1.2.post2) ERROR: No matching distribution found for torch>=1.0.1.post2 (from lightwood==0.6.4->-r reqs.txt (line 25))

    Desktop (please complete the following information):

    • OS: windows 10

    Additional context I think pytorch for Windows is currently not available through PYPI, so using the commands in https://pytorch.org is a better way.

    bug 
    opened by YottaGin 22
  • Integration merlion issue2377

    Integration merlion issue2377

    1. Modify sql_query.py to support to define customized return columns and dtype of ml_handlers;
    2. [issue2377] Merlion integrated, forecaster: default, sarima, prophet, mses, detector: default, isolation forest, windstats, prophet;
    3. Corresponding test cases added, /mindsdb/tests/unit/test_merlion_handler.
    opened by rfsiten 21
  • [Bug]:  metadata-generation-failed

    [Bug]: metadata-generation-failed

    Is there an existing issue for this?

    • [X] I have searched the existing issues

    Current Behavior

    I keep on trying to pip install mindsdb. Screenshot 2022-05-10 11 13 31

    This is the message that it comes up with.

    Things tried:

    • Installing wheel
    • Upgrading pip
    • Installing sktime
    • googling/StackOverflow

    Expected Behavior

    I anticipated that I would be able to download the package.

    Steps To Reproduce

    pip install mindsdb
    

    Anything else?

    No response

    bug 
    opened by TyanBr 20
  • [Bug]: Not able to preview data due to internal server error HTTP 500

    [Bug]: Not able to preview data due to internal server error HTTP 500

    Is there an existing issue for this?

    • [X] I have searched the existing issues

    Current Behavior

    I was trying the mindsdb get started tutorial, that time i encountered HTTP 500 error, is it due to URL authorization scope not found ? or anything else. I tried googling why this happens but couldn't get a proper explanation. I can't do further steps it keeps on giving me a HTTP 500 error. Is it a common issue, coz i keep getting it on the website while running the query for the tutorial and can't preview my tables. Says that the query is not proper, i ran the exact code from tutorial. Is it is some issue from my side...anyway do help me overcome it. I really like mindsdb concept and an AI/ML enthusiast :)

    Here is the ss of what im getting while running the queries:

    Screenshot 2022-07-14 012410

    It says query with error but i am running the code from the tutorial the syntax is intact. Is there any changes to be made in the syntax?

    Expected Behavior

    I should be able to preview the home rentals data that i will train in the further steps.

    Steps To Reproduce

    Go to the mindsdb website and then start the home rentals demo tutorial. Run the demo code given in the step 1. Try to preview the data
    

    Anything else?

    nothing

    bug 
    opened by prathikshetty2002 19
  • Could not load module ModelInterface

    Could not load module ModelInterface

    hello can someone help to solve this :

    • ERROR:mindsdb-logger-f7442ec0-574d-11ea-a55e-106530eaf271:c:\users\drpbengrir\appdata\local\programs\python\python37\lib\site-packages\mindsdb\libs\controllers\transaction.py:188 - Could not load module ModelInterface
    bug 
    opened by simofilahi 18
  • FileNotFoundError: [Errno 2] No such file or directory: '/home/milia/.venvs/mindsdb/lib/python3.6/site-packages/mindsdb_storage/1_0_5/suicide_rates_light_model_metadata.pickle'

    FileNotFoundError: [Errno 2] No such file or directory: '/home/milia/.venvs/mindsdb/lib/python3.6/site-packages/mindsdb_storage/1_0_5/suicide_rates_light_model_metadata.pickle'

    Describe the bug A FileNotFoundError occurs when running the predict.py script described below.

    The full traceback is the following:

    Traceback (most recent call last):
      File "predict.py", line 12, in <module>
        result = Predictor(name='suicide_rates').predict(when={'country':'Greece','year':1981,'sex':'male','age':'35-54','population':300000})
      File "/home/milia/.venvs/mindsdb/lib/python3.6/site-packages/mindsdb/libs/controllers/predictor.py", line 472, in predict
        transaction = Transaction(session=self, light_transaction_metadata=light_transaction_metadata, heavy_transaction_metadata=heavy_transaction_metadata, breakpoint=breakpoint)
      File "/home/milia/.venvs/mindsdb/lib/python3.6/site-packages/mindsdb/libs/controllers/transaction.py", line 53, in __init__
        self.run()
      File "/home/milia/.venvs/mindsdb/lib/python3.6/site-packages/mindsdb/libs/controllers/transaction.py", line 259, in run
        self._execute_predict()
      File "/home/milia/.venvs/mindsdb/lib/python3.6/site-packages/mindsdb/libs/controllers/transaction.py", line 157, in _execute_predict
        with open(CONFIG.MINDSDB_STORAGE_PATH + '/' + self.lmd['name'] + '_light_model_metadata.pickle', 'rb') as fp:
    FileNotFoundError: [Errno 2] No such file or directory: '/home/milia/.venvs/mindsdb/lib/python3.6/site-packages/mindsdb_storage/1_0_5/suicide_rates_light_model_metadata.pickle'
    

    To Reproduce Steps to reproduce the behavior:

    1. Create a train.py script using the dataset: https://www.kaggle.com/russellyates88/suicide-rates-overview-1985-to-2016#master.csv. The train.py script is the one below:
    from mindsdb import Predictor
    
    Predictor(name='suicide_rates').learn(
        to_predict='suicides_no', # the column we want to learn to predict given all the data in the file
        from_data="master.csv" # the path to the file where we can learn from, (note: can be url)
    )
    
    1. Run the train.py script.
    2. Create and run the predict.py script:
    from mindsdb import Predictor
    
    # use the model to make predictions
    result = Predictor(name='suicide_rates').predict(when={'country':'Greece','year':1981,'sex':'male','age':'35-54','population':300000})
    
    # you can now print the results
    print(result)
    
    1. See error

    Expected behavior What was expected was to see the results.

    Desktop (please complete the following information):

    • OS: Ubuntu 18.04.2 LTS
    • mindsdb 1.0.5
    • python 3.6.7
    bug 
    opened by mlliarm 18
  • MySQL / Singlestore DB SSL support

    MySQL / Singlestore DB SSL support

    Problem I cannot connect my Singlestore DB (MySQL driver) because Mindsdb doesn't support SSL options.

    Describe the solution you'd like Full support for MySQL SSL (key, cert, ca).

    Describe alternatives you've considered No alternative is possible at the moment, security first.

    enhancement question 
    opened by pierre-b 17
  • Caching historical data for streams

    Caching historical data for streams

    I'll be using an example here and generalize whenever needed, let's say we have the following dataset we train a timeseries predictor on:

    time,gb,target,aux
    1     ,A, 7,        foo
    2     ,A, 10,      foo
    3     ,A,  12,     bar
    4     ,A,  14,     bar
    2     ,B,  5,       foo
    4     ,B,  9,       foo
    

    In this case target is what we are predicting, gb is the column we are grouping on and we are ordering by time. aux is an unrelated column that's not timeseries in nature and just used "normally".

    We train a predictor with a window of n

    Then let's say we have an input stream that looks something like this:

    time, gb, target, aux
    6,      A ,   33,     foo
    7,      A,    54,     foo
    

    Caching

    First, we will need to store, for each value of the column gb n recrods.

    So, for example, if n==1 we would save the last row in the data above, if n==2 we would save both, whem new rows come in, we un-cache the older rows`.

    Infering

    Second, when a new datapoint comes into the input stream we'll need to "infer" that the prediction we have to make is actually for the "next" datapoint. Which is to say that when: 7, A, 54, foo comes in we need to infer that we need to actually make predictions for:

    8, A, <this is what we are predicting>, foo

    The challenge here is how do we infer that the next timestamp is 8, one simple way to do this is to just subtract from the previous record, but that's an issue for the first observation (since we don't have a previous record to substract from, unless we cache part of the training data) or we could add a feature to native, to either:

    a) Provide a delta argument for each group by (representing by how much we increment the order column[s]) b) Have an argument when doing timeseries prediction that tells it to predict for the "next" row and then do the inferences under the cover.

    @paxcema let me know which of these features would be easy to implement in native, since you're now the resident timeseries expert.

    enhancement 
    opened by George3d6 16
  • Data extraction with mindsdb v.2

    Data extraction with mindsdb v.2

    This is a followup to #334, which was about the same use case and dataset, but different version of MindsDB with different errors.

    Your Environment

    Google Colab.

    • Python version: 3.6
    • Pip version: 19.3.1
    • Mindsdb version you tried to install: 2.13.8

    Describe the bug Running .learn() fails.

    [nltk_data]   Package stopwords is already up-to-date!
    
    /usr/local/lib/python3.6/dist-packages/lightwood/mixers/helpers/ranger.py:86: UserWarning: This overload of addcmul_ is deprecated:
    	addcmul_(Number value, Tensor tensor1, Tensor tensor2)
    Consider using one of the following signatures instead:
    	addcmul_(Tensor tensor1, Tensor tensor2, *, Number value) (Triggered internally at  /pytorch/torch/csrc/utils/python_arg_parser.cpp:766.)
      exp_avg_sq.mul_(beta2).addcmul_(1 - beta2, grad, grad)
    
    Downloading: 100%
    232k/232k [00:00<00:00, 1.31MB/s]
    
    
    Downloading: 100%
    442/442 [00:06<00:00, 68.0B/s]
    
    
    Downloading: 100%
    268M/268M [00:06<00:00, 43.1MB/s]
    
    
    Token indices sequence length is longer than the specified maximum sequence length for this model (606 > 512). Running this sequence through the model will result in indexing errors
    ERROR:mindsdb-logger-ac470732-3303-11eb-bbe9-0242ac1c0002---eb4b7352-566f-4a1b-aef2-c286163e1a10:/usr/local/lib/python3.6/dist-packages/mindsdb_native/libs/controllers/transaction.py:173 - Could not load module ModelInterface
    
    ERROR:mindsdb-logger-ac470732-3303-11eb-bbe9-0242ac1c0002---eb4b7352-566f-4a1b-aef2-c286163e1a10:/usr/local/lib/python3.6/dist-packages/mindsdb_native/libs/controllers/transaction.py:239 - index out of range in self
    
    ---------------------------------------------------------------------------
    
    IndexError                                Traceback (most recent call last)
    
    <ipython-input-13-a5e3bd095e46> in <module>()
          7 mdb.learn(
          8     from_data=train,
    ----> 9     to_predict='birth_year' # the column we want to learn to predict given all the data in the file
         10 )
    
    20 frames
    
    /usr/local/lib/python3.6/dist-packages/torch/nn/functional.py in embedding(input, weight, padding_idx, max_norm, norm_type, scale_grad_by_freq, sparse)
       1812         # remove once script supports set_grad_enabled
       1813         _no_grad_embedding_renorm_(weight, input, max_norm, norm_type)
    -> 1814     return torch.embedding(weight, input, padding_idx, scale_grad_by_freq, sparse)
       1815 
       1816 
    
    IndexError: index out of range in self
    

    https://colab.research.google.com/drive/1a6WRSoGK927m3eMkVdlwBhW6-3BtwaAO?usp=sharing

    To Reproduce

    1. Rerun this notebook on Google Colab https://github.com/opendataby/vybary2019/blob/e08c32ac51e181ddce166f8a4fbf968f81bd2339/canal03-parsing-with-mindsdb.ipynb
    bug 
    opened by abitrolly 15
  • Upload new Predictor

    Upload new Predictor

    Your Environment Scout The Scout upload Prediction does not function when a zip file is trying to upload.

    Errror is "Just .zip files are allowed" even though the zip file was selected. 
    
    

    Question on prediction, is there any way to upload a model of Tensorflow, or do we need to Convert TensorFlow model into the MindDB prediction model?

    bug question 
    opened by Winthan 15
  • [Bug]: TS dates not interpreted correctly

    [Bug]: TS dates not interpreted correctly

    Is there an existing issue for this?

    • [X] I have searched the existing issues

    Current Behavior

    Predictions from a timeseries model (using >LATEST) gives dates starting Dec 1st, however there are Dec dates (e.g. 6th) within the training data.

    Expected Behavior

    Predictions using ">LATEST" should start 1 day after the latest date in the training data.

    Steps To Reproduce

    CREATE MODEL mindsdb.callsdata_time
    FROM files
    (SELECT * from CallData)
    PREDICT CallsOfferedTo5
    ORDER BY DateTime
    GROUP BY PrecisionQueue
    WINDOW 8    
    HORIZON 4;
    
    
    SELECT m.DateTime as date,
      m.CallsOfferedTo5 as forecast
      FROM mindsdb.callsdata_time as m
      JOIN files.CallData as t
      WHERE t.DateTime > LATEST
      AND t.PrecisionQueue = 5000;
    
    
    
    ### Anything else?
    
    **Training data**
    [export (3) (1).csv](https://github.com/mindsdb/mindsdb/files/10335508/export.3.1.csv)
    
    **Example of dates in Dec**
    ![image](https://user-images.githubusercontent.com/34073127/210332080-d2471ece-5c3a-4a3c-942c-ea1e41a2d4cd.png)
    
    **Model output**
    ![image](https://user-images.githubusercontent.com/34073127/210332293-418f2a5a-c6d7-4bba-98a7-1effb8e1bca2.png)
    
    bug 
    opened by tomhuds 1
  • [ENH] Override dtypes - LW handler

    [ENH] Override dtypes - LW handler

    Description

    Enables support for overriding automatically inferred data types when using the Lightwood handler.

    Type of change

    (Please delete options that are not relevant)

    • [ ] 🐛 Bug fix (non-breaking change which fixes an issue)
    • [x] ⚡ New feature (non-breaking change which adds functionality)
    • [ ] 📢 Breaking change (fix or feature that would cause existing functionality to not work as expected)
    • [x] 📄 This change requires a documentation update

    What is the solution?

    If the user provides:

    CREATE ...
    USING 
    dtype_dict = {
       'col1': 'type',
        ...
    };
    

    The handler will extract this mapping and use it to build a modified problem definition, which will trigger the default encoder belonging to each new dtype (note: manually specifying encoders is out of scope for this PR and will be added at a later date).

    Checklist:

    • [x] My code follows the style guidelines(PEP 8) of MindsDB.
    • [x] I have commented my code, particularly in hard-to-understand areas.
    • [ ] I have updated the documentation, or created issues to update them.
    • [x] I fixed|updated|added unit tests and integration tests for each feature (if applicable).
    • [x] I have checked that my code additions will fail neither code linting checks nor unit test.
    • [ ] I have shared a short loom video or screenshots demonstrating any new functionality.
    opened by paxcema 0
  • updated all links

    updated all links

    Description

    Please include a summary of the change and the issue it solves.

    Fixes #4263 Fixes copied modified content of databases.mdx into its copy databases2.mdx Fixes removed https://docs.mindsdb.com from links

    Type of change

    (Please delete options that are not relevant)

    • [ ] 🐛 Bug fix (non-breaking change which fixes an issue)
    • [ ] ⚡ New feature (non-breaking change which adds functionality)
    • [ ] 📢 Breaking change (fix or feature that would cause existing functionality to not work as expected)
    • [x] 📄 Documentation update

    What is the solution?

    (Describe at a high level how the feature was implemented) As in Description.

    Checklist:

    • [ ] My code follows the style guidelines(PEP 8) of MindsDB.
    • [ ] I have commented my code, particularly in hard-to-understand areas.
    • [x] I have updated the documentation.
    • [ ] I fixed|updated|added unit tests and integration tests for each feature (if applicable).
    • [ ] I have checked that my code additions will fail neither code linting checks nor unit test.
    • [ ] I have shared a short loom video or screenshots demonstrating any new functionality.
    documentation 
    opened by martyna-mindsdb 0
  • updated links

    updated links

    Description

    Please include a summary of the change and the issue it solves.

    Fixes #4261

    Type of change

    (Please delete options that are not relevant)

    • [ ] 🐛 Bug fix (non-breaking change which fixes an issue)
    • [ ] ⚡ New feature (non-breaking change which adds functionality)
    • [ ] 📢 Breaking change (fix or feature that would cause existing functionality to not work as expected)
    • [x] 📄 Documentation update

    What is the solution?

    Updated file names in links wherever necessary.

    Checklist:

    • [ ] My code follows the style guidelines(PEP 8) of MindsDB.
    • [ ] I have commented my code, particularly in hard-to-understand areas.
    • [x] I have updated the documentation.
    • [ ] I fixed|updated|added unit tests and integration tests for each feature (if applicable).
    • [ ] I have checked that my code additions will fail neither code linting checks nor unit test.
    • [ ] I have shared a short loom video or screenshots demonstrating any new functionality.
    documentation 
    opened by martyna-mindsdb 0
  • Predictions for ranges/sets of values

    Predictions for ranges/sets of values

    Is there an existing issue for this?

    • [X] I have searched the existing issues

    Is your feature request related to a problem? Please describe.

    I'd like to retrieve a prediction filtering over a range of values rather than only individual exact values. Example: select rental_price, rental_price_explain from mindsdb.home_rentals_model where sqft between 1000 and 1200 and neighborhood in ('berkeley_hills', 'westbrae', 'downtown');

    This currently generates an error: Only 'and' and '=' operations allowed in WHERE clause, found: BetweenOperation(op='between', args=( Identifier(parts=['sqft']), Constant(value=1000), Constant(value=1200) )

    Describe the solution you'd like.

    I'd like to have the ability to use filter criteria such as "in", "between", or "or" logic to retrieve a single prediction.

    Describe an alternate solution.

    No response

    Anything else? (Additional Context)

    https://mindsdbcommunity.slack.com/archives/C01S2T35H18/p1672320517307839

    opened by rbkrejci 0
Releases(v22.12.4.3)
PyTorch code for our paper "Gated Multiple Feedback Network for Image Super-Resolution" (BMVC2019)

Gated Multiple Feedback Network for Image Super-Resolution This repository contains the PyTorch implementation for the proposed GMFN [arXiv]. The fram

Qilei Li 66 Nov 03, 2022
The Ludii general game system, developed as part of the ERC-funded Digital Ludeme Project.

The Ludii General Game System Ludii is a general game system being developed as part of the ERC-funded Digital Ludeme Project (DLP). This repository h

Digital Ludeme Project 50 Jan 04, 2023
End-to-end machine learning project for rices detection

Basmatinet Welcome to this project folks ! Whether you like it or not this project is all about riiiiice or riz in french. It is also about Deep Learn

Béranger 47 Jun 18, 2022
Satellite labelling tool for manual labelling of storm top features such as overshooting tops, above-anvil plumes, cold U/Vs, rings etc.

Satellite labelling tool About this app A tool for manual labelling of storm top features such as overshooting tops, above-anvil plumes, cold U/Vs, ri

Czech Hydrometeorological Institute - Satellite Department 10 Sep 14, 2022
Revisiting Temporal Alignment for Video Restoration

Revisiting Temporal Alignment for Video Restoration [arXiv] Kun Zhou, Wenbo Li, Liying Lu, Xiaoguang Han, Jiangbo Lu We provide our results at Google

52 Dec 25, 2022
Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance

Multiview Neural Surface Reconstruction by Disentangling Geometry and Appearance Project Page | Paper | Data This repository contains an implementatio

Lior Yariv 521 Dec 30, 2022
Public scripts, services, and configuration for running a smart home K3S network cluster

makerhouse_network Public scripts, services, and configuration for running MakerHouse's home network. This network supports: TODO features here For mo

Scott Martin 1 Jan 15, 2022
Brax is a differentiable physics engine that simulates environments made up of rigid bodies, joints, and actuators

Brax is a differentiable physics engine that simulates environments made up of rigid bodies, joints, and actuators. It's also a suite of learning algorithms to train agents to operate in these enviro

Google 1.5k Jan 02, 2023
DeOldify - A Deep Learning based project for colorizing and restoring old images (and video!)

DeOldify - A Deep Learning based project for colorizing and restoring old images (and video!)

Jason Antic 15.8k Jan 04, 2023
wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch

Generative Adversarial Notebooks Collection of my Generative Adversarial Network implementations Most codes are for python3, most notebooks works on C

tjwei 1.5k Dec 16, 2022
Implementation of Shape and Electrostatic similarity metric in deepFMPO.

DeepFMPO v3D Code accompanying the paper "On the value of using 3D-shape and electrostatic similarities in deep generative methods". The paper can be

34 Nov 28, 2022
Neural Tangent Generalization Attacks (NTGA)

Neural Tangent Generalization Attacks (NTGA) ICML 2021 Video | Paper | Quickstart | Results | Unlearnable Datasets | Competitions | Citation Overview

Chia-Hung Yuan 34 Nov 25, 2022
YOLOPのPythonでのONNX推論サンプル

YOLOP-ONNX-Video-Inference-Sample YOLOPのPythonでのONNX推論サンプルです。 ONNXモデルは、hustvl/YOLOP/weights を使用しています。 Requirement OpenCV 3.4.2 or later onnxruntime 1.

KazuhitoTakahashi 8 Sep 05, 2022
Generic image compressor for machine learning. Pytorch code for our paper "Lossy compression for lossless prediction".

Lossy Compression for Lossless Prediction Using: Training: This repostiory contains our implementation of the paper: Lossy Compression for Lossless Pr

Yann Dubois 84 Jan 02, 2023
Probabilistic-Monocular-3D-Human-Pose-Estimation-with-Normalizing-Flows

Probabilistic-Monocular-3D-Human-Pose-Estimation-with-Normalizing-Flows This is the official implementation of the ICCV 2021 Paper "Probabilistic Mono

62 Nov 23, 2022
A tensorflow=1.13 implementation of Deconvolutional Networks on Graph Data (NeurIPS 2021)

GDN A tensorflow=1.13 implementation of Deconvolutional Networks on Graph Data (NeurIPS 2021) Abstract In this paper, we consider an inverse problem i

4 Sep 13, 2022
Latex code for making neural networks diagrams

PlotNeuralNet Latex code for drawing neural networks for reports and presentation. Have a look into examples to see how they are made. Additionally, l

Haris Iqbal 18.6k Jan 01, 2023
基于PaddleClas实现垃圾分类,并转换为inference格式用PaddleHub服务端部署

百度网盘链接及提取码: 链接:https://pan.baidu.com/s/1HKpgakNx1hNlOuZJuW6T1w 提取码:wylx 一个垃圾分类项目带你玩转飞桨多个产品(1) 基于PaddleClas实现垃圾分类,导出inference模型并利用PaddleHub Serving进行服务

thomas-yanxin 22 Jul 12, 2022
Using Language Model to Bootstrap Human Activity Recognition Ambient Sensors Based in Smart Homes

Using Language Model to Bootstrap Human Activity Recognition Ambient Sensors Based in Smart Homes This repository is the official implementation of Us

Damien Bouchabou 0 Oct 18, 2021
李云龙二次元风格化!打滚卖萌,使用了animeGANv2进行了视频的风格迁移

李云龙二次元风格化!一键star、fork,你也可以生成这样的团长! 打滚卖萌求star求fork! 0.效果展示 视频效果前往B站观看效果最佳:李云龙二次元风格化: github开源repo:李云龙二次元风格化 百度AIstudio开源地址,一键fork即可运行: 李云龙二次元风格化!一键fork

oukohou 44 Dec 04, 2022