Compare commits

...

69 Commits

Author SHA1 Message Date
allegroai
712efa208b version bump 2020-07-06 21:09:21 +03:00
allegroai
09b6b6a9de Fix non-root docker image usage
Fix broken trains-agent build
Improve support for dockers with preinstalled conda env
Improve trains-agent-docker spinning
2020-07-06 21:09:11 +03:00
allegroai
98ff9a50e6 Changed agent.docker_init_bash_script default value in comment 2020-07-06 21:05:55 +03:00
allegroai
1f4d358316 Changed default docker image from nvidia/cuda to "nvidia/cuda:10.1-runtime-ubuntu18.04" to support cudnn frameworks (TF) 2020-07-02 01:35:57 +03:00
allegroai
f693fa165c Fix .git-credentials and .gitconfig mapping into docker
Add agent.docker_init_bash_script allow finer control over docker startup script
2020-07-02 01:33:13 +03:00
allegroai
c43084825c Version bump to v0.15.1 2020-06-21 23:23:44 +03:00
allegroai
f1abee91dd Add FORCE_LOCAL_TRAINS_AGENT_WHEEL to force the install of local trains agent wheel into the docker image 2020-06-21 23:23:26 +03:00
allegroai
c6b04edc34 version bump 2020-06-18 01:55:30 +03:00
allegroai
50b847f4f7 Add trains-agent dockerfile 2020-06-18 01:55:24 +03:00
allegroai
1f53a06299 Add agent.force_git_ssh_protocol option to force all git links to ssh:// (issue #16)
Add git user/pass credentials for pip git packages (git+http and  git+ssh) (issue #22)
2020-06-18 01:55:14 +03:00
allegroai
257dd95401 Add warning on --gpus without detected CUDA version (see issue #24) 2020-06-18 01:52:58 +03:00
allegroai
1736d205bb Documentation 2020-06-18 00:31:44 +03:00
allegroai
6fef58df6c embed jsonmodels 2.4 into trains-agent 2020-06-18 00:30:40 +03:00
allegroai
473a8de8bb Fix trains-agent init (max two verification retries, then print error) 2020-06-11 15:39:38 +03:00
Allegro AI
ff6272f48f Merge pull request #23 from H4dr1en/patch-1
remove six and pathlib2 dependencies from setup.py
2020-06-05 19:20:09 +03:00
H4dr1en
1b5bcebd10 remove six and pathlib2 dependencies from setup.py 2020-06-05 18:01:35 +02:00
Allegro AI
c4344d3afd Update README.md 2020-06-02 01:02:34 +03:00
Allegro AI
45a44b087a Update README.md 2020-06-02 00:58:52 +03:00
allegroai
c58ffdb9f8 Version bump to v0.15.0 2020-06-01 19:56:59 +03:00
allegroai
54d9d77294 Allow services mode to re-register (docker can kill it and not exit gracefully) 2020-06-01 16:34:33 +03:00
allegroai
ce02385420 Fix services mode abort docker while installing, detect docker crash 2020-06-01 16:33:47 +03:00
allegroai
87ffd95eaa Upgrade default pip version to <20.2 2020-06-01 16:33:00 +03:00
allegroai
522dd85d7b Fix docker build with no --entry-point to use bash as an entrypoint 2020-06-01 11:05:06 +03:00
allegroai
3651c85fcd Fix print if no repo (standalone script) 2020-05-31 14:03:31 +03:00
allegroai
566427d550 Fix build failing due to missing session 2020-05-31 14:02:42 +03:00
allegroai
cc99077c92 Do not monitor GPU when running with --cpu-only 2020-05-31 14:01:14 +03:00
allegroai
5f112447f7 CUDA_VISIBLE_DEVICES should not be set to "all" 2020-05-31 14:00:51 +03:00
allegroai
22c5f043aa Fix detached mode to correctly use cache folder slots 2020-05-31 14:00:14 +03:00
allegroai
860ff8911c Fix status message check containing "worker" (deprecated test) 2020-05-31 13:58:39 +03:00
allegroai
799b292146 Support running code from module (i.e. '-m' in execution entry point) 2020-05-31 13:54:13 +03:00
allegroai
fffe8e1c3f Fix init wizard, correctly display the input servers 2020-05-31 13:53:34 +03:00
allegroai
8245293f7f Fix request endpoint constant version numbers 2020-05-31 13:52:53 +03:00
allegroai
6563ce70c8 Update README 2020-05-09 20:12:53 +03:00
allegroai
829b1d8f15 Use deep copy to clone configuration, always write configuration before launching a docker 2020-05-09 20:12:29 +03:00
allegroai
f6be64a4b5 Print conda install output if running in debug mode, turn on debugging if --debug flag is used 2020-05-09 20:11:01 +03:00
allegroai
21f6a73f66 Include CUDA version in the pytorch package fail error 2020-05-09 20:09:18 +03:00
allegroai
77c4c79a2f Support pip 20.1 local/http package reference in pip freeze 2020-05-09 20:08:17 +03:00
allegroai
2ad929fa00 Add torch_nightly flag support (if torch wheel is not found on stable try the nightly builds), improve support for torch in freeze (add actually used HTTP link as comment to the original package) 2020-05-09 20:08:05 +03:00
allegroai
53f511f536 Improve docker host-mount support, use TRAINS_AGENT_DOCKER_HOST_MOUNT env var 2020-05-09 20:02:46 +03:00
allegroai
7c87797a40 Pass git credentials to dockerized task execution 2020-05-09 19:59:58 +03:00
allegroai
272fa07c29 Fix and enhance "build --docker"
- Fix standalone docker execution
- Add --install-globally option to install required packages in the docker's system python
- Add --entry-point option to allow automatic task cloning when running the docker
2020-05-09 19:57:25 +03:00
allegroai
6ce9cf7c2a Fix version control links in requirements when using conda 2020-05-09 19:52:51 +03:00
allegroai
abb30ac2b8 Move --gpus and --cpu-only to worker args (used by daemon, execute and build) 2020-05-09 19:51:45 +03:00
allegroai
5bb257c46c Add daemon --create-queue to automatically create a queue and use it if queue name doesn't exist in server 2020-05-09 19:50:53 +03:00
allegroai
c65b28ed92 Update venv_update URL 2020-05-09 19:47:00 +03:00
allegroai
fce8eb6782 Add OS environment configuration for git user/pass using TRAINS_AGENT_GIT_USER/TRAINS_AGENT_GIT_PASS 2020-05-09 19:46:46 +03:00
allegroai
9cb71b9526 Add daemon service mode to allow multiple tasks to be launched simultaneously on the same machine (--service-mode) 2020-05-09 19:45:14 +03:00
allegroai
38e02ca5cd Add worker command state enforcement conforming and verification callback 2020-05-09 19:42:51 +03:00
allegroai
06bfea80bc Fix read file scope 2020-04-09 11:27:04 +03:00
allegroai
e660c7f2be Fix comments in config files 2020-04-09 11:23:45 +03:00
allegroai
fc28467080 Improve error message when failing to locate a task 2020-04-09 11:23:13 +03:00
allegroai
8d47905982 Show host information when failing to obtain a task 2020-04-01 19:12:45 +03:00
allegroai
a6a0b01f71 Remove deprecated OS environment variables 2020-04-01 19:11:37 +03:00
allegroai
2b561f6066 Version bump to v0.14.1 2020-03-24 20:37:18 +02:00
allegroai
61232d05dd Fix run as user support in Windows and add fall-back for created user folders 2020-03-22 19:16:11 +02:00
allegroai
b3418e4496 Add daemon detached mode (--detached, -d) that runs agent in the background and returns immediately 2020-03-22 19:00:29 +02:00
allegroai
5ef627165c Fix PyTorch support to ignore minor versions when looking for package to install or to download 2020-03-20 10:48:48 +02:00
allegroai
98a983d9a2 Add TRAINS_AGENT_EXTRA_PYTHON_PATH to allow adding additional python path for task execution (helpful when using extra untracked modules) 2020-03-20 10:46:56 +02:00
allegroai
482007c4ce Fix run as user feature (TRAINS_AGENT_EXEC_USER) 2020-03-20 10:42:32 +02:00
allegroai
98198b8006 Auto mount ~/.git-credentials into docker container if file exists 2020-03-20 10:39:59 +02:00
allegroai
94bb11a81a Change message when using local torch 2020-03-20 10:37:42 +02:00
allegroai
4158d08f6f Fix test 2020-03-20 10:36:20 +02:00
allegroai
58ab67ea31 Fix execution output handling 2020-03-20 10:35:25 +02:00
allegroai
ea0ed4807e Version bump to v0.14.0 2020-03-12 19:42:32 +02:00
allegroai
389600b91e Fix git checkout with submodules 2020-03-12 18:39:47 +02:00
allegroai
5fb2550212 Update to backend API v2.5 2020-03-12 18:39:10 +02:00
allegroai
15e9e6b778 Fix "execute --clone" support 2020-03-12 18:38:35 +02:00
allegroai
aa75b92e46 Prefer docker image from command line over the one in the experiment 2020-03-12 18:35:49 +02:00
allegroai
757210d5b3 Add support for "execute --docker" and for cloning an experiment before execution 2020-03-12 18:33:07 +02:00
64 changed files with 21238 additions and 542 deletions

140
README.md
View File

@@ -1,4 +1,4 @@
# TRAINS Agent
# Allegro Trains Agent
## Deep Learning DevOps For Everyone - Now supporting all platforms (Linux, macOS, and Windows)
"All the Deep-Learning DevOps your research needs, and then some... Because ain't nobody got time for that"
@@ -8,27 +8,29 @@
[![PyPI version shields.io](https://img.shields.io/pypi/v/trains-agent.svg)](https://img.shields.io/pypi/v/trains-agent.svg)
[![PyPI status](https://img.shields.io/pypi/status/trains-agent.svg)](https://pypi.python.org/pypi/trains-agent/)
**TRAINS Agent is an AI experiment cluster solution.**
### Help improve Trains by filling our 2-min [user survey](https://allegro.ai/lp/trains-user-survey/)
**Trains Agent is an AI experiment cluster solution.**
It is a zero configuration fire-and-forget execution agent, which combined with trains-server provides a full AI cluster solution.
**Full AutoML in 5 steps**
1. Install the [TRAINS server](https://github.com/allegroai/trains-agent) (or use our [open server](https://demoapp.trains.allegro.ai))
2. `pip install trains-agent` ([install](#installing-the-trains-agent) the TRAINS agent on any GPU machine: on-premises / cloud / ...)
3. Add [TRAINS](https://github.com/allegroai/trains) to your code with just 2 lines & run it once (on your machine / laptop)
1. Install the [Trains Server](https://github.com/allegroai/trains-agent) (or use our [open server](https://demoapp.trains.allegro.ai))
2. `pip install trains-agent` ([install](#installing-the-trains-agent) the Trains Agent on any GPU machine: on-premises / cloud / ...)
3. Add [Trains](https://github.com/allegroai/trains) to your code with just 2 lines & run it once (on your machine / laptop)
4. Change the [parameters](#using-the-trains-agent) in the UI & schedule for [execution](#using-the-trains-agent) (or automate with an [AutoML pipeline](#automl-and-orchestration-pipelines-))
5. :chart_with_downwards_trend: :chart_with_upwards_trend: :eyes: :beer:
**Using the TRAINS agent, you can now set up a dynamic cluster with \*epsilon DevOps**
**Using the Trains Agent, you can now set up a dynamic cluster with \*epsilon DevOps**
*epsilon - Because we are scientists :triangular_ruler: and nothing is really zero work
(Experience TRAINS live at [https://demoapp.trains.allegro.ai](https://demoapp.trains.allegro.ai))
(Experience Trains live at [https://demoapp.trains.allegro.ai](https://demoapp.trains.allegro.ai))
<a href="https://demoapp.trains.allegro.ai"><img src="https://raw.githubusercontent.com/allegroai/trains-agent/9f1e86c1ca45c984ee13edc9353c7b10c55d7257/docs/screenshots.gif" width="100%"></a>
## Simple, Flexible Experiment Orchestration
**The TRAINS Agent was built to address the DL/ML R&D DevOps needs:**
**The Trains Agent was built to address the DL/ML R&D DevOps needs:**
* Easily add & remove machines from the cluster
* Reuse machines without the need for any dedicated containers or images
@@ -49,30 +51,30 @@ If you are considering K8S for your research, also consider that you will soon b
In our experience, handling and building the environments, having to package every experiment in a docker, managing those hundreds (or more) containers and building pipelines on top of it all, is very complicated (also, its usually out of scope for the research team, and overwhelming even for the DevOps team).
We feel there has to be a better way, that can be just as powerful for R&D and at the same time allow integration with K8S **when the need arises**.
(If you already have a K8S cluster for AI, detailed instructions on how to integrate TRAINS into your K8S cluster are *coming soon*.)
(If you already have a K8S cluster for AI, detailed instructions on how to integrate Trains into your K8S cluster are [here](https://github.com/allegroai/trains-server-k8s/tree/master/trains-server-chart) with included [helm chart](https://github.com/allegroai/trains-server-helm))
## Using the TRAINS Agent
## Using the Trains Agent
**Full scale HPC with a click of a button**
TRAINS Agent is a job scheduler that listens on job queue(s), pulls jobs, sets the job environments, executes the job and monitors its progress.
The Trains Agent is a job scheduler that listens on job queue(s), pulls jobs, sets the job environments, executes the job and monitors its progress.
Any 'Draft' experiment can be scheduled for execution by a TRAINS agent.
Any 'Draft' experiment can be scheduled for execution by a Trains agent.
A previously run experiment can be put into 'Draft' state by either of two methods:
* Using the **'Reset'** action from the experiment right-click context menu in the
TRAINS UI - This will clear any results and artifacts the previous run had created.
Trains UI - This will clear any results and artifacts the previous run had created.
* Using the **'Clone'** action from the experiment right-click context menu in the
TRAINS UI - This will create a new 'Draft' experiment with the same configuration as the original experiment.
Trains UI - This will create a new 'Draft' experiment with the same configuration as the original experiment.
An experiment is scheduled for execution using the **'Enqueue'** action from the experiment
right-click context menu in the TRAINS UI and selecting the execution queue.
right-click context menu in the Trains UI and selecting the execution queue.
See [creating an experiment and enqueuing it for execution](#from-scratch).
Once an experiment is enqueued, it will be picked up and executed by a TRAINS agent monitoring this queue.
Once an experiment is enqueued, it will be picked up and executed by a Trains agent monitoring this queue.
The TRAINS UI Workers & Queues page provides ongoing execution information:
The Trains UI Workers & Queues page provides ongoing execution information:
- Workers Tab: Monitor you cluster
- Review available resources
- Monitor machines statistics (CPU / GPU / Disk / Network)
@@ -81,16 +83,16 @@ The TRAINS UI Workers & Queues page provides ongoing execution information:
- Cancel or abort job execution
- Move jobs between execution queues
### What The TRAINS Agent Actually Does
The TRAINS agent executes experiments using the following process:
### What The Trains Agent Actually Does
The Trains Agent executes experiments using the following process:
- Create a new virtual environment (or launch the selected docker image)
- Clone the code into the virtual-environment (or inside the docker)
- Install python packages based on the package requirements listed for the experiment
- Special note for PyTorch: The TRAINS agent will automatically select the
- Special note for PyTorch: The Trains Agent will automatically select the
torch packages based on the CUDA_VERSION environment variable of the machine
- Execute the code, while monitoring the process
- Log all stdout/stderr in the TRAINS UI, including the cloning and installation process, for easy debugging
- Monitor the execution and allow you to manually abort the job using the TRAINS UI (or, in the unfortunate case of a code crash, catch the error and signal the experiment has failed)
- Log all stdout/stderr in the Trains UI, including the cloning and installation process, for easy debugging
- Monitor the execution and allow you to manually abort the job using the Trains UI (or, in the unfortunate case of a code crash, catch the error and signal the experiment has failed)
### System Design & Flow
```text
@@ -98,24 +100,24 @@ The TRAINS agent executes experiments using the following process:
| GPU Machine |
Development Machine | |
+------------------------+ | +-------------+ |
| Data Scientist's | +--------------+ | |TRAINS Agent | |
| Data Scientist's | +--------------+ | |Trains Agent | |
| DL/ML Code | | WEB UI | | | | |
| | | | | | +---------+ | |
| | | | | | | DL/ML | | |
| | +--------------+ | | | Code | | |
| | User Clones Exp #1 / . . . . . . . / | | | | | |
| +-------------------+ | into Exp #2 / . . . . . . . / | | +---------+ | |
| | TRAINS | | +---------------/-_____________-/ | | | |
| | Trains | | +---------------/-_____________-/ | | | |
| +---------+---------+ | | | | ^ | |
+-----------|------------+ | | +------|------+ |
| | +--------|--------+
Auto-Magically | |
Creates Exp #1 | The TRAINS Agent
Creates Exp #1 | The Trains Agent
\ User Change Hyper-Parameters Pulls Exp #2, setup the
| | environment & clone code.
| | Start execution with the
+------------|------------+ | +--------------------+ new set of Hyper-Parameters.
| +---------v---------+ | | | TRAINS-SERVER | |
| +---------v---------+ | | | Trains Server | |
| | Experiment #1 | | | | | |
| +-------------------+ | | | Execution Queue | |
| || | | | | |
@@ -126,17 +128,17 @@ Development Machine |
| | ------------->---------------+ | |
| | User Send Exp #2 | |Execute Exp #2 +--------------------+
| | For Execution | +---------------+ |
| TRAINS-SERVER | | |
| Trains Server | | |
+-------------------------+ +--------------------+
```
### Installing the TRAINS Agent
### Installing the Trains Agent
```bash
pip install trains-agent
```
### TRAINS Agent Usage Examples
### Trains Agent Usage Examples
Full Interface and capabilities are available with
```bash
@@ -144,29 +146,30 @@ trains-agent --help
trains-agent daemon --help
```
### Configuring the TRAINS Agent
### Configuring the Trains Agent
```bash
trains-agent init
```
Note: The TRAINS agent uses a cache folder to cache pip packages, apt packages and cloned repositories. The default TRAINS Agent cache folder is `~/.trains`
Note: The Trains Agent uses a cache folder to cache pip packages, apt packages and cloned repositories. The default Trains Agent cache folder is `~/.trains`
See full details in your configuration file at `~/trains.conf`
Note: The **TRAINS agent** extends the **TRAINS** configuration file `~/trains.conf`
Note: The **Trains agent** extends the **Trains** configuration file `~/trains.conf`
They are designed to share the same configuration file, see example [here](docs/trains.conf)
### Running the TRAINS Agent
### Running the Trains Agent
For debug and experimentation, start the TRAINS agent in `foreground` mode, where all the output is printed to screen
For debug and experimentation, start the Trains agent in `foreground` mode, where all the output is printed to screen
```bash
trains-agent daemon --queue default --foreground
```
For actual service mode, all the stdout will be stored automatically into a temporary file (no need to pipe)
Notice: with `--detached` flag, the *trains-agent* will be running in the background
```bash
trains-agent daemon --queue default
trains-agent daemon --detached --queue default
```
GPU allocation is controlled via the standard OS environment `NVIDIA_VISIBLE_DEVICES` or `--gpus` flag (or disabled with `--cpu-only`).
@@ -175,42 +178,44 @@ If no flag is set, and `NVIDIA_VISIBLE_DEVICES` variable doesn't exist, all GPU'
If `--cpu-only` flag is set, or `NVIDIA_VISIBLE_DEVICES` is an empty string (""), no gpu will be allocated for the `trains-agent`
Example: spin two agents, one per gpu on the same machine:
Notice: with `--detached` flag, the *trains-agent* will be running in the background
```bash
trains-agent daemon --gpus 0 --queue default &
trains-agent daemon --gpus 1 --queue default &
trains-agent daemon --detached --gpus 0 --queue default
trains-agent daemon --detached --gpus 1 --queue default
```
Example: spin two agents, pulling from dedicated `dual_gpu` queue, two gpu's per agent
```bash
trains-agent daemon --gpus 0,1 --queue dual_gpu &
trains-agent daemon --gpus 2,3 --queue dual_gpu &
trains-agent daemon --detached --gpus 0,1 --queue dual_gpu
trains-agent daemon --detached --gpus 2,3 --queue dual_gpu
```
#### Starting the TRAINS Agent in docker mode
#### Starting the Trains Agent in docker mode
For debug and experimentation, start the TRAINS agent in `foreground` mode, where all the output is printed to screen
For debug and experimentation, start the Trains agent in `foreground` mode, where all the output is printed to screen
```bash
trains-agent daemon --queue default --docker --foreground
```
For actual service mode, all the stdout will be stored automatically into a file (no need to pipe)
Notice: with `--detached` flag, the *trains-agent* will be running in the background
```bash
trains-agent daemon --queue default --docker
trains-agent daemon --detached --queue default --docker
```
Example: spin two agents, one per gpu on the same machine, with default nvidia/cuda docker:
```bash
trains-agent daemon --gpus 0 --queue default --docker nvidia/cuda &
trains-agent daemon --gpus 1 --queue default --docker nvidia/cuda &
trains-agent daemon --detached --gpus 0 --queue default --docker nvidia/cuda
trains-agent daemon --detached --gpus 1 --queue default --docker nvidia/cuda
```
Example: spin two agents, pulling from dedicated `dual_gpu` queue, two gpu's per agent, with default nvidia/cuda docker:
```bash
trains-agent daemon --gpus 0,1 --queue dual_gpu --docker nvidia/cuda &
trains-agent daemon --gpus 2,3 --queue dual_gpu --docker nvidia/cuda &
trains-agent daemon --detached --gpus 0,1 --queue dual_gpu --docker nvidia/cuda
trains-agent daemon --detached --gpus 2,3 --queue dual_gpu --docker nvidia/cuda
```
#### Starting the TRAINS Agent - Priority Queues
#### Starting the Trains Agent - Priority Queues
Priority Queues are also supported, example use case:
@@ -218,14 +223,14 @@ High priority queue: `important_jobs` Low priority queue: `default`
```bash
trains-agent daemon --queue important_jobs default
```
The **TRAINS agent** will first try to pull jobs from the `important_jobs` queue, only then it will fetch a job from the `default` queue.
The **Trains Agent** will first try to pull jobs from the `important_jobs` queue, only then it will fetch a job from the `default` queue.
Adding queues, managing job order within a queue and moving jobs between queues, is available using the Web UI, see example on our [open server](https://demoapp.trains.allegro.ai/workers-and-queues/queues)
# How do I create an experiment on the TRAINS server? <a name="from-scratch"></a>
* Integrate [TRAINS](https://github.com/allegroai/trains) with your code
## How do I create an experiment on the Trains Server? <a name="from-scratch"></a>
* Integrate [Trains](https://github.com/allegroai/trains) with your code
* Execute the code on your machine (Manually / PyCharm / Jupyter Notebook)
* As your code is running, **TRAINS** creates an experiment logging all the necessary execution information:
* As your code is running, **Trains** creates an experiment logging all the necessary execution information:
- Git repository link and commit ID (or an entire jupyter notebook)
- Git diff (were not saying you never commit and push, but still...)
- Python packages used by your code (including specific versions used)
@@ -234,7 +239,7 @@ Adding queues, managing job order within a queue and moving jobs between queues,
You now have a 'template' of your experiment with everything required for automated execution
* In the TRAINS UI, Right click on the experiment and select 'clone'. A copy of your experiment will be created.
* In the Trains UI, Right click on the experiment and select 'clone'. A copy of your experiment will be created.
* You now have a new draft experiment cloned from your original experiment, feel free to edit it
- Change the Hyper-Parameters
- Switch to the latest code base of the repository
@@ -243,10 +248,31 @@ Adding queues, managing job order within a queue and moving jobs between queues,
- Or simply change nothing to run the same experiment again...
* Schedule the newly created experiment for execution: Right-click the experiment and select 'enqueue'
# AutoML and Orchestration Pipelines <a name="automl-pipes"></a>
The TRAINS Agent can also be used to implement AutoML orchestration and Experiment Pipelines in conjunction with the TRAINS package.
## Trains-Agent Services Mode <a name="services"></a>
Sample AutoML & Orchestration examples can be found in the TRAINS [example/automl](https://github.com/allegroai/trains/tree/master/examples/automl) folder.
Trains-Agent Services is a special mode of Trains-Agent that provides the ability to launch long-lasting jobs
that previously had to be executed on local / dedicated machines. It allows a single agent to
launch multiple dockers (Tasks) for different use cases. To name a few use cases, auto-scaler service (spinning instances
when the need arises and the budget allows), Controllers (Implementing pipelines and more sophisticated DevOps logic),
Optimizer (such as Hyper-parameter Optimization or sweeping), and Application (such as interactive Bokeh apps for
increased data transparency)
Trains-Agent Services mode will spin **any** task enqueued into the specified queue.
Every task launched by Trains-Agent Services will be registered as a new node in the system,
providing tracking and transparency capabilities.
Currently trains-agent in services-mode supports cpu only configuration. Trains-agent services mode can be launched alongside GPU agents.
```bash
trains-agent daemon --services-mode --detached --queue services --create-queue --docker ubuntu:18.04 --cpu-only
```
**Note**: It is the user's responsibility to make sure the proper tasks are pushed into the specified queue.
## AutoML and Orchestration Pipelines <a name="automl-pipes"></a>
The Trains Agent can also be used to implement AutoML orchestration and Experiment Pipelines in conjunction with the Trains package.
Sample AutoML & Orchestration examples can be found in the Trains [example/automl](https://github.com/allegroai/trains/tree/master/examples/automl) folder.
AutoML examples
- [Toy Keras training experiment](https://github.com/allegroai/trains/blob/master/examples/automl/automl_base_template_keras_simple.py)
@@ -259,3 +285,7 @@ Experiment Pipeline examples
- This example will "process data", and once done, will launch a copy of the 'second step' experiment-template
- [Second step experiment](https://github.com/allegroai/trains/blob/master/examples/automl/toy_base_task.py)
- In order to create an experiment-template in the system, this code must be executed once manually
## License
Apache License, Version 2.0 (see the [LICENSE](https://www.apache.org/licenses/LICENSE-2.0.html) for more information)

18
docker/agent/Dockerfile Normal file
View File

@@ -0,0 +1,18 @@
# syntax = docker/dockerfile
FROM nvidia/cuda
WORKDIR /usr/agent
COPY . /usr/agent
RUN apt-get update
RUN apt-get dist-upgrade -y
RUN apt-get install -y curl python3-pip git
RUN curl -sSL https://get.docker.com/ | sh
RUN python3 -m pip install -U pip
RUN python3 -m pip install trains-agent
RUN python3 -m pip install -U "cryptography>=2.9"
ENV TRAINS_DOCKER_SKIP_GPUS_FLAG=1
ENTRYPOINT ["/usr/agent/entrypoint.sh"]

19
docker/agent/entrypoint.sh Executable file
View File

@@ -0,0 +1,19 @@
#!/bin/sh
LOWER_PIP_UPDATE_VERSION="$(echo "$PIP_UPDATE_VERSION" | tr '[:upper:]' '[:lower:]')"
LOWER_TRAINS_AGENT_UPDATE_VERSION="$(echo "$TRAINS_AGENT_UPDATE_VERSION" | tr '[:upper:]' '[:lower:]')"
if [ "$LOWER_PIP_UPDATE_VERSION" = "yes" ] || [ "$LOWER_PIP_UPDATE_VERSION" = "true" ] ; then
python3 -m pip install -U pip
elif [ ! -z "$LOWER_PIP_UPDATE_VERSION" ] ; then
python3 -m pip install pip$LOWER_PIP_UPDATE_VERSION ;
fi
echo "TRAINS_AGENT_UPDATE_VERSION = $LOWER_TRAINS_AGENT_UPDATE_VERSION"
if [ "$LOWER_TRAINS_AGENT_UPDATE_VERSION" = "yes" ] || [ "$LOWER_TRAINS_AGENT_UPDATE_VERSION" = "true" ] ; then
python3 -m pip install trains-agent -U
elif [ ! -z "$LOWER_TRAINS_AGENT_UPDATE_VERSION" ] ; then
python3 -m pip install trains-agent$LOWER_TRAINS_AGENT_UPDATE_VERSION ;
fi
python3 -m trains_agent daemon --docker "$TRAINS_AGENT_DEFAULT_BASE_DOCKER" --force-current-version $TRAINS_AGENT_EXTRA_ARGS

View File

@@ -0,0 +1,16 @@
# syntax = docker/dockerfile
FROM ubuntu:18.04
WORKDIR /usr/agent
COPY . /usr/agent
RUN apt-get update
RUN apt-get dist-upgrade -y
RUN apt-get install -y curl python3-pip git
RUN curl -sSL https://get.docker.com/ | sh
RUN python3 -m pip install -U pip
RUN python3 -m pip install trains-agent
RUN python3 -m pip install -U "cryptography>=2.9"
ENTRYPOINT ["/usr/agent/entrypoint.sh"]

14
docker/services/entrypoint.sh Executable file
View File

@@ -0,0 +1,14 @@
#!/bin/sh
if [ -z "$TRAINS_FILES_HOST" ]; then
TRAINS_HOST_IP=${TRAINS_HOST_IP:-$(curl -s https://ifconfig.me/ip)}
fi
TRAINS_FILES_HOST=${TRAINS_FILES_HOST:-"http://$TRAINS_HOST_IP:8081"}
TRAINS_WEB_HOST=${TRAINS_WEB_HOST:-"http://$TRAINS_HOST_IP:8080"}
TRAINS_API_HOST=${TRAINS_API_HOST:-"http://$TRAINS_HOST_IP:8008"}
echo $TRAINS_FILES_HOST $TRAINS_WEB_HOST $TRAINS_API_HOST 1>&2
python3 -m pip install -q -U "trains-agent${TRAINS_AGENT_UPDATE_VERSION}"
trains-agent daemon --services-mode --queue services --create-queue --docker $TRAINS_AGENT_DEFAULT_BASE_DOCKER --cpu-only $TRAINS_AGENT_EXTRA_ARGS

View File

@@ -13,11 +13,13 @@ api {
}
agent {
# Set GIT user/pass credentials
# leave blank for GIT SSH credentials
# Set GIT user/pass credentials (if user/pass are set, GIT protocol will be set to https)
# leave blank for GIT SSH credentials (set force_git_ssh_protocol=true to force SSH protocol)
git_user=""
git_pass=""
# Force GIT protocol to use SSH regardless of the git url (Assumes GIT user/pass are blank)
force_git_ssh_protocol: false
# unique name of this worker, if None, created based on hostname:process_id
# Overridden with os environment: TRAINS_WORKER_NAME
@@ -55,6 +57,10 @@ agent {
# additional conda channels to use when installing with conda package manager
conda_channels: ["pytorch", "conda-forge", ]
# set to True to support torch nightly build installation,
# notice: torch nightly builds are ephemeral and are deleted from time to time
torch_nightly: false,
},
# target folder for virtual environments builds, created when executing experiment
@@ -82,9 +88,9 @@ agent {
# reload configuration file every daemon execution
reload_config: false,
# pip cache folder used mapped into docker, for python package caching
# pip cache folder mapped into docker, used for python package caching
docker_pip_cache = ~/.trains/pip-cache
# apt cache folder used mapped into docker, for ubuntu package caching
# apt cache folder mapped into docker, used for ubuntu package caching
docker_apt_cache = ~/.trains/apt-cache
# optional arguments to pass to docker image
@@ -100,11 +106,16 @@ agent {
default_docker: {
# default docker image to use when running in docker mode
image: "nvidia/cuda"
image: "nvidia/cuda:10.1-runtime-ubuntu18.04"
# optional arguments to pass to docker image
# arguments: ["--ipc=host"]
}
# CUDA versions used for Conda setup & solving PyTorch wheel packages
# it Should be detected automatically. Override with os environment CUDA_VERSION / CUDNN_VERSION
# cuda_version: 10.1
# cudnn_version: 7.6
}
sdk {

View File

@@ -3,9 +3,7 @@ enum34>=0.9 ; python_version < '3.6'
furl>=2.0.0
future>=0.16.0
humanfriendly>=2.1
jsonmodels>=2.2
jsonschema>=2.6.0
packaging>=16.0
pathlib2>=2.3.0
psutil>=3.4.2
pyhocon>=0.3.38

View File

@@ -4,28 +4,31 @@ TRAINS-AGENT DevOps for machine/deep learning
https://github.com/allegroai/trains-agent
"""
import os.path
# Always prefer setuptools over distutils
from setuptools import setup, find_packages
from six import exec_
from pathlib2 import Path
def read_text(filepath):
with open(filepath, "r") as f:
return f.read()
here = Path(__file__).resolve().parent
here = os.path.dirname(__file__)
# Get the long description from the README file
long_description = (here / 'README.md').read_text()
long_description = read_text(os.path.join(here, 'README.md'))
def read_version_string():
result = {}
exec_((here / 'trains_agent/version.py').read_text(), result)
return result['__version__']
def read_version_string(version_file):
for line in read_text(version_file).splitlines():
if line.startswith('__version__'):
delim = '"' if '"' in line else "'"
return line.split(delim)[1]
else:
raise RuntimeError("Unable to find version string.")
version = read_version_string()
requirements = (here / 'requirements.txt').read_text().splitlines()
version = read_version_string("trains_agent/version.py")
requirements = read_text(os.path.join(here, 'requirements.txt')).splitlines()
setup(
name='trains_agent',

View File

@@ -30,6 +30,6 @@ from trains_agent.helper.repo import VCS
),
)
def test(url, expected):
result = VCS.resolve_ssh_url(url)
result = VCS.replace_ssh_url(url)
expected = expected or url
assert result == expected

View File

@@ -11,7 +11,7 @@ from contextlib import contextmanager
from typing import Iterator, ContextManager, Sequence, IO, Text
from uuid import uuid4
from trains_agent.backend_api.services.tasks import Script
from trains_agent.backend_api.services import tasks
from trains_agent.backend_api.session.client import APIClient
from pathlib2 import Path
from pytest import fixture
@@ -154,7 +154,7 @@ def test_entry_point_warning(client):
"""
with create_task(
client,
script=Script(diff="print('hello')", entry_point="foo.py", repository=""),
script=tasks.Script(diff="print('hello')", entry_point="foo.py", repository=""),
**DEFAULT_TASK_ARGS
) as task, iterate_output(SHORT_TIMEOUT, run_task(task)) as output:
for line in output:
@@ -172,7 +172,7 @@ def test_run_no_dirs(client):
script = "print('{}')".format(uuid)
with create_task(
client,
script=Script(diff=script, entry_point="", repository="", working_dir=""),
script=tasks.Script(diff=script, entry_point="", repository="", working_dir=""),
**DEFAULT_TASK_ARGS
) as task, iterate_output(SHORT_TIMEOUT, run_task(task)) as output:
search_lines(
@@ -196,7 +196,7 @@ def test_run_working_dir(client):
script = "print('{}')".format(uuid)
with create_task(
client,
script=Script(
script=tasks.Script(
diff=script,
entry_point="",
repository="git@bitbucket.org:seematics/roee_test_git.git",
@@ -223,7 +223,7 @@ def test_regular_task(client):
"""
with create_task(
client,
script=Script(
script=tasks.Script(
entry_point="noop.py",
repository="git@bitbucket.org:seematics/roee_test_git.git",
),
@@ -241,7 +241,7 @@ def test_regular_task_nested(client):
"""
with create_task(
client,
script=Script(
script=tasks.Script(
entry_point="noop_nested.py",
working_dir="no_reqs",
repository="git@bitbucket.org:seematics/roee_test_git.git",

View File

@@ -20,6 +20,8 @@ from .interface import get_parser
def run_command(parser, args, command_name):
debug = args.debug
session.Session.set_debug_mode(debug)
if command_name and command_name.lower() in ('config', 'init'):
command_class = commands.Config
elif len(command_name.split('.')) < 2:

View File

@@ -9,10 +9,14 @@
# worker_name: "trains-agent-machine1"
worker_name: ""
# Set GIT user/pass credentials for cloning code, leave blank for GIT SSH credentials.
# Set GIT user/pass credentials (if user/pass are set, GIT protocol will be set to https)
# leave blank for GIT SSH credentials (set force_git_ssh_protocol=true to force SSH protocol)
# git_user: ""
# git_pass: ""
# Force GIT protocol to use SSH regardless of the git url (Assumes GIT user/pass are blank)
force_git_ssh_protocol: false
# Set the python version to use when creating the virtual environment and launching the experiment
# Example values: "/usr/bin/python3" or "/usr/local/bin/python3.6"
# The default is the python executing the trains_agent
@@ -26,7 +30,7 @@
type: pip,
# specify pip version to use (examples "<20", "==19.3.1", "", empty string will install the latest version)
pip_version: "<20",
pip_version: "<20.2",
# virtual environment inheres packages from system
system_site_packages: false,
@@ -39,6 +43,10 @@
# additional conda channels to use when installing with conda package manager
conda_channels: ["defaults", "conda-forge", "pytorch", ]
# set to True to support torch nightly build installation,
# notice: torch nightly builds are ephemeral and are deleted from time to time
torch_nightly: false,
},
# target folder for virtual environments builds, created when executing experiment
@@ -66,9 +74,9 @@
# reload configuration file every daemon execution
reload_config: false,
# pip cache folder used mapped into docker, for python package caching
# pip cache folder mapped into docker, used for python package caching
docker_pip_cache = ~/.trains/pip-cache
# apt cache folder used mapped into docker, for ubuntu package caching
# apt cache folder mapped into docker, used for ubuntu package caching
docker_apt_cache = ~/.trains/apt-cache
# optional arguments to pass to docker image
@@ -84,12 +92,23 @@
default_docker: {
# default docker image to use when running in docker mode
image: "nvidia/cuda"
image: "nvidia/cuda:10.1-runtime-ubuntu18.04"
# optional arguments to pass to docker image
# arguments: ["--ipc=host", ]
}
# set the initial bash script to execute at the startup of any docker.
# all lines will be executed regardless of their exit code.
# {python_single_digit} is translated to 'python3' or 'python2' according to requested python version
# docker_init_bash_script = [
# "echo 'Binary::apt::APT::Keep-Downloaded-Packages \"true\";' > /etc/apt/apt.conf.d/docker-clean",
# "chown -R root /root/.cache/pip",
# "apt-get update",
# "apt-get install -y git libsm6 libxext6 libxrender-dev libglib2.0-0",
# "(which {python_single_digit} && {python_single_digit} -m pip --version) || apt-get install -y {python_single_digit}-pip",
# ]
# cuda versions used for solving pytorch wheel packages
# should be detected automatically. Override with os environment CUDA_VERSION / CUDNN_VERSION
# cuda_version: 10.1

View File

@@ -1,10 +1,10 @@
from .v2_4 import auth
from .v2_4 import debug
from .v2_4 import queues
from .v2_4 import tasks
from .v2_4 import workers
from .v2_4 import events
from .v2_4 import models
from .v2_5 import auth
from .v2_5 import debug
from .v2_5 import queues
from .v2_5 import tasks
from .v2_5 import workers
from .v2_5 import events
from .v2_5 import models
__all__ = [
'auth',

View File

@@ -151,7 +151,7 @@ class CreateCredentialsRequest(Request):
_service = "auth"
_action = "create_credentials"
_version = "2.1"
_version = "2.4"
_schema = {
'additionalProperties': False,
'definitions': {},
@@ -169,7 +169,7 @@ class CreateCredentialsResponse(Response):
"""
_service = "auth"
_action = "create_credentials"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
@@ -230,7 +230,7 @@ class EditUserRequest(Request):
_service = "auth"
_action = "edit_user"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -287,7 +287,7 @@ class EditUserResponse(Response):
"""
_service = "auth"
_action = "edit_user"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -347,7 +347,7 @@ class GetCredentialsRequest(Request):
_service = "auth"
_action = "get_credentials"
_version = "2.1"
_version = "2.4"
_schema = {
'additionalProperties': False,
'definitions': {},
@@ -365,7 +365,7 @@ class GetCredentialsResponse(Response):
"""
_service = "auth"
_action = "get_credentials"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
@@ -433,7 +433,7 @@ class LoginRequest(Request):
_service = "auth"
_action = "login"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -474,7 +474,7 @@ class LoginResponse(Response):
"""
_service = "auth"
_action = "login"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -510,7 +510,7 @@ class LogoutRequest(Request):
_service = "auth"
_action = "logout"
_version = "2.2"
_version = "2.4"
_schema = {'additionalProperties': False, 'definitions': {}, 'type': 'object'}
@@ -521,7 +521,7 @@ class LogoutResponse(Response):
"""
_service = "auth"
_action = "logout"
_version = "2.2"
_version = "2.4"
_schema = {'additionalProperties': False, 'definitions': {}, 'type': 'object'}
@@ -537,7 +537,7 @@ class RevokeCredentialsRequest(Request):
_service = "auth"
_action = "revoke_credentials"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -577,7 +577,7 @@ class RevokeCredentialsResponse(Response):
"""
_service = "auth"
_action = "revoke_credentials"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},

View File

@@ -19,7 +19,7 @@ class ApiexRequest(Request):
_service = "debug"
_action = "apiex"
_version = "1.5"
_version = "2.4"
_schema = {'definitions': {}, 'properties': {}, 'required': [], 'type': 'object'}
@@ -30,7 +30,7 @@ class ApiexResponse(Response):
"""
_service = "debug"
_action = "apiex"
_version = "1.5"
_version = "2.4"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
@@ -43,7 +43,7 @@ class EchoRequest(Request):
_service = "debug"
_action = "echo"
_version = "1.5"
_version = "2.4"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
@@ -54,7 +54,7 @@ class EchoResponse(Response):
"""
_service = "debug"
_action = "echo"
_version = "1.5"
_version = "2.4"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
@@ -65,7 +65,7 @@ class ExRequest(Request):
_service = "debug"
_action = "ex"
_version = "1.5"
_version = "2.4"
_schema = {'definitions': {}, 'properties': {}, 'required': [], 'type': 'object'}
@@ -76,7 +76,7 @@ class ExResponse(Response):
"""
_service = "debug"
_action = "ex"
_version = "1.5"
_version = "2.4"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
@@ -89,7 +89,7 @@ class PingRequest(Request):
_service = "debug"
_action = "ping"
_version = "1.5"
_version = "2.4"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
@@ -102,7 +102,7 @@ class PingResponse(Response):
"""
_service = "debug"
_action = "ping"
_version = "1.5"
_version = "2.4"
_schema = {
'definitions': {},
@@ -141,7 +141,7 @@ class PingAuthRequest(Request):
_service = "debug"
_action = "ping_auth"
_version = "1.5"
_version = "2.4"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
@@ -154,7 +154,7 @@ class PingAuthResponse(Response):
"""
_service = "debug"
_action = "ping_auth"
_version = "1.5"
_version = "2.4"
_schema = {
'definitions': {},

View File

@@ -734,7 +734,7 @@ class AddRequest(CompoundRequest):
_service = "events"
_action = "add"
_version = "2.1"
_version = "2.4"
_item_prop_name = "event"
_schema = {
'anyOf': [
@@ -926,7 +926,7 @@ class AddResponse(Response):
"""
_service = "events"
_action = "add"
_version = "2.1"
_version = "2.4"
_schema = {'additionalProperties': True, 'definitions': {}, 'type': 'object'}
@@ -939,7 +939,7 @@ class AddBatchRequest(BatchRequest):
_service = "events"
_action = "add_batch"
_version = "2.1"
_version = "2.4"
_batched_request_cls = AddRequest
@@ -954,7 +954,7 @@ class AddBatchResponse(Response):
"""
_service = "events"
_action = "add_batch"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -1015,7 +1015,7 @@ class DebugImagesRequest(Request):
_service = "events"
_action = "debug_images"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -1098,7 +1098,7 @@ class DebugImagesResponse(Response):
"""
_service = "events"
_action = "debug_images"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -1213,7 +1213,7 @@ class DeleteForTaskRequest(Request):
_service = "events"
_action = "delete_for_task"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {'task': {'description': 'Task ID', 'type': 'string'}},
@@ -1248,7 +1248,7 @@ class DeleteForTaskResponse(Response):
"""
_service = "events"
_action = "delete_for_task"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -1293,7 +1293,7 @@ class DownloadTaskLogRequest(Request):
_service = "events"
_action = "download_task_log"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -1366,7 +1366,7 @@ class DownloadTaskLogResponse(Response):
"""
_service = "events"
_action = "download_task_log"
_version = "2.1"
_version = "2.4"
_schema = {'definitions': {}, 'type': 'string'}
@@ -1385,7 +1385,7 @@ class GetMultiTaskPlotsRequest(Request):
_service = "events"
_action = "get_multi_task_plots"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -1472,7 +1472,7 @@ class GetMultiTaskPlotsResponse(Response):
"""
_service = "events"
_action = "get_multi_task_plots"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -1571,7 +1571,7 @@ class GetScalarMetricDataRequest(Request):
_service = "events"
_action = "get_scalar_metric_data"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -1628,7 +1628,7 @@ class GetScalarMetricDataResponse(Response):
"""
_service = "events"
_action = "get_scalar_metric_data"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -1730,7 +1730,7 @@ class GetScalarMetricsAndVariantsRequest(Request):
_service = "events"
_action = "get_scalar_metrics_and_variants"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {'task': {'description': 'task ID', 'type': 'string'}},
@@ -1765,7 +1765,7 @@ class GetScalarMetricsAndVariantsResponse(Response):
"""
_service = "events"
_action = "get_scalar_metrics_and_variants"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -1811,7 +1811,7 @@ class GetTaskEventsRequest(Request):
_service = "events"
_action = "get_task_events"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -1928,7 +1928,7 @@ class GetTaskEventsResponse(Response):
"""
_service = "events"
_action = "get_task_events"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2028,7 +2028,7 @@ class GetTaskLatestScalarValuesRequest(Request):
_service = "events"
_action = "get_task_latest_scalar_values"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {'task': {'description': 'Task ID', 'type': 'string'}},
@@ -2063,7 +2063,7 @@ class GetTaskLatestScalarValuesResponse(Response):
"""
_service = "events"
_action = "get_task_latest_scalar_values"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2141,7 +2141,7 @@ class GetTaskLogRequest(Request):
_service = "events"
_action = "get_task_log"
_version = "1.7"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -2254,7 +2254,7 @@ class GetTaskLogResponse(Response):
"""
_service = "events"
_action = "get_task_log"
_version = "1.7"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2358,7 +2358,7 @@ class GetTaskPlotsRequest(Request):
_service = "events"
_action = "get_task_plots"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -2439,7 +2439,7 @@ class GetTaskPlotsResponse(Response):
"""
_service = "events"
_action = "get_task_plots"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2537,7 +2537,7 @@ class GetVectorMetricsAndVariantsRequest(Request):
_service = "events"
_action = "get_vector_metrics_and_variants"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {'task': {'description': 'Task ID', 'type': 'string'}},
@@ -2572,7 +2572,7 @@ class GetVectorMetricsAndVariantsResponse(Response):
"""
_service = "events"
_action = "get_vector_metrics_and_variants"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2623,7 +2623,7 @@ class MultiTaskScalarMetricsIterHistogramRequest(Request):
_service = "events"
_action = "multi_task_scalar_metrics_iter_histogram"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
'scalar_key_enum': {'enum': ['iter', 'timestamp', 'iso_time'], 'type': 'string'},
@@ -2712,7 +2712,7 @@ class MultiTaskScalarMetricsIterHistogramResponse(Response):
"""
_service = "events"
_action = "multi_task_scalar_metrics_iter_histogram"
_version = "2.1"
_version = "2.4"
_schema = {'additionalProperties': True, 'definitions': {}, 'type': 'object'}
@@ -2734,7 +2734,7 @@ class ScalarMetricsIterHistogramRequest(Request):
_service = "events"
_action = "scalar_metrics_iter_histogram"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
'scalar_key_enum': {'enum': ['iter', 'timestamp', 'iso_time'], 'type': 'string'},
@@ -2816,7 +2816,7 @@ class ScalarMetricsIterHistogramResponse(Response):
"""
_service = "events"
_action = "scalar_metrics_iter_histogram"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2860,7 +2860,7 @@ class VectorMetricsIterHistogramRequest(Request):
_service = "events"
_action = "vector_metrics_iter_histogram"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -2927,7 +2927,7 @@ class VectorMetricsIterHistogramResponse(Response):
"""
_service = "events"
_action = "vector_metrics_iter_histogram"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},

View File

@@ -464,7 +464,7 @@ class CreateRequest(Request):
_service = "models"
_action = "create"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -720,7 +720,7 @@ class CreateResponse(Response):
"""
_service = "models"
_action = "create"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -779,7 +779,7 @@ class DeleteRequest(Request):
_service = "models"
_action = "delete"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -834,7 +834,7 @@ class DeleteResponse(Response):
"""
_service = "models"
_action = "delete"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -904,7 +904,7 @@ class EditRequest(Request):
_service = "models"
_action = "edit"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -1175,7 +1175,7 @@ class EditResponse(Response):
"""
_service = "models"
_action = "edit"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -1279,7 +1279,7 @@ class GetAllRequest(Request):
_service = "models"
_action = "get_all"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
'multi_field_pattern_data': {
@@ -1647,7 +1647,7 @@ class GetAllResponse(Response):
"""
_service = "models"
_action = "get_all"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
@@ -1770,7 +1770,7 @@ class GetByIdRequest(Request):
_service = "models"
_action = "get_by_id"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {'model': {'description': 'Model id', 'type': 'string'}},
@@ -1805,7 +1805,7 @@ class GetByIdResponse(Response):
"""
_service = "models"
_action = "get_by_id"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
@@ -1925,7 +1925,7 @@ class GetByTaskIdRequest(Request):
_service = "models"
_action = "get_by_task_id"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -1961,7 +1961,7 @@ class GetByTaskIdResponse(Response):
"""
_service = "models"
_action = "get_by_task_id"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
@@ -2087,7 +2087,7 @@ class SetReadyRequest(Request):
_service = "models"
_action = "set_ready"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -2164,7 +2164,7 @@ class SetReadyResponse(Response):
"""
_service = "models"
_action = "set_ready"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2276,7 +2276,7 @@ class UpdateRequest(Request):
_service = "models"
_action = "update"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -2502,7 +2502,7 @@ class UpdateResponse(Response):
"""
_service = "models"
_action = "update"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2581,7 +2581,7 @@ class UpdateForTaskRequest(Request):
_service = "models"
_action = "update_for_task"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -2752,7 +2752,7 @@ class UpdateForTaskResponse(Response):
"""
_service = "models"
_action = "update_for_task"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},

View File

@@ -1518,7 +1518,7 @@ class CloseRequest(Request):
_service = "tasks"
_action = "close"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -1612,7 +1612,7 @@ class CloseResponse(Response):
"""
_service = "tasks"
_action = "close"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -1682,7 +1682,7 @@ class CompletedRequest(Request):
_service = "tasks"
_action = "completed"
_version = "2.2"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -1776,7 +1776,7 @@ class CompletedResponse(Response):
"""
_service = "tasks"
_action = "completed"
_version = "2.2"
_version = "2.4"
_schema = {
'definitions': {},
@@ -1862,7 +1862,7 @@ class CreateRequest(Request):
_service = "tasks"
_action = "create"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
'artifact': {
@@ -2229,7 +2229,7 @@ class CreateResponse(Response):
"""
_service = "tasks"
_action = "create"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2280,7 +2280,7 @@ class DeleteRequest(Request):
_service = "tasks"
_action = "delete"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -2403,7 +2403,7 @@ class DeleteResponse(Response):
"""
_service = "tasks"
_action = "delete"
_version = "1.5"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2547,7 +2547,7 @@ class DequeueRequest(Request):
_service = "tasks"
_action = "dequeue"
_version = "1.5"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -2624,7 +2624,7 @@ class DequeueResponse(Response):
"""
_service = "tasks"
_action = "dequeue"
_version = "1.5"
_version = "2.4"
_schema = {
'definitions': {},
@@ -2733,7 +2733,7 @@ class EditRequest(Request):
_service = "tasks"
_action = "edit"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
'artifact': {
@@ -3123,7 +3123,7 @@ class EditResponse(Response):
"""
_service = "tasks"
_action = "edit"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -3201,7 +3201,7 @@ class EnqueueRequest(Request):
_service = "tasks"
_action = "enqueue"
_version = "1.5"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -3296,7 +3296,7 @@ class EnqueueResponse(Response):
"""
_service = "tasks"
_action = "enqueue"
_version = "1.5"
_version = "2.4"
_schema = {
'definitions': {},
@@ -3386,7 +3386,7 @@ class FailedRequest(Request):
_service = "tasks"
_action = "failed"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -3480,7 +3480,7 @@ class FailedResponse(Response):
"""
_service = "tasks"
_action = "failed"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -3587,7 +3587,7 @@ class GetAllRequest(Request):
_service = "tasks"
_action = "get_all"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
'multi_field_pattern_data': {
@@ -3986,7 +3986,7 @@ class GetAllResponse(Response):
"""
_service = "tasks"
_action = "get_all"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
@@ -4373,7 +4373,7 @@ class GetByIdRequest(Request):
_service = "tasks"
_action = "get_by_id"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {'task': {'description': 'Task ID', 'type': 'string'}},
@@ -4408,7 +4408,7 @@ class GetByIdResponse(Response):
"""
_service = "tasks"
_action = "get_by_id"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
@@ -4792,7 +4792,7 @@ class PingRequest(Request):
_service = "tasks"
_action = "ping"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {'task': {'description': 'Task ID', 'type': 'string'}},
@@ -4825,7 +4825,7 @@ class PingResponse(Response):
"""
_service = "tasks"
_action = "ping"
_version = "2.1"
_version = "2.4"
_schema = {'additionalProperties': False, 'definitions': {}, 'type': 'object'}
@@ -4853,7 +4853,7 @@ class PublishRequest(Request):
_service = "tasks"
_action = "publish"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -4967,7 +4967,7 @@ class PublishResponse(Response):
"""
_service = "tasks"
_action = "publish"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -5057,7 +5057,7 @@ class ResetRequest(Request):
_service = "tasks"
_action = "reset"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -5160,7 +5160,7 @@ class ResetResponse(Response):
"""
_service = "tasks"
_action = "reset"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -5305,7 +5305,7 @@ class SetRequirementsRequest(Request):
_service = "tasks"
_action = "set_requirements"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -5362,7 +5362,7 @@ class SetRequirementsResponse(Response):
"""
_service = "tasks"
_action = "set_requirements"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -5431,7 +5431,7 @@ class StartedRequest(Request):
_service = "tasks"
_action = "started"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -5527,7 +5527,7 @@ class StartedResponse(Response):
"""
_service = "tasks"
_action = "started"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -5617,7 +5617,7 @@ class StopRequest(Request):
_service = "tasks"
_action = "stop"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -5711,7 +5711,7 @@ class StopResponse(Response):
"""
_service = "tasks"
_action = "stop"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -5780,7 +5780,7 @@ class StoppedRequest(Request):
_service = "tasks"
_action = "stopped"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -5874,7 +5874,7 @@ class StoppedResponse(Response):
"""
_service = "tasks"
_action = "stopped"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -5952,7 +5952,7 @@ class UpdateRequest(Request):
_service = "tasks"
_action = "update"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
'properties': {
@@ -6120,7 +6120,7 @@ class UpdateResponse(Response):
"""
_service = "tasks"
_action = "update"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -6183,7 +6183,7 @@ class UpdateBatchRequest(BatchRequest):
_service = "tasks"
_action = "update_batch"
_version = "2.1"
_version = "2.4"
_batched_request_cls = UpdateRequest
@@ -6196,7 +6196,7 @@ class UpdateBatchResponse(Response):
"""
_service = "tasks"
_action = "update_batch"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {},
@@ -6261,7 +6261,7 @@ class ValidateRequest(Request):
_service = "tasks"
_action = "validate"
_version = "2.1"
_version = "2.4"
_schema = {
'definitions': {
'artifact': {
@@ -6614,7 +6614,7 @@ class ValidateResponse(Response):
"""
_service = "tasks"
_action = "validate"
_version = "2.1"
_version = "2.4"
_schema = {'additionalProperties': False, 'definitions': {}, 'type': 'object'}

View File

@@ -0,0 +1,623 @@
"""
auth service
This service provides authentication management and authorization
validation for the entire system.
"""
import six
import types
from datetime import datetime
import enum
from dateutil.parser import parse as parse_datetime
from ....backend_api.session import Request, BatchRequest, Response, DataModel, NonStrictDataModel, CompoundRequest, schema_property, StringEnum
class Credentials(NonStrictDataModel):
"""
:param access_key: Credentials access key
:type access_key: str
:param secret_key: Credentials secret key
:type secret_key: str
"""
_schema = {
'properties': {
'access_key': {
'description': 'Credentials access key',
'type': ['string', 'null'],
},
'secret_key': {
'description': 'Credentials secret key',
'type': ['string', 'null'],
},
},
'type': 'object',
}
def __init__(
self, access_key=None, secret_key=None, **kwargs):
super(Credentials, self).__init__(**kwargs)
self.access_key = access_key
self.secret_key = secret_key
@schema_property('access_key')
def access_key(self):
return self._property_access_key
@access_key.setter
def access_key(self, value):
if value is None:
self._property_access_key = None
return
self.assert_isinstance(value, "access_key", six.string_types)
self._property_access_key = value
@schema_property('secret_key')
def secret_key(self):
return self._property_secret_key
@secret_key.setter
def secret_key(self, value):
if value is None:
self._property_secret_key = None
return
self.assert_isinstance(value, "secret_key", six.string_types)
self._property_secret_key = value
class CredentialKey(NonStrictDataModel):
"""
:param access_key:
:type access_key: str
:param last_used:
:type last_used: datetime.datetime
:param last_used_from:
:type last_used_from: str
"""
_schema = {
'properties': {
'access_key': {'description': '', 'type': ['string', 'null']},
'last_used': {
'description': '',
'format': 'date-time',
'type': ['string', 'null'],
},
'last_used_from': {'description': '', 'type': ['string', 'null']},
},
'type': 'object',
}
def __init__(
self, access_key=None, last_used=None, last_used_from=None, **kwargs):
super(CredentialKey, self).__init__(**kwargs)
self.access_key = access_key
self.last_used = last_used
self.last_used_from = last_used_from
@schema_property('access_key')
def access_key(self):
return self._property_access_key
@access_key.setter
def access_key(self, value):
if value is None:
self._property_access_key = None
return
self.assert_isinstance(value, "access_key", six.string_types)
self._property_access_key = value
@schema_property('last_used')
def last_used(self):
return self._property_last_used
@last_used.setter
def last_used(self, value):
if value is None:
self._property_last_used = None
return
self.assert_isinstance(value, "last_used", six.string_types + (datetime,))
if not isinstance(value, datetime):
value = parse_datetime(value)
self._property_last_used = value
@schema_property('last_used_from')
def last_used_from(self):
return self._property_last_used_from
@last_used_from.setter
def last_used_from(self, value):
if value is None:
self._property_last_used_from = None
return
self.assert_isinstance(value, "last_used_from", six.string_types)
self._property_last_used_from = value
class CreateCredentialsRequest(Request):
"""
Creates a new set of credentials for the authenticated user.
New key/secret is returned.
Note: Secret will never be returned in any other API call.
If a secret is lost or compromised, the key should be revoked
and a new set of credentials can be created.
"""
_service = "auth"
_action = "create_credentials"
_version = "2.5"
_schema = {
'additionalProperties': False,
'definitions': {},
'properties': {},
'type': 'object',
}
class CreateCredentialsResponse(Response):
"""
Response of auth.create_credentials endpoint.
:param credentials: Created credentials
:type credentials: Credentials
"""
_service = "auth"
_action = "create_credentials"
_version = "2.5"
_schema = {
'definitions': {
'credentials': {
'properties': {
'access_key': {
'description': 'Credentials access key',
'type': ['string', 'null'],
},
'secret_key': {
'description': 'Credentials secret key',
'type': ['string', 'null'],
},
},
'type': 'object',
},
},
'properties': {
'credentials': {
'description': 'Created credentials',
'oneOf': [{'$ref': '#/definitions/credentials'}, {'type': 'null'}],
},
},
'type': 'object',
}
def __init__(
self, credentials=None, **kwargs):
super(CreateCredentialsResponse, self).__init__(**kwargs)
self.credentials = credentials
@schema_property('credentials')
def credentials(self):
return self._property_credentials
@credentials.setter
def credentials(self, value):
if value is None:
self._property_credentials = None
return
if isinstance(value, dict):
value = Credentials.from_dict(value)
else:
self.assert_isinstance(value, "credentials", Credentials)
self._property_credentials = value
class EditUserRequest(Request):
"""
Edit a users' auth data properties
:param user: User ID
:type user: str
:param role: The new user's role within the company
:type role: str
"""
_service = "auth"
_action = "edit_user"
_version = "2.5"
_schema = {
'definitions': {},
'properties': {
'role': {
'description': "The new user's role within the company",
'enum': ['admin', 'superuser', 'user', 'annotator'],
'type': ['string', 'null'],
},
'user': {'description': 'User ID', 'type': ['string', 'null']},
},
'type': 'object',
}
def __init__(
self, user=None, role=None, **kwargs):
super(EditUserRequest, self).__init__(**kwargs)
self.user = user
self.role = role
@schema_property('user')
def user(self):
return self._property_user
@user.setter
def user(self, value):
if value is None:
self._property_user = None
return
self.assert_isinstance(value, "user", six.string_types)
self._property_user = value
@schema_property('role')
def role(self):
return self._property_role
@role.setter
def role(self, value):
if value is None:
self._property_role = None
return
self.assert_isinstance(value, "role", six.string_types)
self._property_role = value
class EditUserResponse(Response):
"""
Response of auth.edit_user endpoint.
:param updated: Number of users updated (0 or 1)
:type updated: float
:param fields: Updated fields names and values
:type fields: dict
"""
_service = "auth"
_action = "edit_user"
_version = "2.5"
_schema = {
'definitions': {},
'properties': {
'fields': {
'additionalProperties': True,
'description': 'Updated fields names and values',
'type': ['object', 'null'],
},
'updated': {
'description': 'Number of users updated (0 or 1)',
'enum': [0, 1],
'type': ['number', 'null'],
},
},
'type': 'object',
}
def __init__(
self, updated=None, fields=None, **kwargs):
super(EditUserResponse, self).__init__(**kwargs)
self.updated = updated
self.fields = fields
@schema_property('updated')
def updated(self):
return self._property_updated
@updated.setter
def updated(self, value):
if value is None:
self._property_updated = None
return
self.assert_isinstance(value, "updated", six.integer_types + (float,))
self._property_updated = value
@schema_property('fields')
def fields(self):
return self._property_fields
@fields.setter
def fields(self, value):
if value is None:
self._property_fields = None
return
self.assert_isinstance(value, "fields", (dict,))
self._property_fields = value
class GetCredentialsRequest(Request):
"""
Returns all existing credential keys for the authenticated user.
Note: Only credential keys are returned.
"""
_service = "auth"
_action = "get_credentials"
_version = "2.5"
_schema = {
'additionalProperties': False,
'definitions': {},
'properties': {},
'type': 'object',
}
class GetCredentialsResponse(Response):
"""
Response of auth.get_credentials endpoint.
:param credentials: List of credentials, each with an empty secret field.
:type credentials: Sequence[CredentialKey]
"""
_service = "auth"
_action = "get_credentials"
_version = "2.5"
_schema = {
'definitions': {
'credential_key': {
'properties': {
'access_key': {'description': '', 'type': ['string', 'null']},
'last_used': {
'description': '',
'format': 'date-time',
'type': ['string', 'null'],
},
'last_used_from': {
'description': '',
'type': ['string', 'null'],
},
},
'type': 'object',
},
},
'properties': {
'credentials': {
'description': 'List of credentials, each with an empty secret field.',
'items': {'$ref': '#/definitions/credential_key'},
'type': ['array', 'null'],
},
},
'type': 'object',
}
def __init__(
self, credentials=None, **kwargs):
super(GetCredentialsResponse, self).__init__(**kwargs)
self.credentials = credentials
@schema_property('credentials')
def credentials(self):
return self._property_credentials
@credentials.setter
def credentials(self, value):
if value is None:
self._property_credentials = None
return
self.assert_isinstance(value, "credentials", (list, tuple))
if any(isinstance(v, dict) for v in value):
value = [CredentialKey.from_dict(v) if isinstance(v, dict) else v for v in value]
else:
self.assert_isinstance(value, "credentials", CredentialKey, is_array=True)
self._property_credentials = value
class LoginRequest(Request):
"""
Get a token based on supplied credentials (key/secret).
Intended for use by users with key/secret credentials that wish to obtain a token
for use with other services. Token will be limited by the same permissions that
exist for the credentials used in this call.
:param expiration_sec: Requested token expiration time in seconds. Not
guaranteed, might be overridden by the service
:type expiration_sec: int
"""
_service = "auth"
_action = "login"
_version = "2.5"
_schema = {
'definitions': {},
'properties': {
'expiration_sec': {
'description': 'Requested token expiration time in seconds. \n Not guaranteed, might be overridden by the service',
'type': ['integer', 'null'],
},
},
'type': 'object',
}
def __init__(
self, expiration_sec=None, **kwargs):
super(LoginRequest, self).__init__(**kwargs)
self.expiration_sec = expiration_sec
@schema_property('expiration_sec')
def expiration_sec(self):
return self._property_expiration_sec
@expiration_sec.setter
def expiration_sec(self, value):
if value is None:
self._property_expiration_sec = None
return
if isinstance(value, float) and value.is_integer():
value = int(value)
self.assert_isinstance(value, "expiration_sec", six.integer_types)
self._property_expiration_sec = value
class LoginResponse(Response):
"""
Response of auth.login endpoint.
:param token: Token string
:type token: str
"""
_service = "auth"
_action = "login"
_version = "2.5"
_schema = {
'definitions': {},
'properties': {
'token': {'description': 'Token string', 'type': ['string', 'null']},
},
'type': 'object',
}
def __init__(
self, token=None, **kwargs):
super(LoginResponse, self).__init__(**kwargs)
self.token = token
@schema_property('token')
def token(self):
return self._property_token
@token.setter
def token(self, value):
if value is None:
self._property_token = None
return
self.assert_isinstance(value, "token", six.string_types)
self._property_token = value
class LogoutRequest(Request):
"""
Removes the authentication cookie from the current session
"""
_service = "auth"
_action = "logout"
_version = "2.5"
_schema = {'additionalProperties': False, 'definitions': {}, 'type': 'object'}
class LogoutResponse(Response):
"""
Response of auth.logout endpoint.
"""
_service = "auth"
_action = "logout"
_version = "2.5"
_schema = {'additionalProperties': False, 'definitions': {}, 'type': 'object'}
class RevokeCredentialsRequest(Request):
"""
Revokes (and deletes) a set (key, secret) of credentials for
the authenticated user.
:param access_key: Credentials key
:type access_key: str
"""
_service = "auth"
_action = "revoke_credentials"
_version = "2.5"
_schema = {
'definitions': {},
'properties': {
'access_key': {
'description': 'Credentials key',
'type': ['string', 'null'],
},
},
'required': ['key_id'],
'type': 'object',
}
def __init__(
self, access_key=None, **kwargs):
super(RevokeCredentialsRequest, self).__init__(**kwargs)
self.access_key = access_key
@schema_property('access_key')
def access_key(self):
return self._property_access_key
@access_key.setter
def access_key(self, value):
if value is None:
self._property_access_key = None
return
self.assert_isinstance(value, "access_key", six.string_types)
self._property_access_key = value
class RevokeCredentialsResponse(Response):
"""
Response of auth.revoke_credentials endpoint.
:param revoked: Number of credentials revoked
:type revoked: int
"""
_service = "auth"
_action = "revoke_credentials"
_version = "2.5"
_schema = {
'definitions': {},
'properties': {
'revoked': {
'description': 'Number of credentials revoked',
'enum': [0, 1],
'type': ['integer', 'null'],
},
},
'type': 'object',
}
def __init__(
self, revoked=None, **kwargs):
super(RevokeCredentialsResponse, self).__init__(**kwargs)
self.revoked = revoked
@schema_property('revoked')
def revoked(self):
return self._property_revoked
@revoked.setter
def revoked(self, value):
if value is None:
self._property_revoked = None
return
if isinstance(value, float) and value.is_integer():
value = int(value)
self.assert_isinstance(value, "revoked", six.integer_types)
self._property_revoked = value
response_mapping = {
LoginRequest: LoginResponse,
LogoutRequest: LogoutResponse,
CreateCredentialsRequest: CreateCredentialsResponse,
GetCredentialsRequest: GetCredentialsResponse,
RevokeCredentialsRequest: RevokeCredentialsResponse,
EditUserRequest: EditUserResponse,
}

View File

@@ -0,0 +1,194 @@
"""
debug service
Debugging utilities
"""
import six
import types
from datetime import datetime
import enum
from dateutil.parser import parse as parse_datetime
from ....backend_api.session import Request, BatchRequest, Response, DataModel, NonStrictDataModel, CompoundRequest, schema_property, StringEnum
class ApiexRequest(Request):
"""
"""
_service = "debug"
_action = "apiex"
_version = "2.5"
_schema = {'definitions': {}, 'properties': {}, 'required': [], 'type': 'object'}
class ApiexResponse(Response):
"""
Response of debug.apiex endpoint.
"""
_service = "debug"
_action = "apiex"
_version = "2.5"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
class EchoRequest(Request):
"""
Return request data
"""
_service = "debug"
_action = "echo"
_version = "2.5"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
class EchoResponse(Response):
"""
Response of debug.echo endpoint.
"""
_service = "debug"
_action = "echo"
_version = "2.5"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
class ExRequest(Request):
"""
"""
_service = "debug"
_action = "ex"
_version = "2.5"
_schema = {'definitions': {}, 'properties': {}, 'required': [], 'type': 'object'}
class ExResponse(Response):
"""
Response of debug.ex endpoint.
"""
_service = "debug"
_action = "ex"
_version = "2.5"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
class PingRequest(Request):
"""
Return a message. Does not require authorization.
"""
_service = "debug"
_action = "ping"
_version = "2.5"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
class PingResponse(Response):
"""
Response of debug.ping endpoint.
:param msg: A friendly message
:type msg: str
"""
_service = "debug"
_action = "ping"
_version = "2.5"
_schema = {
'definitions': {},
'properties': {
'msg': {
'description': 'A friendly message',
'type': ['string', 'null'],
},
},
'type': 'object',
}
def __init__(
self, msg=None, **kwargs):
super(PingResponse, self).__init__(**kwargs)
self.msg = msg
@schema_property('msg')
def msg(self):
return self._property_msg
@msg.setter
def msg(self, value):
if value is None:
self._property_msg = None
return
self.assert_isinstance(value, "msg", six.string_types)
self._property_msg = value
class PingAuthRequest(Request):
"""
Return a message. Requires authorization.
"""
_service = "debug"
_action = "ping_auth"
_version = "2.5"
_schema = {'definitions': {}, 'properties': {}, 'type': 'object'}
class PingAuthResponse(Response):
"""
Response of debug.ping_auth endpoint.
:param msg: A friendly message
:type msg: str
"""
_service = "debug"
_action = "ping_auth"
_version = "2.5"
_schema = {
'definitions': {},
'properties': {
'msg': {
'description': 'A friendly message',
'type': ['string', 'null'],
},
},
'type': 'object',
}
def __init__(
self, msg=None, **kwargs):
super(PingAuthResponse, self).__init__(**kwargs)
self.msg = msg
@schema_property('msg')
def msg(self):
return self._property_msg
@msg.setter
def msg(self, value):
if value is None:
self._property_msg = None
return
self.assert_isinstance(value, "msg", six.string_types)
self._property_msg = value
response_mapping = {
EchoRequest: EchoResponse,
PingRequest: PingResponse,
PingAuthRequest: PingAuthResponse,
ApiexRequest: ApiexResponse,
ExRequest: ExResponse,
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,9 @@
# coding: utf-8
__author__ = 'Szczepan Cieślik'
__email__ = 'szczepan.cieslik@gmail.com'
__version__ = '2.4'
from . import models
from . import fields
from . import errors

View File

@@ -0,0 +1,230 @@
"""Builders to generate in memory representation of model and fields tree."""
from __future__ import absolute_import
from collections import defaultdict
import six
from . import errors
from .fields import NotSet
class Builder(object):
def __init__(self, parent=None, nullable=False, default=NotSet):
self.parent = parent
self.types_builders = {}
self.types_count = defaultdict(int)
self.definitions = set()
self.nullable = nullable
self.default = default
@property
def has_default(self):
return self.default is not NotSet
def register_type(self, type, builder):
if self.parent:
return self.parent.register_type(type, builder)
self.types_count[type] += 1
if type not in self.types_builders:
self.types_builders[type] = builder
def get_builder(self, type):
if self.parent:
return self.parent.get_builder(type)
return self.types_builders[type]
def count_type(self, type):
if self.parent:
return self.parent.count_type(type)
return self.types_count[type]
@staticmethod
def maybe_build(value):
return value.build() if isinstance(value, Builder) else value
def add_definition(self, builder):
if self.parent:
return self.parent.add_definition(builder)
self.definitions.add(builder)
class ObjectBuilder(Builder):
def __init__(self, model_type, *args, **kwargs):
super(ObjectBuilder, self).__init__(*args, **kwargs)
self.properties = {}
self.required = []
self.type = model_type
self.register_type(self.type, self)
def add_field(self, name, field, schema):
_apply_validators_modifications(schema, field)
self.properties[name] = schema
if field.required:
self.required.append(name)
def build(self):
builder = self.get_builder(self.type)
if self.is_definition and not self.is_root:
self.add_definition(builder)
[self.maybe_build(value) for _, value in self.properties.items()]
return '#/definitions/{name}'.format(name=self.type_name)
else:
return builder.build_definition(nullable=self.nullable)
@property
def type_name(self):
module_name = '{module}.{name}'.format(
module=self.type.__module__,
name=self.type.__name__,
)
return module_name.replace('.', '_').lower()
def build_definition(self, add_defintitions=True, nullable=False):
properties = dict(
(name, self.maybe_build(value))
for name, value
in self.properties.items()
)
schema = {
'type': 'object',
'additionalProperties': False,
'properties': properties,
}
if self.required:
schema['required'] = self.required
if self.definitions and add_defintitions:
schema['definitions'] = dict(
(builder.type_name, builder.build_definition(False, False))
for builder in self.definitions
)
return schema
@property
def is_definition(self):
if self.count_type(self.type) > 1:
return True
elif self.parent:
return self.parent.is_definition
else:
return False
@property
def is_root(self):
return not bool(self.parent)
def _apply_validators_modifications(field_schema, field):
for validator in field.validators:
try:
validator.modify_schema(field_schema)
except AttributeError:
pass
class PrimitiveBuilder(Builder):
def __init__(self, type, *args, **kwargs):
super(PrimitiveBuilder, self).__init__(*args, **kwargs)
self.type = type
def build(self):
schema = {}
if issubclass(self.type, six.string_types):
obj_type = 'string'
elif issubclass(self.type, bool):
obj_type = 'boolean'
elif issubclass(self.type, int):
obj_type = 'number'
elif issubclass(self.type, float):
obj_type = 'number'
else:
raise errors.FieldNotSupported(
"Can't specify value schema!", self.type
)
if self.nullable:
obj_type = [obj_type, 'null']
schema['type'] = obj_type
if self.has_default:
schema["default"] = self.default
return schema
class ListBuilder(Builder):
def __init__(self, *args, **kwargs):
super(ListBuilder, self).__init__(*args, **kwargs)
self.schemas = []
def add_type_schema(self, schema):
self.schemas.append(schema)
def build(self):
schema = {'type': 'array'}
if self.nullable:
self.add_type_schema({'type': 'null'})
if self.has_default:
schema["default"] = [self.to_struct(i) for i in self.default]
schemas = [self.maybe_build(s) for s in self.schemas]
if len(schemas) == 1:
items = schemas[0]
else:
items = {'oneOf': schemas}
schema['items'] = items
return schema
@property
def is_definition(self):
return self.parent.is_definition
@staticmethod
def to_struct(item):
from .models import Base
if isinstance(item, Base):
return item.to_struct()
return item
class EmbeddedBuilder(Builder):
def __init__(self, *args, **kwargs):
super(EmbeddedBuilder, self).__init__(*args, **kwargs)
self.schemas = []
def add_type_schema(self, schema):
self.schemas.append(schema)
def build(self):
if self.nullable:
self.add_type_schema({'type': 'null'})
schemas = [self.maybe_build(schema) for schema in self.schemas]
if len(schemas) == 1:
schema = schemas[0]
else:
schema = {'oneOf': schemas}
if self.has_default:
# The default value of EmbeddedField is expected to be an instance
# of a subclass of models.Base, thus have `to_struct`
schema["default"] = self.default.to_struct()
return schema
@property
def is_definition(self):
return self.parent.is_definition

View File

@@ -0,0 +1,21 @@
class ModelCollection(list):
"""`ModelCollection` is list which validates stored values.
Validation is made with use of field passed to `__init__` at each point,
when new value is assigned.
"""
def __init__(self, field):
self.field = field
def append(self, value):
self.field.validate_single_value(value)
super(ModelCollection, self).append(value)
def __setitem__(self, key, value):
self.field.validate_single_value(value)
super(ModelCollection, self).__setitem__(key, value)

View File

@@ -0,0 +1,15 @@
class ValidationError(RuntimeError):
pass
class FieldNotFound(RuntimeError):
pass
class FieldNotSupported(ValueError):
pass

View File

@@ -0,0 +1,488 @@
import datetime
import re
from weakref import WeakKeyDictionary
import six
from dateutil.parser import parse
from .errors import ValidationError
from .collections import ModelCollection
# unique marker for "no default value specified". None is not good enough since
# it is a completely valid default value.
NotSet = object()
class BaseField(object):
"""Base class for all fields."""
types = None
def __init__(
self,
required=False,
nullable=False,
help_text=None,
validators=None,
default=NotSet,
name=None):
self.memory = WeakKeyDictionary()
self.required = required
self.help_text = help_text
self.nullable = nullable
self._assign_validators(validators)
self.name = name
self._validate_name()
if default is not NotSet:
self.validate(default)
self._default = default
@property
def has_default(self):
return self._default is not NotSet
def _assign_validators(self, validators):
if validators and not isinstance(validators, list):
validators = [validators]
self.validators = validators or []
def __set__(self, instance, value):
self._finish_initialization(type(instance))
value = self.parse_value(value)
self.validate(value)
self.memory[instance._cache_key] = value
def __get__(self, instance, owner=None):
if instance is None:
self._finish_initialization(owner)
return self
self._finish_initialization(type(instance))
self._check_value(instance)
return self.memory[instance._cache_key]
def _finish_initialization(self, owner):
pass
def _check_value(self, obj):
if obj._cache_key not in self.memory:
self.__set__(obj, self.get_default_value())
def validate_for_object(self, obj):
value = self.__get__(obj)
self.validate(value)
def validate(self, value):
self._check_types()
self._validate_against_types(value)
self._check_against_required(value)
self._validate_with_custom_validators(value)
def _check_against_required(self, value):
if value is None and self.required:
raise ValidationError('Field is required!')
def _validate_against_types(self, value):
if value is not None and not isinstance(value, self.types):
raise ValidationError(
'Value is wrong, expected type "{types}"'.format(
types=', '.join([t.__name__ for t in self.types])
),
value,
)
def _check_types(self):
if self.types is None:
raise ValidationError(
'Field "{type}" is not usable, try '
'different field type.'.format(type=type(self).__name__))
def to_struct(self, value):
"""Cast value to Python structure."""
return value
def parse_value(self, value):
"""Parse value from primitive to desired format.
Each field can parse value to form it wants it to be (like string or
int).
"""
return value
def _validate_with_custom_validators(self, value):
if value is None and self.nullable:
return
for validator in self.validators:
try:
validator.validate(value)
except AttributeError:
validator(value)
def get_default_value(self):
"""Get default value for field.
Each field can specify its default.
"""
return self._default if self.has_default else None
def _validate_name(self):
if self.name is None:
return
if not re.match('^[A-Za-z_](([\w\-]*)?\w+)?$', self.name):
raise ValueError('Wrong name', self.name)
def structue_name(self, default):
return self.name if self.name is not None else default
class StringField(BaseField):
"""String field."""
types = six.string_types
class IntField(BaseField):
"""Integer field."""
types = (int,)
def parse_value(self, value):
"""Cast value to `int`, e.g. from string or long"""
parsed = super(IntField, self).parse_value(value)
if parsed is None:
return parsed
return int(parsed)
class FloatField(BaseField):
"""Float field."""
types = (float, int)
class BoolField(BaseField):
"""Bool field."""
types = (bool,)
def parse_value(self, value):
"""Cast value to `bool`."""
parsed = super(BoolField, self).parse_value(value)
return bool(parsed) if parsed is not None else None
class ListField(BaseField):
"""List field."""
types = (list,)
def __init__(self, items_types=None, *args, **kwargs):
"""Init.
`ListField` is **always not required**. If you want to control number
of items use validators.
"""
self._assign_types(items_types)
super(ListField, self).__init__(*args, **kwargs)
self.required = False
def get_default_value(self):
default = super(ListField, self).get_default_value()
if default is None:
return ModelCollection(self)
return default
def _assign_types(self, items_types):
if items_types:
try:
self.items_types = tuple(items_types)
except TypeError:
self.items_types = items_types,
else:
self.items_types = tuple()
types = []
for type_ in self.items_types:
if isinstance(type_, six.string_types):
types.append(_LazyType(type_))
else:
types.append(type_)
self.items_types = tuple(types)
def validate(self, value):
super(ListField, self).validate(value)
if len(self.items_types) == 0:
return
for item in value:
self.validate_single_value(item)
def validate_single_value(self, item):
if len(self.items_types) == 0:
return
if not isinstance(item, self.items_types):
raise ValidationError(
'All items must be instances '
'of "{types}", and not "{type}".'.format(
types=', '.join([t.__name__ for t in self.items_types]),
type=type(item).__name__,
))
def parse_value(self, values):
"""Cast value to proper collection."""
result = self.get_default_value()
if not values:
return result
if not isinstance(values, list):
return values
return [self._cast_value(value) for value in values]
def _cast_value(self, value):
if isinstance(value, self.items_types):
return value
else:
if len(self.items_types) != 1:
tpl = 'Cannot decide which type to choose from "{types}".'
raise ValidationError(
tpl.format(
types=', '.join([t.__name__ for t in self.items_types])
)
)
return self.items_types[0](**value)
def _finish_initialization(self, owner):
super(ListField, self)._finish_initialization(owner)
types = []
for type in self.items_types:
if isinstance(type, _LazyType):
types.append(type.evaluate(owner))
else:
types.append(type)
self.items_types = tuple(types)
def _elem_to_struct(self, value):
try:
return value.to_struct()
except AttributeError:
return value
def to_struct(self, values):
return [self._elem_to_struct(v) for v in values]
class EmbeddedField(BaseField):
"""Field for embedded models."""
def __init__(self, model_types, *args, **kwargs):
self._assign_model_types(model_types)
super(EmbeddedField, self).__init__(*args, **kwargs)
def _assign_model_types(self, model_types):
if not isinstance(model_types, (list, tuple)):
model_types = (model_types,)
types = []
for type_ in model_types:
if isinstance(type_, six.string_types):
types.append(_LazyType(type_))
else:
types.append(type_)
self.types = tuple(types)
def _finish_initialization(self, owner):
super(EmbeddedField, self)._finish_initialization(owner)
types = []
for type in self.types:
if isinstance(type, _LazyType):
types.append(type.evaluate(owner))
else:
types.append(type)
self.types = tuple(types)
def validate(self, value):
super(EmbeddedField, self).validate(value)
try:
value.validate()
except AttributeError:
pass
def parse_value(self, value):
"""Parse value to proper model type."""
if not isinstance(value, dict):
return value
embed_type = self._get_embed_type()
return embed_type(**value)
def _get_embed_type(self):
if len(self.types) != 1:
raise ValidationError(
'Cannot decide which type to choose from "{types}".'.format(
types=', '.join([t.__name__ for t in self.types])
)
)
return self.types[0]
def to_struct(self, value):
return value.to_struct()
class _LazyType(object):
def __init__(self, path):
self.path = path
def evaluate(self, base_cls):
module, type_name = _evaluate_path(self.path, base_cls)
return _import(module, type_name)
def _evaluate_path(relative_path, base_cls):
base_module = base_cls.__module__
modules = _get_modules(relative_path, base_module)
type_name = modules.pop()
module = '.'.join(modules)
if not module:
module = base_module
return module, type_name
def _get_modules(relative_path, base_module):
canonical_path = relative_path.lstrip('.')
canonical_modules = canonical_path.split('.')
if not relative_path.startswith('.'):
return canonical_modules
parents_amount = len(relative_path) - len(canonical_path)
parent_modules = base_module.split('.')
parents_amount = max(0, parents_amount - 1)
if parents_amount > len(parent_modules):
raise ValueError("Can't evaluate path '{}'".format(relative_path))
return parent_modules[:parents_amount * -1] + canonical_modules
def _import(module_name, type_name):
module = __import__(module_name, fromlist=[type_name])
try:
return getattr(module, type_name)
except AttributeError:
raise ValueError(
"Can't find type '{}.{}'.".format(module_name, type_name))
class TimeField(StringField):
"""Time field."""
types = (datetime.time,)
def __init__(self, str_format=None, *args, **kwargs):
"""Init.
:param str str_format: Format to cast time to (if `None` - casting to
ISO 8601 format).
"""
self.str_format = str_format
super(TimeField, self).__init__(*args, **kwargs)
def to_struct(self, value):
"""Cast `time` object to string."""
if self.str_format:
return value.strftime(self.str_format)
return value.isoformat()
def parse_value(self, value):
"""Parse string into instance of `time`."""
if value is None:
return value
if isinstance(value, datetime.time):
return value
return parse(value).timetz()
class DateField(StringField):
"""Date field."""
types = (datetime.date,)
default_format = '%Y-%m-%d'
def __init__(self, str_format=None, *args, **kwargs):
"""Init.
:param str str_format: Format to cast date to (if `None` - casting to
%Y-%m-%d format).
"""
self.str_format = str_format
super(DateField, self).__init__(*args, **kwargs)
def to_struct(self, value):
"""Cast `date` object to string."""
if self.str_format:
return value.strftime(self.str_format)
return value.strftime(self.default_format)
def parse_value(self, value):
"""Parse string into instance of `date`."""
if value is None:
return value
if isinstance(value, datetime.date):
return value
return parse(value).date()
class DateTimeField(StringField):
"""Datetime field."""
types = (datetime.datetime,)
def __init__(self, str_format=None, *args, **kwargs):
"""Init.
:param str str_format: Format to cast datetime to (if `None` - casting
to ISO 8601 format).
"""
self.str_format = str_format
super(DateTimeField, self).__init__(*args, **kwargs)
def to_struct(self, value):
"""Cast `datetime` object to string."""
if self.str_format:
return value.strftime(self.str_format)
return value.isoformat()
def parse_value(self, value):
"""Parse string into instance of `datetime`."""
if isinstance(value, datetime.datetime):
return value
if value:
return parse(value)
else:
return None

View File

@@ -0,0 +1,154 @@
import six
from . import parsers, errors
from .fields import BaseField
from .errors import ValidationError
class JsonmodelMeta(type):
def __new__(cls, name, bases, attributes):
cls.validate_fields(attributes)
return super(cls, cls).__new__(cls, name, bases, attributes)
@staticmethod
def validate_fields(attributes):
fields = {
key: value for key, value in attributes.items()
if isinstance(value, BaseField)
}
taken_names = set()
for name, field in fields.items():
structue_name = field.structue_name(name)
if structue_name in taken_names:
raise ValueError('Name taken', structue_name, name)
taken_names.add(structue_name)
class Base(six.with_metaclass(JsonmodelMeta, object)):
"""Base class for all models."""
def __init__(self, **kwargs):
self._cache_key = _CacheKey()
self.populate(**kwargs)
def populate(self, **values):
"""Populate values to fields. Skip non-existing."""
values = values.copy()
fields = list(self.iterate_with_name())
for _, structure_name, field in fields:
if structure_name in values:
field.__set__(self, values.pop(structure_name))
for name, _, field in fields:
if name in values:
field.__set__(self, values.pop(name))
def get_field(self, field_name):
"""Get field associated with given attribute."""
for attr_name, field in self:
if field_name == attr_name:
return field
raise errors.FieldNotFound('Field not found', field_name)
def __iter__(self):
"""Iterate through fields and values."""
for name, field in self.iterate_over_fields():
yield name, field
def validate(self):
"""Explicitly validate all the fields."""
for name, field in self:
try:
field.validate_for_object(self)
except ValidationError as error:
raise ValidationError(
"Error for field '{name}'.".format(name=name),
error,
)
@classmethod
def iterate_over_fields(cls):
"""Iterate through fields as `(attribute_name, field_instance)`."""
for attr in dir(cls):
clsattr = getattr(cls, attr)
if isinstance(clsattr, BaseField):
yield attr, clsattr
@classmethod
def iterate_with_name(cls):
"""Iterate over fields, but also give `structure_name`.
Format is `(attribute_name, structue_name, field_instance)`.
Structure name is name under which value is seen in structure and
schema (in primitives) and only there.
"""
for attr_name, field in cls.iterate_over_fields():
structure_name = field.structue_name(attr_name)
yield attr_name, structure_name, field
def to_struct(self):
"""Cast model to Python structure."""
return parsers.to_struct(self)
@classmethod
def to_json_schema(cls):
"""Generate JSON schema for model."""
return parsers.to_json_schema(cls)
def __repr__(self):
attrs = {}
for name, _ in self:
try:
attr = getattr(self, name)
if attr is not None:
attrs[name] = repr(attr)
except ValidationError:
pass
return '{class_name}({fields})'.format(
class_name=self.__class__.__name__,
fields=', '.join(
'{0[0]}={0[1]}'.format(x) for x in sorted(attrs.items())
),
)
def __str__(self):
return '{name} object'.format(name=self.__class__.__name__)
def __setattr__(self, name, value):
try:
return super(Base, self).__setattr__(name, value)
except ValidationError as error:
raise ValidationError(
"Error for field '{name}'.".format(name=name),
error
)
def __eq__(self, other):
if type(other) is not type(self):
return False
for name, _ in self.iterate_over_fields():
try:
our = getattr(self, name)
except errors.ValidationError:
our = None
try:
their = getattr(other, name)
except errors.ValidationError:
their = None
if our != their:
return False
return True
def __ne__(self, other):
return not (self == other)
class _CacheKey(object):
"""Object to identify model in memory."""

View File

@@ -0,0 +1,106 @@
"""Parsers to change model structure into different ones."""
import inspect
from . import fields, builders, errors
def to_struct(model):
"""Cast instance of model to python structure.
:param model: Model to be casted.
:rtype: ``dict``
"""
model.validate()
resp = {}
for _, name, field in model.iterate_with_name():
value = field.__get__(model)
if value is None:
continue
value = field.to_struct(value)
resp[name] = value
return resp
def to_json_schema(cls):
"""Generate JSON schema for given class.
:param cls: Class to be casted.
:rtype: ``dict``
"""
builder = build_json_schema(cls)
return builder.build()
def build_json_schema(value, parent_builder=None):
from .models import Base
cls = value if inspect.isclass(value) else value.__class__
if issubclass(cls, Base):
return build_json_schema_object(cls, parent_builder)
else:
return build_json_schema_primitive(cls, parent_builder)
def build_json_schema_object(cls, parent_builder=None):
builder = builders.ObjectBuilder(cls, parent_builder)
if builder.count_type(builder.type) > 1:
return builder
for _, name, field in cls.iterate_with_name():
if isinstance(field, fields.EmbeddedField):
builder.add_field(name, field, _parse_embedded(field, builder))
elif isinstance(field, fields.ListField):
builder.add_field(name, field, _parse_list(field, builder))
else:
builder.add_field(
name, field, _create_primitive_field_schema(field))
return builder
def _parse_list(field, parent_builder):
builder = builders.ListBuilder(
parent_builder, field.nullable, default=field._default)
for type in field.items_types:
builder.add_type_schema(build_json_schema(type, builder))
return builder
def _parse_embedded(field, parent_builder):
builder = builders.EmbeddedBuilder(
parent_builder, field.nullable, default=field._default)
for type in field.types:
builder.add_type_schema(build_json_schema(type, builder))
return builder
def build_json_schema_primitive(cls, parent_builder):
builder = builders.PrimitiveBuilder(cls, parent_builder)
return builder
def _create_primitive_field_schema(field):
if isinstance(field, fields.StringField):
obj_type = 'string'
elif isinstance(field, fields.IntField):
obj_type = 'number'
elif isinstance(field, fields.FloatField):
obj_type = 'float'
elif isinstance(field, fields.BoolField):
obj_type = 'boolean'
else:
raise errors.FieldNotSupported(
'Field {field} is not supported!'.format(
field=type(field).__class__.__name__))
if field.nullable:
obj_type = [obj_type, 'null']
schema = {'type': obj_type}
if field.has_default:
schema["default"] = field._default
return schema

View File

@@ -0,0 +1,156 @@
from __future__ import absolute_import
import six
import re
from collections import namedtuple
SCALAR_TYPES = tuple(list(six.string_types) + [int, float, bool])
ECMA_TO_PYTHON_FLAGS = {
'i': re.I,
'm': re.M,
}
PYTHON_TO_ECMA_FLAGS = dict(
(value, key) for key, value in ECMA_TO_PYTHON_FLAGS.items()
)
PythonRegex = namedtuple('PythonRegex', ['regex', 'flags'])
def _normalize_string_type(value):
if isinstance(value, six.string_types):
return six.text_type(value)
else:
return value
def _compare_dicts(one, two):
if len(one) != len(two):
return False
for key, value in one.items():
if key not in one or key not in two:
return False
if not compare_schemas(one[key], two[key]):
return False
return True
def _compare_lists(one, two):
if len(one) != len(two):
return False
they_match = False
for first_item in one:
for second_item in two:
if they_match:
continue
they_match = compare_schemas(first_item, second_item)
return they_match
def _assert_same_types(one, two):
if not isinstance(one, type(two)) or not isinstance(two, type(one)):
raise RuntimeError('Types mismatch! "{type1}" and "{type2}".'.format(
type1=type(one).__name__, type2=type(two).__name__))
def compare_schemas(one, two):
"""Compare two structures that represents JSON schemas.
For comparison you can't use normal comparison, because in JSON schema
lists DO NOT keep order (and Python lists do), so this must be taken into
account during comparison.
Note this wont check all configurations, only first one that seems to
match, which can lead to wrong results.
:param one: First schema to compare.
:param two: Second schema to compare.
:rtype: `bool`
"""
one = _normalize_string_type(one)
two = _normalize_string_type(two)
_assert_same_types(one, two)
if isinstance(one, list):
return _compare_lists(one, two)
elif isinstance(one, dict):
return _compare_dicts(one, two)
elif isinstance(one, SCALAR_TYPES):
return one == two
elif one is None:
return one is two
else:
raise RuntimeError('Not allowed type "{type}"'.format(
type=type(one).__name__))
def is_ecma_regex(regex):
"""Check if given regex is of type ECMA 262 or not.
:rtype: bool
"""
parts = regex.split('/')
if len(parts) == 1:
return False
if len(parts) < 3:
raise ValueError('Given regex isn\'t ECMA regex nor Python regex.')
parts.pop()
parts.append('')
raw_regex = '/'.join(parts)
if raw_regex.startswith('/') and raw_regex.endswith('/'):
return True
return False
def convert_ecma_regex_to_python(value):
"""Convert ECMA 262 regex to Python tuple with regex and flags.
If given value is already Python regex it will be returned unchanged.
:param string value: ECMA regex.
:return: 2-tuple with `regex` and `flags`
:rtype: namedtuple
"""
if not is_ecma_regex(value):
return PythonRegex(value, [])
parts = value.split('/')
flags = parts.pop()
try:
result_flags = [ECMA_TO_PYTHON_FLAGS[f] for f in flags]
except KeyError:
raise ValueError('Wrong flags "{}".'.format(flags))
return PythonRegex('/'.join(parts[1:]), result_flags)
def convert_python_regex_to_ecma(value, flags=[]):
"""Convert Python regex to ECMA 262 regex.
If given value is already ECMA regex it will be returned unchanged.
:param string value: Python regex.
:param list flags: List of flags (allowed flags: `re.I`, `re.M`)
:return: ECMA 262 regex
:rtype: str
"""
if is_ecma_regex(value):
return value
result_flags = [PYTHON_TO_ECMA_FLAGS[f] for f in flags]
result_flags = ''.join(result_flags)
return '/{value}/{flags}'.format(value=value, flags=result_flags)

View File

@@ -0,0 +1,202 @@
"""Predefined validators."""
import re
from six.moves import reduce
from .errors import ValidationError
from . import utilities
class Min(object):
"""Validator for minimum value."""
def __init__(self, minimum_value, exclusive=False):
"""Init.
:param minimum_value: Minimum value for validator.
:param bool exclusive: If `True`, then validated value must be strongly
lower than given threshold.
"""
self.minimum_value = minimum_value
self.exclusive = exclusive
def validate(self, value):
"""Validate value."""
if self.exclusive:
if value <= self.minimum_value:
tpl = "'{value}' is lower or equal than minimum ('{min}')."
raise ValidationError(
tpl.format(value=value, min=self.minimum_value))
else:
if value < self.minimum_value:
raise ValidationError(
"'{value}' is lower than minimum ('{min}').".format(
value=value, min=self.minimum_value))
def modify_schema(self, field_schema):
"""Modify field schema."""
field_schema['minimum'] = self.minimum_value
if self.exclusive:
field_schema['exclusiveMinimum'] = True
class Max(object):
"""Validator for maximum value."""
def __init__(self, maximum_value, exclusive=False):
"""Init.
:param maximum_value: Maximum value for validator.
:param bool exclusive: If `True`, then validated value must be strongly
bigger than given threshold.
"""
self.maximum_value = maximum_value
self.exclusive = exclusive
def validate(self, value):
"""Validate value."""
if self.exclusive:
if value >= self.maximum_value:
tpl = "'{val}' is bigger or equal than maximum ('{max}')."
raise ValidationError(
tpl.format(val=value, max=self.maximum_value))
else:
if value > self.maximum_value:
raise ValidationError(
"'{value}' is bigger than maximum ('{max}').".format(
value=value, max=self.maximum_value))
def modify_schema(self, field_schema):
"""Modify field schema."""
field_schema['maximum'] = self.maximum_value
if self.exclusive:
field_schema['exclusiveMaximum'] = True
class Regex(object):
"""Validator for regular expressions."""
FLAGS = {
'ignorecase': re.I,
'multiline': re.M,
}
def __init__(self, pattern, **flags):
"""Init.
Note, that if given pattern is ECMA regex, given flags will be
**completely ignored** and taken from given regex.
:param string pattern: Pattern of regex.
:param bool flags: Flags used for the regex matching.
Allowed flag names are in the `FLAGS` attribute. The flag value
does not matter as long as it evaluates to True.
Flags with False values will be ignored.
Invalid flags will be ignored.
"""
if utilities.is_ecma_regex(pattern):
result = utilities.convert_ecma_regex_to_python(pattern)
self.pattern, self.flags = result
else:
self.pattern = pattern
self.flags = [self.FLAGS[key] for key, value in flags.items()
if key in self.FLAGS and value]
def validate(self, value):
"""Validate value."""
flags = self._calculate_flags()
try:
result = re.search(self.pattern, value, flags)
except TypeError as te:
raise ValidationError(*te.args)
if not result:
raise ValidationError(
'Value "{value}" did not match pattern "{pattern}".'.format(
value=value, pattern=self.pattern
))
def _calculate_flags(self):
return reduce(lambda x, y: x | y, self.flags, 0)
def modify_schema(self, field_schema):
"""Modify field schema."""
field_schema['pattern'] = utilities.convert_python_regex_to_ecma(
self.pattern, self.flags)
class Length(object):
"""Validator for length."""
def __init__(self, minimum_value=None, maximum_value=None):
"""Init.
Note that if no `minimum_value` neither `maximum_value` will be
specified, `ValueError` will be raised.
:param int minimum_value: Minimum value (optional).
:param int maximum_value: Maximum value (optional).
"""
if minimum_value is None and maximum_value is None:
raise ValueError(
"Either 'minimum_value' or 'maximum_value' must be specified.")
self.minimum_value = minimum_value
self.maximum_value = maximum_value
def validate(self, value):
"""Validate value."""
len_ = len(value)
if self.minimum_value is not None and len_ < self.minimum_value:
tpl = "Value '{val}' length is lower than allowed minimum '{min}'."
raise ValidationError(tpl.format(
val=value, min=self.minimum_value
))
if self.maximum_value is not None and len_ > self.maximum_value:
raise ValidationError(
"Value '{val}' length is bigger than "
"allowed maximum '{max}'.".format(
val=value,
max=self.maximum_value,
))
def modify_schema(self, field_schema):
"""Modify field schema."""
if self.minimum_value:
field_schema['minLength'] = self.minimum_value
if self.maximum_value:
field_schema['maxLength'] = self.maximum_value
class Enum(object):
"""Validator for enums."""
def __init__(self, *choices):
"""Init.
:param [] choices: Valid choices for the field.
"""
self.choices = list(choices)
def validate(self, value):
if value not in self.choices:
tpl = "Value '{val}' is not a valid choice."
raise ValidationError(tpl.format(val=value))
def modify_schema(self, field_schema):
field_schema['enum'] = self.choices

View File

@@ -1,10 +1,8 @@
import requests
import six
import jsonmodels.models
import jsonmodels.fields
import jsonmodels.errors
from . import jsonmodels
from .apimodel import ApiModel
from .datamodel import NonStrictDataModelMixin

View File

@@ -16,6 +16,7 @@ from .request import Request, BatchRequest
from .token_manager import TokenManager
from ..config import load
from ..utils import get_http_session_with_retry, urllib_log_warning_setup
from ...backend_config.environment import backward_compatibility_support
from ...version import __version__
@@ -84,8 +85,11 @@ class Session(TokenManager):
initialize_logging=True,
client=None,
config=None,
http_retries_config=None,
**kwargs
):
# add backward compatibility support for old environment variables
backward_compatibility_support()
if config is not None:
self.config = config
@@ -126,7 +130,7 @@ class Session(TokenManager):
raise ValueError("host is required in init or config")
self.__host = host.strip("/")
http_retries_config = self.config.get(
http_retries_config = http_retries_config or self.config.get(
"api.http.retries", ConfigTree()
).as_plain_ordered_dict()
http_retries_config["status_forcelist"] = self._retry_codes

View File

@@ -23,3 +23,31 @@ class EnvEntry(Entry):
def error(self, message):
print("Environment configuration: {}".format(message))
def backward_compatibility_support():
from ..definitions import ENVIRONMENT_CONFIG, ENVIRONMENT_SDK_PARAMS, ENVIRONMENT_BACKWARD_COMPATIBLE
if not ENVIRONMENT_BACKWARD_COMPATIBLE.get():
return
# Add ALG_ prefix on every TRAINS_ os environment we support
for k, v in ENVIRONMENT_CONFIG.items():
try:
trains_vars = [var for var in v.vars if var.startswith('TRAINS_')]
if not trains_vars:
continue
alg_var = trains_vars[0].replace('TRAINS_', 'ALG_', 1)
if alg_var not in v.vars:
v.vars = tuple(list(v.vars) + [alg_var])
except:
continue
for k, v in ENVIRONMENT_SDK_PARAMS.items():
try:
trains_vars = [var for var in v if var.startswith('TRAINS_')]
if not trains_vars:
continue
alg_var = trains_vars[0].replace('TRAINS_', 'ALG_', 1)
if alg_var not in v:
ENVIRONMENT_SDK_PARAMS[k] = tuple(list(v) + [alg_var])
except:
continue

View File

@@ -94,9 +94,20 @@ class ServiceCommandSection(BaseCommandSection):
def __init__(self, *args, **kwargs):
super(ServiceCommandSection, self).__init__()
kwargs = self._verify_command_states(kwargs)
self._session = self._get_session(*args, **kwargs)
self._list_formatter = ListFormatter(self.service)
@classmethod
def _verify_command_states(cls, kwargs):
"""
Conform and enforce command argument
This is where you can automatically turn on/off switches based on different states.
:param kwargs:
:return: kwargs
"""
return kwargs
@staticmethod
def _get_session(*args, **kwargs):
return Session(*args, **kwargs)

View File

@@ -44,7 +44,7 @@ def main():
sentinel = ''
parse_input = '\n'.join(iter(input, sentinel))
credentials = None
api_host = None
api_server = None
web_server = None
# noinspection PyBroadException
try:
@@ -52,11 +52,11 @@ def main():
if parsed:
# Take the credentials in raw form or from api section
credentials = get_parsed_field(parsed, ["credentials"])
api_host = get_parsed_field(parsed, ["api_server", "host"])
api_server = get_parsed_field(parsed, ["api_server", "host"])
web_server = get_parsed_field(parsed, ["web_server"])
except Exception:
credentials = credentials or None
api_host = api_host or None
api_server = api_server or None
web_server = web_server or None
while not credentials or set(credentials) != {"access_key", "secret_key"}:
@@ -65,63 +65,25 @@ def main():
print('Detected credentials key=\"{}\" secret=\"{}\"'.format(credentials['access_key'],
credentials['secret_key'][0:4] + "***"))
if api_host:
api_host = input_url('API Host', api_host)
web_input = True
if web_server:
host = input_url('WEB Host', web_server)
elif api_server:
web_input = False
host = input_url('API Host', api_server)
else:
print(host_description)
api_host = input_url('API Host', '')
parsed_host = verify_url(api_host)
host = input_url('WEB Host', '')
if parsed_host.netloc.startswith('demoapp.'):
# this is our demo server
api_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('demoapp.', 'demoapi.', 1) + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('demoapp.', 'demofiles.', 1) + parsed_host.path
elif parsed_host.netloc.startswith('app.'):
# this is our application server
api_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('app.', 'api.', 1) + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('app.', 'files.', 1) + parsed_host.path
elif parsed_host.netloc.startswith('demoapi.'):
print('{} is the api server, we need the web server. Replacing \'demoapi.\' with \'demoapp.\''.format(
parsed_host.netloc))
api_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('demoapi.', 'demoapp.', 1) + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('demoapi.', 'demofiles.', 1) + parsed_host.path
elif parsed_host.netloc.startswith('api.'):
print('{} is the api server, we need the web server. Replacing \'api.\' with \'app.\''.format(
parsed_host.netloc))
api_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('api.', 'app.', 1) + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('api.', 'files.', 1) + parsed_host.path
elif parsed_host.port == 8008:
print('Port 8008 is the api port. Replacing 8080 with 8008 for Web application')
api_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc.replace(':8008', ':8080', 1) + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace(':8008', ':8081', 1) + parsed_host.path
elif parsed_host.port == 8080:
api_host = parsed_host.scheme + "://" + parsed_host.netloc.replace(':8080', ':8008', 1) + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace(':8080', ':8081', 1) + parsed_host.path
parsed_host = verify_url(host)
api_host, files_host, web_host = parse_host(parsed_host, allow_input=True)
# on of these two we configured
if not web_input:
web_host = input_url('Web Application Host', web_host)
else:
api_host = ''
web_host = ''
files_host = ''
if not parsed_host.port:
print('Host port not detected, do you wish to use the default 8080 port n/[y]? ', end='')
replace_port = input().lower()
if not replace_port or replace_port == 'y' or replace_port == 'yes':
api_host = parsed_host.scheme + "://" + parsed_host.netloc + ':8008' + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc + ':8080' + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc + ':8081' + parsed_host.path
elif not replace_port or replace_port.lower() == 'n' or replace_port.lower() == 'no':
web_host = input_host_port("Web", parsed_host)
api_host = input_host_port("API", parsed_host)
files_host = input_host_port("Files", parsed_host)
if not api_host:
api_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
api_host = input_url('API Host', api_host)
web_host = input_url('Web Application Host', web_server if web_server else web_host)
files_host = input_url('File Store Host', files_host)
print('\nTRAINS Hosts configuration:\nWeb App: {}\nAPI: {}\nFile Store: {}\n'.format(
@@ -208,13 +170,71 @@ def main():
print('TRAINS-AGENT setup completed successfully.')
def parse_host(parsed_host, allow_input=True):
if parsed_host.netloc.startswith('demoapp.'):
# this is our demo server
api_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('demoapp.', 'demoapi.', 1) + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('demoapp.', 'demofiles.',
1) + parsed_host.path
elif parsed_host.netloc.startswith('app.'):
# this is our application server
api_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('app.', 'api.', 1) + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('app.', 'files.', 1) + parsed_host.path
elif parsed_host.netloc.startswith('demoapi.'):
print('{} is the api server, we need the web server. Replacing \'demoapi.\' with \'demoapp.\''.format(
parsed_host.netloc))
api_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('demoapi.', 'demoapp.', 1) + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('demoapi.', 'demofiles.',
1) + parsed_host.path
elif parsed_host.netloc.startswith('api.'):
print('{} is the api server, we need the web server. Replacing \'api.\' with \'app.\''.format(
parsed_host.netloc))
api_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('api.', 'app.', 1) + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace('api.', 'files.', 1) + parsed_host.path
elif parsed_host.port == 8008:
print('Port 8008 is the api port. Replacing 8080 with 8008 for Web application')
api_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc.replace(':8008', ':8080', 1) + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace(':8008', ':8081', 1) + parsed_host.path
elif parsed_host.port == 8080:
api_host = parsed_host.scheme + "://" + parsed_host.netloc.replace(':8080', ':8008', 1) + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc.replace(':8080', ':8081', 1) + parsed_host.path
elif allow_input:
api_host = ''
web_host = ''
files_host = ''
if not parsed_host.port:
print('Host port not detected, do you wish to use the default 8080 port n/[y]? ', end='')
replace_port = input().lower()
if not replace_port or replace_port == 'y' or replace_port == 'yes':
api_host = parsed_host.scheme + "://" + parsed_host.netloc + ':8008' + parsed_host.path
web_host = parsed_host.scheme + "://" + parsed_host.netloc + ':8080' + parsed_host.path
files_host = parsed_host.scheme + "://" + parsed_host.netloc + ':8081' + parsed_host.path
elif not replace_port or replace_port.lower() == 'n' or replace_port.lower() == 'no':
web_host = input_host_port("Web", parsed_host)
api_host = input_host_port("API", parsed_host)
files_host = input_host_port("Files", parsed_host)
if not api_host:
api_host = parsed_host.scheme + "://" + parsed_host.netloc + parsed_host.path
else:
raise ValueError("Could not parse host name")
return api_host, files_host, web_host
def verify_credentials(api_host, credentials):
"""check if the credentials are valid"""
# noinspection PyBroadException
try:
print('Verifying credentials ...')
if api_host:
Session(api_key=credentials['access_key'], secret_key=credentials['secret_key'], host=api_host)
Session(api_key=credentials['access_key'], secret_key=credentials['secret_key'], host=api_host,
http_retries_config={"total": 2})
print('Credentials verified!')
return True
else:
@@ -256,7 +276,7 @@ def read_manual_credentials():
def input_url(host_type, host=None):
while True:
print('{} configured to: [{}] '.format(host_type, host), end='')
print('{} configured to: {}'.format(host_type, '[{}] '.format(host) if host else ''), end='')
parse_input = input()
if host and (not parse_input or parse_input.lower() == 'yes' or parse_input.lower() == 'y'):
break
@@ -270,11 +290,12 @@ def input_url(host_type, host=None):
def input_host_port(host_type, parsed_host):
print('Enter port for {} host '.format(host_type), end='')
replace_port = input().lower()
return parsed_host.scheme + "://" + parsed_host.netloc + (':{}'.format(replace_port) if replace_port else '') + \
parsed_host.path
return parsed_host.scheme + "://" + parsed_host.netloc + (
':{}'.format(replace_port) if replace_port else '') + parsed_host.path
def verify_url(parse_input):
# noinspection PyBroadException
try:
if not parse_input.startswith('http://') and not parse_input.startswith('https://'):
# if we have a specific port, use http prefix, otherwise assume https

File diff suppressed because it is too large Load Diff

View File

@@ -55,23 +55,23 @@ class EnvironmentConfig(object):
ENVIRONMENT_CONFIG = {
"api.api_server": EnvironmentConfig("TRAINS_API_HOST", "ALG_API_HOST"),
"api.api_server": EnvironmentConfig("TRAINS_API_HOST", ),
"api.credentials.access_key": EnvironmentConfig(
"TRAINS_API_ACCESS_KEY", "ALG_API_ACCESS_KEY"
"TRAINS_API_ACCESS_KEY",
),
"api.credentials.secret_key": EnvironmentConfig(
"TRAINS_API_SECRET_KEY", "ALG_API_SECRET_KEY"
"TRAINS_API_SECRET_KEY",
),
"agent.worker_name": EnvironmentConfig("TRAINS_WORKER_NAME", "ALG_WORKER_NAME"),
"agent.worker_id": EnvironmentConfig("TRAINS_WORKER_ID", "ALG_WORKER_ID"),
"agent.worker_name": EnvironmentConfig("TRAINS_WORKER_NAME", ),
"agent.worker_id": EnvironmentConfig("TRAINS_WORKER_ID", ),
"agent.cuda_version": EnvironmentConfig(
"TRAINS_CUDA_VERSION", "ALG_CUDA_VERSION", "CUDA_VERSION"
"TRAINS_CUDA_VERSION", "CUDA_VERSION"
),
"agent.cudnn_version": EnvironmentConfig(
"TRAINS_CUDNN_VERSION", "ALG_CUDNN_VERSION", "CUDNN_VERSION"
"TRAINS_CUDNN_VERSION", "CUDNN_VERSION"
),
"agent.cpu_only": EnvironmentConfig(
"TRAINS_CPU_ONLY", "ALG_CPU_ONLY", "CPU_ONLY", type=bool
"TRAINS_CPU_ONLY", "CPU_ONLY", type=bool
),
"sdk.aws.s3.key": EnvironmentConfig("AWS_ACCESS_KEY_ID"),
"sdk.aws.s3.secret": EnvironmentConfig("AWS_SECRET_ACCESS_KEY"),
@@ -81,15 +81,15 @@ ENVIRONMENT_CONFIG = {
"sdk.google.storage.credentials_json": EnvironmentConfig("GOOGLE_APPLICATION_CREDENTIALS"),
}
CONFIG_FILE_ENV = EnvironmentConfig("ALG_CONFIG_FILE")
ENVIRONMENT_SDK_PARAMS = {
"task_id": ("TRAINS_TASK_ID", "ALG_TASK_ID"),
"config_file": ("TRAINS_CONFIG_FILE", "ALG_CONFIG_FILE", "TRAINS_CONFIG_FILE"),
"log_level": ("TRAINS_LOG_LEVEL", "ALG_LOG_LEVEL"),
"log_to_backend": ("TRAINS_LOG_TASK_TO_BACKEND", "ALG_LOG_TASK_TO_BACKEND"),
"task_id": ("TRAINS_TASK_ID", ),
"config_file": ("TRAINS_CONFIG_FILE", ),
"log_level": ("TRAINS_LOG_LEVEL", ),
"log_to_backend": ("TRAINS_LOG_TASK_TO_BACKEND", ),
}
ENVIRONMENT_BACKWARD_COMPATIBLE = EnvironmentConfig("TRAINS_AGENT_ALG_ENV", type=bool)
VIRTUAL_ENVIRONMENT_PATH = {
"python2": normalize_path(CONFIG_DIR, "py2venv"),
"python3": normalize_path(CONFIG_DIR, "py3venv"),
@@ -113,15 +113,18 @@ HTTP_HEADERS = {
METADATA_EXTENSION = ".json"
DEFAULT_VENV_UPDATE_URL = (
"https://raw.githubusercontent.com/Yelp/venv-update/v3.2.2/venv_update.py"
"https://raw.githubusercontent.com/Yelp/venv-update/v3.2.4/venv_update.py"
)
WORKING_REPOSITORY_DIR = "task_repository"
DEFAULT_VCS_CACHE = normalize_path(CONFIG_DIR, "vcs-cache")
PIP_EXTRA_INDICES = [
]
DEFAULT_PIP_DOWNLOAD_CACHE = normalize_path(CONFIG_DIR, "pip-download-cache")
ENV_AGENT_GIT_USER = EnvironmentConfig('TRAINS_AGENT_GIT_USER')
ENV_AGENT_GIT_PASS = EnvironmentConfig('TRAINS_AGENT_GIT_PASS')
ENV_TASK_EXECUTE_AS_USER = 'TRAINS_AGENT_EXEC_USER'
ENV_K8S_HOST_MOUNT = 'TRAINS_AGENT_K8S_HOST_MOUNT'
ENV_TASK_EXTRA_PYTHON_PATH = 'TRAINS_AGENT_EXTRA_PYTHON_PATH'
ENV_DOCKER_HOST_MOUNT = EnvironmentConfig('TRAINS_AGENT_K8S_HOST_MOUNT', 'TRAINS_AGENT_DOCKER_HOST_MOUNT')
class FileBuffering(IntEnum):

View File

@@ -0,0 +1 @@

View File

@@ -199,6 +199,20 @@ def get_python_path(script_dir, entry_point, package_api):
return None
def add_python_path(base_path, extra_path):
try:
if not extra_path:
return base_path
python_path_sep = ';' if is_windows_platform() else ':'
base_path = base_path or ''
if not base_path.endswith(python_path_sep):
base_path += python_path_sep
base_path += extra_path.replace(':', python_path_sep)
except:
pass
return base_path
class Singleton(ABCMeta):
_instances = {}
@@ -541,3 +555,17 @@ class ExecutionInfo(NonStrictAttrs):
execution.working_dir = working_dir or ""
return execution
class safe_furl(furl.furl):
@property
def port(self):
return self._port
@port.setter
def port(self, port):
"""
Any port value is valid
"""
self._port = port

View File

@@ -4,7 +4,7 @@ from time import sleep
import requests
import json
from threading import Thread
from packaging import version as packaging_version
from .package.requirements import SimpleVersion
from ..version import __version__
__check_update_thread = None
@@ -30,11 +30,11 @@ def _check_new_version_available():
return None
trains_answer = update_server_releases.get("trains-agent", {})
latest_version = trains_answer.get("version")
cur_version = packaging_version.parse(cur_version)
latest_version = packaging_version.parse(latest_version or '')
if cur_version >= latest_version:
cur_version = cur_version
latest_version = latest_version or ''
if SimpleVersion.compare_versions(cur_version, '>=', latest_version):
return None
patch_upgrade = latest_version.major == cur_version.major and latest_version.minor == cur_version.minor
patch_upgrade = True # latest_version.major == cur_version.major and latest_version.minor == cur_version.minor
return str(latest_version), patch_upgrade, trains_answer.get("description").split("\r\n")

View File

View File

@@ -0,0 +1,74 @@
import os
def daemonize_process(redirect_fd=None):
"""
Detach a process from the controlling terminal and run it in the background as a daemon.
"""
assert redirect_fd is None or isinstance(redirect_fd, int)
# re-spawn in the same directory
WORKDIR = os.getcwd()
# The standard I/O file descriptors are redirected to /dev/null by default.
if hasattr(os, "devnull"):
devnull = os.devnull
else:
devnull = "/dev/null"
try:
# Fork a child process so the parent can exit. This returns control to
# the command-line or shell. It also guarantees that the child will not
# be a process group leader, since the child receives a new process ID
# and inherits the parent's process group ID. This step is required
# to insure that the next call to os.setsid is successful.
pid = os.fork()
except OSError as e:
raise Exception("%s [%d]" % (e.strerror, e.errno))
if pid == 0: # The first child.
# To become the session leader of this new session and the process group
# leader of the new process group, we call os.setsid().
# The process is also guaranteed not to have a controlling terminal.
os.setsid()
# Is ignoring SIGHUP necessary? (Set handlers for asynchronous events.)
# import signal
# signal.signal(signal.SIGHUP, signal.SIG_IGN)
try:
# Fork a second child and exit immediately to prevent zombies. This
# causes the second child process to be orphaned, making the init
# process responsible for its cleanup.
pid = os.fork() # Fork a second child.
except OSError as e:
raise Exception("%s [%d]" % (e.strerror, e.errno))
if pid == 0: # The second child.
# Since the current working directory may be a mounted filesystem, we
# avoid the issue of not being able to unmount the filesystem at
# shutdown time by changing it to the root directory.
os.chdir(WORKDIR)
# We probably don't want the file mode creation mask inherited from
# the parent, so we give the child complete control over permissions.
os.umask(0)
else:
# Exit parent (the first child) of the second child.
os._exit(0)
else:
# Exit parent of the first child.
os._exit(0)
# notice we count on the fact that we keep all file descriptors open,
# since we opened then in the parent process, but the daemon process will use them
# Redirect the standard I/O file descriptors to the specified file /dev/null.
if redirect_fd is None:
redirect_fd = os.open(devnull, os.O_RDWR)
# Duplicate standard input to standard output and standard error.
# standard output (1), standard error (2)
os.dup2(redirect_fd, 1)
os.dup2(redirect_fd, 2)
return 0

View File

@@ -111,10 +111,12 @@ class PackageManager(object):
def out_of_scope_install_package(cls, package_name, *args):
if PackageManager._selected_manager is not None:
try:
return PackageManager._selected_manager._install(package_name, *args)
result = PackageManager._selected_manager._install(package_name, *args)
if result not in (0, None, True):
return False
except Exception:
pass
return
return False
return True
@classmethod
def out_of_scope_freeze(cls):

View File

@@ -14,13 +14,13 @@ import yaml
from time import time
from attr import attrs, attrib, Factory
from pathlib2 import Path
from packaging import version as packaging_version
from requirements import parse
from requirements.requirement import Requirement
from trains_agent.errors import CommandFailedError
from trains_agent.helper.base import rm_tree, NonStrictAttrs, select_for_platform, is_windows_platform
from trains_agent.helper.process import Argv, Executable, DEVNULL, CommandSequence, PathLike
from trains_agent.helper.package.requirements import SimpleVersion
from trains_agent.session import Session
from .base import PackageManager
from .pip_api.venv import VirtualenvPip
@@ -59,7 +59,7 @@ class CondaAPI(PackageManager):
A programmatic interface for controlling conda
"""
MINIMUM_VERSION = packaging_version.parse("4.3.30")
MINIMUM_VERSION = "4.3.30"
def __init__(self, session, path, python, requirements_manager):
# type: (Session, PathLike, float, RequirementsManager) -> None
@@ -93,7 +93,7 @@ class CondaAPI(PackageManager):
)
)
self.conda_version = self.get_conda_version(output)
if packaging_version.parse(self.conda_version) < self.MINIMUM_VERSION:
if SimpleVersion.compare_versions(self.conda_version, '<', self.MINIMUM_VERSION):
raise CommandFailedError(
"conda version '{}' is smaller than minimum supported conda version '{}'".format(
self.conda_version, self.MINIMUM_VERSION
@@ -262,6 +262,7 @@ class CondaAPI(PackageManager):
# this should happen if experiment was executed on non-conda machine or old trains client
conda_supported_req = requirements['pip'] if requirements.get('conda', None) is None else requirements['conda']
conda_supported_req_names = []
pip_requirements = []
for r in conda_supported_req:
try:
marker = list(parse(r))
@@ -271,6 +272,10 @@ class CondaAPI(PackageManager):
continue
m = MarkerRequirement(marker[0])
# conda does not support version control links
if m.vcs:
pip_requirements.append(m)
continue
conda_supported_req_names.append(m.name.lower())
if m.req.name.lower() == 'matplotlib':
has_matplotlib = True
@@ -287,7 +292,6 @@ class CondaAPI(PackageManager):
reqs.append(m)
pip_requirements = []
# if we have a conda list, the rest should be installed with pip,
if requirements.get('conda', None) is not None:
for r in requirements['pip']:
@@ -374,7 +378,7 @@ class CondaAPI(PackageManager):
print(e)
raise e
self.requirements_manager.post_install()
self.requirements_manager.post_install(self.session)
return True
def _parse_conda_result_bad_packges(self, result_dict):
@@ -416,10 +420,14 @@ class CondaAPI(PackageManager):
try:
print('Executing Conda: {}'.format(command.serialize()))
result = command.get_output(stdin=DEVNULL, **kwargs)
if self.session.debug_mode:
print(result)
except Exception as e:
result = e.output if hasattr(e, 'output') else ''
if self.session.debug_mode:
print(result)
if raw:
raise
result = e.output if hasattr(e, 'output') else ''
if raw:
return result

View File

@@ -3,6 +3,7 @@ from typing import Text
from .base import PackageManager
from .requirements import SimpleSubstitution
from ..base import safe_furl as furl
class ExternalRequirements(SimpleSubstitution):
@@ -22,7 +23,7 @@ class ExternalRequirements(SimpleSubstitution):
return False
return True
def post_install(self):
def post_install(self, session):
post_install_req = self.post_install_req
self.post_install_req = []
for req in post_install_req:
@@ -30,7 +31,30 @@ class ExternalRequirements(SimpleSubstitution):
freeze_base = PackageManager.out_of_scope_freeze() or ''
except:
freeze_base = ''
PackageManager.out_of_scope_install_package(req.tostr(markers=False), "--no-deps")
req_line = req.tostr(markers=False)
if req.req.vcs and req_line.startswith('git+'):
try:
url_no_frag = furl(req_line)
url_no_frag.set(fragment=None)
# reverse replace
fragment = req_line[::-1].replace(url_no_frag.url[::-1], '', 1)[::-1]
vcs_url = req_line[4:]
# reverse replace
vcs_url = vcs_url[::-1].replace(fragment[::-1], '', 1)[::-1]
from ..repo import Git
vcs = Git(session=session, url=vcs_url, location=None, revision=None)
vcs._set_ssh_url()
new_req_line = 'git+{}{}'.format(vcs.url_with_auth, fragment)
if new_req_line != req_line:
url_pass = furl(new_req_line).password
print('Replacing original pip vcs \'{}\' with \'{}\''.format(
req_line, new_req_line.replace(url_pass, '****', 1) if url_pass else new_req_line))
req_line = new_req_line
except Exception:
print('WARNING: Failed parsing pip git install, using original line {}'.format(req_line))
PackageManager.out_of_scope_install_package(req_line, "--no-deps")
try:
freeze_post = PackageManager.out_of_scope_freeze() or ''
package_name = list(set(freeze_post['pip']) - set(freeze_base['pip']))
@@ -38,7 +62,8 @@ class ExternalRequirements(SimpleSubstitution):
self.post_install_req_lookup[package_name[0]] = req.req.line
except:
pass
PackageManager.out_of_scope_install_package(req.tostr(markers=False), "--ignore-installed")
if not PackageManager.out_of_scope_install_package(req_line, "--ignore-installed"):
raise ValueError("Failed installing GIT/HTTPs package \'{}\'".format(req_line))
def replace(self, req):
"""

View File

@@ -16,7 +16,7 @@ class HorovodRequirement(SimpleSubstitution):
# match both horovod
return req.name and self.name == req.name.lower()
def post_install(self):
def post_install(self, session):
if self.post_install_req:
PackageManager.out_of_scope_install_package(self.post_install_req.tostr(markers=False))
self.post_install_req = None

View File

@@ -1,22 +1,24 @@
import sys
from itertools import chain
from typing import Text
from typing import Text, Optional
from trains_agent.definitions import PIP_EXTRA_INDICES, PROGRAM_NAME
from trains_agent.helper.package.base import PackageManager
from trains_agent.helper.process import Argv, DEVNULL
from trains_agent.session import Session
class SystemPip(PackageManager):
indices_args = None
def __init__(self, interpreter=None):
# type: (Text) -> ()
def __init__(self, interpreter=None, session=None):
# type: (Optional[Text], Optional[Session]) -> ()
"""
Program interface to the system pip.
"""
self._bin = interpreter or sys.executable
self.session = session
@property
def bin(self):

View File

@@ -15,19 +15,17 @@ class VirtualenvPip(SystemPip, PackageManager):
Program interface to virtualenv pip.
Must be given either path to virtualenv or source command.
Either way, ``self.source`` is exposed.
:param session: a Session object for communication
:param python: interpreter path
:param path: path of virtual environment to create/manipulate
:param python: python version
:param interpreter: path of python interpreter
"""
super(VirtualenvPip, self).__init__(
interpreter
or Path(
path,
select_for_platform(linux="bin/python", windows="scripts/python.exe"),
)
session=session,
interpreter=interpreter or Path(
path, select_for_platform(linux="bin/python", windows="scripts/python.exe"))
)
self.session = session
self.path = path
self.requirements_manager = requirements_manager
self.python = python
@@ -39,7 +37,7 @@ class VirtualenvPip(SystemPip, PackageManager):
if isinstance(requirements, dict) and requirements.get("pip"):
requirements["pip"] = self.requirements_manager.replace(requirements["pip"])
super(VirtualenvPip, self).load_requirements(requirements)
self.requirements_manager.post_install()
self.requirements_manager.post_install(self.session)
def create_flags(self):
"""

View File

@@ -10,11 +10,9 @@ from typing import Text
import attr
import requests
from packaging import version as packaging_version
from packaging.specifiers import SpecifierSet
import six
from .requirements import SimpleSubstitution, FatalSpecsResolutionError
from .requirements import SimpleSubstitution, FatalSpecsResolutionError, SimpleVersion
OS_TO_WHEEL_NAME = {"linux": "linux_x86_64", "windows": "win_amd64"}
@@ -76,6 +74,7 @@ class SimplePytorchRequirement(SimpleSubstitution):
packages = ("torch", "torchvision", "torchaudio")
page_lookup_template = 'https://download.pytorch.org/whl/cu{}/torch_stable.html'
nightly_page_lookup_template = 'https://download.pytorch.org/whl/nightly/cu{}/torch_nightly.html'
torch_page_lookup = {
0: 'https://download.pytorch.org/whl/cpu/torch_stable.html',
80: 'https://download.pytorch.org/whl/cu80/torch_stable.html',
@@ -117,11 +116,23 @@ class SimplePytorchRequirement(SimpleSubstitution):
package_manager.add_extra_install_flags(('-f', extra_url))
@classmethod
def get_torch_page(cls, cuda_version):
def get_torch_page(cls, cuda_version, nightly=False):
try:
cuda = int(cuda_version)
except:
cuda = 0
if nightly:
# then try the nightly builds, it might be there...
torch_url = cls.nightly_page_lookup_template.format(cuda)
try:
if requests.get(torch_url, timeout=10).ok:
cls.torch_page_lookup[cuda] = torch_url
return cls.torch_page_lookup[cuda], cuda
except Exception:
pass
return
# first check if key is valid
if cuda in cls.torch_page_lookup:
return cls.torch_page_lookup[cuda], cuda
@@ -156,8 +167,7 @@ class PytorchRequirement(SimpleSubstitution):
self.os = os_name or self.get_platform()
self.cuda = "cuda{}".format(self.cuda_version).lower()
self.python_version_string = str(self.config["agent.default_python"])
self.python_major_minor_str = '.'.join(packaging_version.parse(
self.python_version_string).base_version.split('.')[:2])
self.python_major_minor_str = '.'.join(self.python_version_string.split('.')[:2])
if '.' not in self.python_major_minor_str:
raise PytorchResolutionError(
"invalid python version {!r} defined in configuration file, key 'agent.default_python': "
@@ -183,6 +193,8 @@ class PytorchRequirement(SimpleSubstitution):
except PytorchResolutionError as e:
self.log.warn("will not be able to install pytorch wheels: %s", e.args[0])
self._original_req = []
@property
def is_conda(self):
return self.package_manager == "conda"
@@ -222,7 +234,6 @@ class PytorchRequirement(SimpleSubstitution):
platform_wheel = "win" if self.get_platform() == "windows" else self.get_platform()
py_ver = self.python_major_minor_str.replace('.', '')
url = None
spec = SpecifierSet(req.format_specs())
last_v = None
# search for our package
for l in links_parser.links:
@@ -234,10 +245,11 @@ class PytorchRequirement(SimpleSubstitution):
# version (ignore +cpu +cu92 etc. + is %2B in the file link)
# version ignore .postX suffix (treat as regular version)
try:
v = packaging_version.parse(parts[1].split('%')[0].split('+')[0])
v = str(parts[1].split('%')[0].split('+')[0])
except Exception:
continue
if v not in spec or (last_v and last_v > v):
if not req.compare_version(v) or \
(last_v and SimpleVersion.compare_versions(last_v, '>', v, ignore_sub_versions=False)):
continue
if not parts[2].endswith(py_ver):
continue
@@ -245,18 +257,26 @@ class PytorchRequirement(SimpleSubstitution):
continue
url = '/'.join(torch_url.split('/')[:-1] + l.split('/'))
last_v = v
# if we found an exact match, use it
try:
if req.specs[0][0] == '==' and \
SimpleVersion.compare_versions(req.specs[0][1], '==', v, ignore_sub_versions=False):
break
except:
pass
return url
def get_url_for_platform(self, req):
# check if package is already installed with system packages
try:
if self.config.get("agent.package_manager.system_site_packages"):
if self.config.get("agent.package_manager.system_site_packages", None):
from pip._internal.commands.show import search_packages_info
installed_torch = list(search_packages_info([req.name]))
op, version = req.specs[0] if req.specs else (None, None)
# notice the comparision order, the first part will make sure we have a valid installed package
if installed_torch[0]['version'] and (installed_torch[0]['version'] == version or not version):
if installed_torch[0]['version'] and req.compare_version(installed_torch[0]['version']):
print('PyTorch: requested "{}" version {}, using pre-installed version {}'.format(
req.name, req.specs[0] if req.specs else 'unspecified', installed_torch[0]['version']))
# package already installed, do nothing
return str(req), True
except:
@@ -275,6 +295,9 @@ class PytorchRequirement(SimpleSubstitution):
torch_url, torch_url_key = SimplePytorchRequirement.get_torch_page(self.cuda_version)
url = self._get_link_from_torch_page(req, torch_url)
if not url and self.config.get("agent.package_manager.torch_nightly", None):
torch_url, torch_url_key = SimplePytorchRequirement.get_torch_page(self.cuda_version, nightly=True)
url = self._get_link_from_torch_page(req, torch_url)
# try one more time, with a lower cuda version (never fallback to CPU):
while not url and torch_url_key > 0:
previous_cuda_key = torch_url_key
@@ -306,20 +329,17 @@ class PytorchRequirement(SimpleSubstitution):
@staticmethod
def match_version(req, options):
versioned_options = sorted(
((packaging_version.parse(fix_version(key)), value) for key, value in options.items()),
((fix_version(key), value) for key, value in options.items()),
key=itemgetter(0),
reverse=True,
)
req.specs = [(op, fix_version(version)) for op, version in req.specs]
if req.specs:
specs = SpecifierSet(req.format_specs())
else:
specs = None
try:
return next(
replacement
for version, replacement in versioned_options
if not specs or version in specs
if req.compare_version(version)
)
except StopIteration:
raise PytorchResolutionError(
@@ -368,7 +388,10 @@ class PytorchRequirement(SimpleSubstitution):
def replace(self, req):
try:
return self._replace(req)
new_req = self._replace(req)
if new_req:
self._original_req.append((req, new_req))
return new_req
except Exception as e:
message = "Exception when trying to resolve python wheel"
self.log.debug(message, exc_info=True)
@@ -383,17 +406,17 @@ class PytorchRequirement(SimpleSubstitution):
except:
pass
try:
result = self._table_lookup(req)
except Exception as e:
exc = e
else:
self.log.debug('Replacing requirement "%s" with %r', req, result)
return result
# try:
# result = self._table_lookup(req)
# except Exception as e:
# exc = e
# else:
# self.log.debug('Replacing requirement "%s" with %r', req, result)
# return result
# self.log.debug(
# "Could not find Pytorch wheel in table, trying manually constructing URL"
# )
self.log.debug(
"Could not find Pytorch wheel in table, trying manually constructing URL"
)
result = ok = None
# try:
# result, ok = self.get_url_for_platform(req)
@@ -404,7 +427,7 @@ class PytorchRequirement(SimpleSubstitution):
if result:
self.log.debug("URL not found: {}".format(result))
exc = PytorchResolutionError(
"Was not able to find pytorch wheel URL: {}".format(exc)
"Could not find pytorch wheel URL for: {} with cuda {} support".format(req, self.cuda_version)
)
# cancel exception chaining
six.raise_from(exc, None)
@@ -412,6 +435,37 @@ class PytorchRequirement(SimpleSubstitution):
self.log.debug('Replacing requirement "%s" with %r', req, result)
return result
def replace_back(self, list_of_requirements): # type: (Dict) -> Dict
"""
:param list_of_requirements: {'pip': ['a==1.0', ]}
:return: {'pip': ['a==1.0', ]}
"""
if not self._original_req:
return list_of_requirements
try:
for k, lines in list_of_requirements.items():
# k is either pip/conda
if k not in ('pip', 'conda'):
continue
for i, line in enumerate(lines):
if not line or line.lstrip().startswith('#'):
continue
parts = [p for p in re.split('\s|=|\.|<|>|~|!|@|#', line) if p]
if not parts:
continue
for req, new_req in self._original_req:
if req.req.name == parts[0]:
# support for pip >= 20.1
if '@' in line:
lines[i] = '{} # {}'.format(str(req), str(new_req))
else:
lines[i] = '{} # {}'.format(line, str(new_req))
break
except:
pass
return list_of_requirements
MAP = {
"windows": {
"cuda100": {

View File

@@ -10,7 +10,6 @@ from operator import itemgetter
from os import path
from typing import Text, List, Type, Optional, Tuple, Dict
from packaging import version as packaging_version
from pathlib2 import Path
from pyhocon import ConfigTree
from requirements import parse
@@ -55,7 +54,17 @@ class MarkerRequirement(object):
if self.specifier:
parts.append(self.format_specs())
elif self.vcs:
# leave the line as is, let pip handle it
if self.line:
parts = [self.line]
else:
# let's build the line manually
parts = [
self.uri,
'@{}'.format(self.revision) if self.revision else '',
'#subdirectory={}'.format(self.subdirectory) if self.subdirectory else ''
]
else:
parts = [self.uri]
@@ -69,8 +78,19 @@ class MarkerRequirement(object):
def __repr__(self):
return '{self.__class__.__name__}[{self}]'.format(self=self)
def format_specs(self):
return ','.join(starmap(operator.add, self.specs))
def format_specs(self, num_parts=None, max_num_parts=None):
max_num_parts = max_num_parts or num_parts
if max_num_parts is None or not self.specs:
return ','.join(starmap(operator.add, self.specs))
op, version = self.specs[0]
for v in self._sub_versions_pep440:
version = version.replace(v, '.')
if num_parts:
version = (version.strip('.').split('.') + ['0'] * num_parts)[:max_num_parts]
else:
version = version.strip('.').split('.')[:max_num_parts]
return op+'.'.join(version)
def __getattr__(self, item):
return getattr(self.req, item)
@@ -99,6 +119,186 @@ class MarkerRequirement(object):
else:
self.specs = greater + smaller
def compare_version(self, requested_version, op=None, num_parts=3):
"""
compare the requested version with the one we have in the spec,
If the requested version is 1.2.3 the self.spec should be 1.2.3*
If the requested version is 1.2 the self.spec should be 1.2*
etc.
:param str requested_version:
:param str op: '==', '>', '>=', '<=', '<', '~='
:param int num_parts: number of parts to compare
:return: True if we answer the requested version
"""
# if we have no specific version, we cannot compare, so assume it's okay
if not self.specs:
return True
version = self.specs[0][1]
op = (op or self.specs[0][0]).strip()
return SimpleVersion.compare_versions(requested_version, op, version)
class SimpleVersion:
_sub_versions_pep440 = ['a', 'b', 'rc', '.post', '.dev', '+', ]
VERSION_PATTERN = r"""
v?
(?:
(?:(?P<epoch>[0-9]+)!)? # epoch
(?P<release>[0-9]+(?:\.[0-9]+)*) # release segment
(?P<pre> # pre-release
[-_\.]?
(?P<pre_l>(a|b|c|rc|alpha|beta|pre|preview))
[-_\.]?
(?P<pre_n>[0-9]+)?
)?
(?P<post> # post release
(?:-(?P<post_n1>[0-9]+))
|
(?:
[-_\.]?
(?P<post_l>post|rev|r)
[-_\.]?
(?P<post_n2>[0-9]+)?
)
)?
(?P<dev> # dev release
[-_\.]?
(?P<dev_l>dev)
[-_\.]?
(?P<dev_n>[0-9]+)?
)?
)
(?:\+(?P<local>[a-z0-9]+(?:[-_\.][a-z0-9]+)*))? # local version
"""
_local_version_separators = re.compile(r"[\._-]")
_regex = re.compile(r"^\s*" + VERSION_PATTERN + r"\s*$", re.VERBOSE | re.IGNORECASE)
@classmethod
def compare_versions(cls, version_a, op, version_b, ignore_sub_versions=True):
"""
Compare two versions based on the op operator
returns bool(version_a op version_b)
Notice: Ignores a/b/rc/post/dev markers on the version
:param str version_a:
:param str op: '==', '===', '>', '>=', '<=', '<', '~='
:param str version_b:
:param bool ignore_sub_versions: if true compare only major.minor.patch
(ignore a/b/rc/post/dev in the comparison)
:return bool: version_a op version_b
"""
if not version_b:
return True
num_parts = 3
if op == '~=':
num_parts = max(num_parts, 2)
op = '=='
ignore_sub_versions = True
elif op == '===':
op = '=='
try:
version_a_key = cls._get_match_key(cls._regex.search(version_a), num_parts, ignore_sub_versions)
version_b_key = cls._get_match_key(cls._regex.search(version_b), num_parts, ignore_sub_versions)
except:
# revert to string based
for v in cls._sub_versions_pep440:
version_a = version_a.replace(v, '.')
version_b = version_b.replace(v, '.')
version_a = (version_a.strip('.').split('.') + ['0'] * num_parts)[:num_parts]
version_b = (version_b.strip('.').split('.') + ['0'] * num_parts)[:num_parts]
version_a_key = ''
version_b_key = ''
for i in range(num_parts):
pad = '{:0>%d}.' % max([9, 1 + len(version_a[i]), 1 + len(version_b[i])])
version_a_key += pad.format(version_a[i])
version_b_key += pad.format(version_b[i])
if op == '==':
return version_a_key == version_b_key
if op == '<=':
return version_a_key <= version_b_key
if op == '>=':
return version_a_key >= version_b_key
if op == '>':
return version_a_key > version_b_key
if op == '<':
return version_a_key < version_b_key
raise ValueError('Unrecognized comparison operator [{}]'.format(op))
@staticmethod
def _parse_letter_version(
letter, # type: str
number, # type: Union[str, bytes, SupportsInt]
):
# type: (...) -> Optional[Tuple[str, int]]
if letter:
# We consider there to be an implicit 0 in a pre-release if there is
# not a numeral associated with it.
if number is None:
number = 0
# We normalize any letters to their lower case form
letter = letter.lower()
# We consider some words to be alternate spellings of other words and
# in those cases we want to normalize the spellings to our preferred
# spelling.
if letter == "alpha":
letter = "a"
elif letter == "beta":
letter = "b"
elif letter in ["c", "pre", "preview"]:
letter = "rc"
elif letter in ["rev", "r"]:
letter = "post"
return letter, int(number)
if not letter and number:
# We assume if we are given a number, but we are not given a letter
# then this is using the implicit post release syntax (e.g. 1.0-1)
letter = "post"
return letter, int(number)
return ()
@staticmethod
def _get_match_key(match, num_parts, ignore_sub_versions):
if ignore_sub_versions:
return (0, tuple(int(i) for i in match.group("release").split(".")[:num_parts]),
(), (), (), (),)
return (
int(match.group("epoch")) if match.group("epoch") else 0,
tuple(int(i) for i in match.group("release").split(".")[:num_parts]),
SimpleVersion._parse_letter_version(match.group("pre_l"), match.group("pre_n")),
SimpleVersion._parse_letter_version(
match.group("post_l"), match.group("post_n1") or match.group("post_n2")
),
SimpleVersion._parse_letter_version(match.group("dev_l"), match.group("dev_n")),
SimpleVersion._parse_local_version(match.group("local")),
)
@staticmethod
def _parse_local_version(local):
# type: (str) -> Optional[LocalType]
"""
Takes a string like abc.1.twelve and turns it into ("abc", 1, "twelve").
"""
if local is not None:
return tuple(
part.lower() if not part.isdigit() else int(part)
for part in SimpleVersion._local_version_separators.split(local)
)
return ()
@six.add_metaclass(ABCMeta)
class RequirementSubstitution(object):
@@ -126,7 +326,7 @@ class RequirementSubstitution(object):
"""
pass
def post_install(self):
def post_install(self, session):
pass
@classmethod
@@ -177,7 +377,7 @@ class SimpleSubstitution(RequirementSubstitution):
if req.specs:
_, version_number = req.specs[0]
assert packaging_version.parse(version_number)
# assert packaging_version.parse(version_number)
else:
version_number = self.get_pip_version(self.name)
@@ -282,12 +482,13 @@ class RequirementsManager(object):
result = map(self.translator.translate, result)
return join_lines(result)
def post_install(self):
def post_install(self, session):
for h in self.handlers:
try:
h.post_install()
h.post_install(session)
except Exception as ex:
print('RequirementsManager handler {} raised exception: {}'.format(h, ex))
raise
def replace_back(self, requirements):
for h in self.handlers:

View File

@@ -22,7 +22,7 @@ class RequirementsTranslator(object):
self.enabled = config["agent.pip_download_cache.enabled"]
Path(self.cache_dir).mkdir(parents=True, exist_ok=True)
self.config = Config()
self.pip = SystemPip(interpreter=interpreter)
self.pip = SystemPip(interpreter=interpreter, session=self._session)
def download(self, url):
self.pip.download_package(url, cache_dir=self.cache_dir)

View File

@@ -83,7 +83,15 @@ def shutdown_docker_process(docker_cmd_contains=None, docker_id=None):
pass
def commit_docker(container_name, docker_cmd_contains=None, docker_id=None):
def commit_docker(container_name, docker_cmd_contains=None, docker_id=None, apply_change=None):
"""
Commit a docker into a new image
:param str container_name: Name for the new image
:param docker_cmd_contains: partial container id to be committed
:param str docker_id: Id of container to be comitted
:param str apply_change: apply Dockerfile instructions to the image that is created
(see docker commit documentation for '--change').
"""
try:
if not docker_id:
docker_id = get_docker_id(docker_cmd_contains=docker_cmd_contains)
@@ -93,7 +101,8 @@ def commit_docker(container_name, docker_cmd_contains=None, docker_id=None):
if docker_id:
# we found our docker, stop it
output = get_bash_output(cmd='docker commit {} {}'.format(docker_id, container_name))
apply_change = '--change=\'{}\''.format(apply_change) if apply_change else ''
output = get_bash_output(cmd='docker commit {} {} {}'.format(apply_change, docker_id, container_name))
return output
except Exception:
pass

View File

@@ -12,6 +12,8 @@ from furl import furl
from pathlib2 import Path
import six
from trains_agent.definitions import ENV_AGENT_GIT_USER, ENV_AGENT_GIT_PASS
from trains_agent.helper.console import ensure_text, ensure_binary
from trains_agent.errors import CommandFailedError
from trains_agent.helper.base import (
@@ -95,7 +97,7 @@ class VCS(object):
:param session: program session
:param url: repository url
:param location: (desired) clone location
:param: desired clone revision
:param revision: desired clone revision
"""
self.session = session
self.log = self.session.get_logger(
@@ -206,7 +208,7 @@ class VCS(object):
)
@classmethod
def resolve_ssh_url(cls, url):
def replace_ssh_url(cls, url):
# type: (Text) -> Text
"""
Replace SSH URL with HTTPS URL when applicable
@@ -240,18 +242,46 @@ class VCS(object):
).url
return url
@classmethod
def replace_http_url(cls, url):
# type: (Text) -> Text
"""
Replace HTTPS URL with SSH URL when applicable
"""
parsed_url = furl(url)
if parsed_url.scheme == "https":
parsed_url.scheme = "ssh"
parsed_url.username = "git"
parsed_url.password = None
# make sure there is no port in the final url (safe_furl support)
parsed_url.port = None
url = parsed_url.url
return url
def _set_ssh_url(self):
"""
Replace instance URL with SSH substitution result and report to log.
According to ``man ssh-add``, ``SSH_AUTH_SOCK`` must be set in order for ``ssh-add`` to work.
"""
if self.session.config.get('agent.force_git_ssh_protocol', None) and self.url:
parsed_url = furl(self.url)
if parsed_url.scheme == "https":
new_url = self.replace_http_url(self.url)
if new_url != self.url:
print("Using SSH credentials - replacing https url '{}' with ssh url '{}'".format(
self.url, new_url))
self.url = new_url
return
if not self.session.config.agent.translate_ssh:
return
ssh_agent_variable = "SSH_AUTH_SOCK"
if not getenv(ssh_agent_variable) and (self.session.config.get('agent.git_user', None) and
self.session.config.get('agent.git_pass', None)):
new_url = self.resolve_ssh_url(self.url)
if not getenv(ssh_agent_variable) and (
(ENV_AGENT_GIT_USER.get() or self.session.config.get('agent.git_user', None)) and
(ENV_AGENT_GIT_PASS.get() or self.session.config.get('agent.git_pass', None))
):
new_url = self.replace_ssh_url(self.url)
if new_url != self.url:
print("Using user/pass credentials - replacing ssh url '{}' with https url '{}'".format(
self.url, new_url))
@@ -392,11 +422,14 @@ class VCS(object):
Add username and password to URL if missing from URL and present in config.
Does not modify ssh URLs.
"""
parsed_url = furl(url)
try:
parsed_url = furl(url)
except ValueError:
return url
if parsed_url.scheme in ["", "ssh"] or parsed_url.scheme.startswith("git"):
return parsed_url.url
config_user = config.get("agent.{}_user".format(cls.executable_name), None)
config_pass = config.get("agent.{}_pass".format(cls.executable_name), None)
config_user = ENV_AGENT_GIT_USER.get() or config.get("agent.{}_user".format(cls.executable_name), None)
config_pass = ENV_AGENT_GIT_PASS.get() or config.get("agent.{}_pass".format(cls.executable_name), None)
if (
(not (parsed_url.username and parsed_url.password))
and config_user
@@ -458,6 +491,16 @@ class Git(VCS):
def pull(self):
self.call("fetch", "--all", "--recurse-submodules", cwd=self.location)
def checkout(self): # type: () -> None
"""
Checkout repository at specified revision
"""
self.call("checkout", self.revision, *self.checkout_flags, cwd=self.location)
try:
self.call("submodule", "update", "--recursive", cwd=self.location)
except:
pass
info_commands = dict(
url=Argv(executable_name, "ls-remote", "--get-url", "origin"),
branch=Argv(executable_name, "rev-parse", "--abbrev-ref", "HEAD"),
@@ -519,11 +562,16 @@ def clone_repository_cached(session, execution, destination):
clone_folder_name = Path(str(furl(repo_url).path)).name # type: str
clone_folder = Path(destination) / clone_folder_name
cached_repo_path = (
Path(session.config["agent.vcs_cache.path"]).expanduser()
/ "{}.{}".format(clone_folder_name, md5(ensure_binary(repo_url)).hexdigest())
/ clone_folder_name
) # type: Path
standalone_mode = session.config.get("agent.standalone_mode", False)
if standalone_mode:
cached_repo_path = clone_folder
else:
cached_repo_path = (
Path(session.config["agent.vcs_cache.path"]).expanduser()
/ "{}.{}".format(clone_folder_name, md5(ensure_binary(repo_url)).hexdigest())
/ clone_folder_name
) # type: Path
vcs = VcsFactory.create(
session, execution_info=execution, location=cached_repo_path
@@ -531,23 +579,25 @@ def clone_repository_cached(session, execution, destination):
if not find_executable(vcs.executable_name):
raise CommandFailedError(vcs.executable_not_found_error_help())
if session.config["agent.vcs_cache.enabled"] and cached_repo_path.exists():
print('Using cached repository in "{}"'.format(cached_repo_path))
else:
print("cloning: {}".format(no_password_url))
rm_tree(cached_repo_path)
# We clone the entire repository, not a specific branch
vcs.clone() # branch=execution.branch)
if not standalone_mode:
if session.config["agent.vcs_cache.enabled"] and cached_repo_path.exists():
print('Using cached repository in "{}"'.format(cached_repo_path))
vcs.pull()
rm_tree(destination)
shutil.copytree(Text(cached_repo_path), Text(clone_folder))
if not clone_folder.is_dir():
raise CommandFailedError(
"copying of repository failed: from {} to {}".format(
cached_repo_path, clone_folder
else:
print("cloning: {}".format(no_password_url))
rm_tree(cached_repo_path)
# We clone the entire repository, not a specific branch
vcs.clone() # branch=execution.branch)
vcs.pull()
rm_tree(destination)
shutil.copytree(Text(cached_repo_path), Text(clone_folder))
if not clone_folder.is_dir():
raise CommandFailedError(
"copying of repository failed: from {} to {}".format(
cached_repo_path, clone_folder
)
)
)
# checkout in the newly copy destination
vcs.location = Text(clone_folder)

View File

@@ -75,9 +75,15 @@ class ResourceMonitor(object):
self._exit_event = Event()
self._gpustat_fail = 0
self._gpustat = gpustat
if not self._gpustat:
self._active_gpus = None
if os.environ.get('NVIDIA_VISIBLE_DEVICES') == 'none':
# NVIDIA_VISIBLE_DEVICES set to none, marks cpu_only flag
# active_gpus == False means no GPU reporting
self._active_gpus = False
elif not self._gpustat:
log.warning('Trains-Agent Resource Monitor: GPU monitoring is not available')
else:
# None means no filtering, report all gpus
self._active_gpus = None
try:
active_gpus = os.environ.get('NVIDIA_VISIBLE_DEVICES', '') or \
@@ -244,8 +250,8 @@ class ResourceMonitor(object):
stats["io_read_mbs"] = BytesSizes.megabytes(io_stats.read_bytes)
stats["io_write_mbs"] = BytesSizes.megabytes(io_stats.write_bytes)
# check if we can access the gpu statistics
if self._gpustat:
# check if we need to monitor gpus and if we can access the gpu statistics
if self._active_gpus is not False and self._gpustat:
try:
gpu_stat = self._gpustat.new_query()
for i, g in enumerate(gpu_stat.gpus):

View File

@@ -4,7 +4,7 @@ from time import sleep
from glob import glob
from tempfile import gettempdir, NamedTemporaryFile
from trains_agent.definitions import ENV_K8S_HOST_MOUNT
from trains_agent.definitions import ENV_DOCKER_HOST_MOUNT
from trains_agent.helper.base import warning
@@ -18,9 +18,27 @@ class Singleton(object):
_pid_file = None
_lock_file_name = sep+prefix+sep+'global.lock'
_lock_timeout = 10
_pid = None
@classmethod
def register_instance(cls, unique_worker_id=None, worker_name=None, api_client=None):
def update_pid_file(cls):
new_pid = str(os.getpid())
if not cls._pid_file or cls._pid == new_pid:
return
old_name = cls._pid_file.name
parts = cls._pid_file.name.split(os.path.sep)
parts[-1] = parts[-1].replace(cls.sep + cls._pid + cls.sep, cls.sep + new_pid + cls.sep)
new_pid_file = os.path.sep.join(parts)
cls._pid = new_pid
cls._pid_file.name = new_pid_file
# we need to rename to match new pid
try:
os.rename(old_name, new_pid_file)
except:
pass
@classmethod
def register_instance(cls, unique_worker_id=None, worker_name=None, api_client=None, allow_double=False):
"""
# Exit the process if another instance of us is using the same worker_id
@@ -47,8 +65,9 @@ class Singleton(object):
f.write(bytes(os.getpid()))
f.flush()
try:
ret = cls._register_instance(unique_worker_id=unique_worker_id, worker_name=worker_name,
api_client=api_client)
ret = cls._register_instance(
unique_worker_id=unique_worker_id, worker_name=worker_name,
api_client=api_client, allow_double=allow_double)
except:
ret = None, None
@@ -60,7 +79,7 @@ class Singleton(object):
return ret
@classmethod
def _register_instance(cls, unique_worker_id=None, worker_name=None, api_client=None):
def _register_instance(cls, unique_worker_id=None, worker_name=None, api_client=None, allow_double=False):
if cls.worker_id:
return cls.worker_id, cls.instance_slot
# make sure we have a unique name
@@ -85,7 +104,7 @@ class Singleton(object):
pass
worker = None
if api_client and os.environ.get(ENV_K8S_HOST_MOUNT) and uid:
if api_client and ENV_DOCKER_HOST_MOUNT.get() and uid:
try:
worker = [w for w in api_client.workers.get_all() if w.id == uid]
except Exception:
@@ -105,7 +124,11 @@ class Singleton(object):
continue
if uid == unique_worker_id:
return None, None
if allow_double:
warning('Instance with the same WORKER_ID [{}] was found on this machine. '
'We are ignoring it, make sure this not a mistake.'.format(unique_worker_id))
else:
return None, None
slots[slot] = uid
@@ -124,8 +147,9 @@ class Singleton(object):
unique_worker_id = worker_name + cls.worker_name_sep + str(cls.instance_slot)
# create lock
cls._pid_file = NamedTemporaryFile(dir=cls._get_temp_folder(),
prefix=cls.prefix + cls.sep + str(os.getpid()) + cls.sep, suffix=cls.ext)
cls._pid = str(os.getpid())
cls._pid_file = NamedTemporaryFile(
dir=cls._get_temp_folder(), prefix=cls.prefix + cls.sep + cls._pid + cls.sep, suffix=cls.ext)
cls._pid_file.write(('{}\n{}'.format(unique_worker_id, cls.instance_slot)).encode())
cls._pid_file.flush()
cls.worker_id = unique_worker_id
@@ -134,6 +158,10 @@ class Singleton(object):
@classmethod
def _get_temp_folder(cls):
if os.environ.get(ENV_K8S_HOST_MOUNT):
return os.environ.get(ENV_K8S_HOST_MOUNT).split(':')[-1]
if ENV_DOCKER_HOST_MOUNT.get():
return ENV_DOCKER_HOST_MOUNT.get().split(':')[-1]
return gettempdir()
@classmethod
def get_slot(cls):
return cls.instance_slot or 0

View File

@@ -35,6 +35,7 @@ def get_parser():
for group_name, group in groups:
p = parser if not group_name else parser.add_argument_group(group_name)
for key, value in group:
p.add_argument(key, **value)
aliases = value.pop("aliases", [])
p.add_argument(key, *aliases, **value)
return top_parser

View File

@@ -30,6 +30,17 @@ WORKER_ARGS = {
'type': lambda x: x.upper(),
'default': 'INFO',
},
'--gpus': {
'help': 'Specify active GPUs for the daemon to use (docker / virtual environment), '
'Equivalent to setting NVIDIA_VISIBLE_DEVICES '
'Examples: --gpus 0 or --gpu 0,1,2 or --gpus all',
'group': 'Docker support',
},
'--cpu-only': {
'help': 'Disable GPU access for the daemon, only use CPU in either docker or virtual environment',
'action': 'store_true',
'group': 'Docker support',
},
}
DAEMON_ARGS = dict({
@@ -45,17 +56,6 @@ DAEMON_ARGS = dict({
'default': False,
'group': 'Docker support',
},
'--gpus': {
'help': 'Specify active GPUs for the daemon to use (docker / virtual environment), '
'Equivalent to setting NVIDIA_VISIBLE_DEVICES '
'Examples: --gpus 0 or --gpu 0,1,2 or --gpus all',
'group': 'Docker support',
},
'--cpu-only': {
'help': 'Disable GPU access for the daemon, only use CPU in either docker or virtual environment',
'action': 'store_true',
'group': 'Docker support',
},
'--force-current-version': {
'help': 'Force trains-agent to use the current trains-agent version when running in the docker',
'action': 'store_true',
@@ -72,6 +72,19 @@ DAEMON_ARGS = dict({
'help': 'Do not use any network connects, assume everything is pre-installed',
'action': 'store_true',
},
'--services-mode': {
'help': 'Launch multiple long-term docker services. Implies docker & cpu-only flags.',
'action': 'store_true',
},
'--create-queue': {
'help': 'Create requested queue if it does not exist already.',
'action': 'store_true',
},
'--detached': {
'help': 'Detached mode, run agent in the background',
'action': 'store_true',
'aliases': ['-d'],
},
}, **WORKER_ARGS)
@@ -105,6 +118,17 @@ COMMANDS = {
'help': 'Do not use any network connects, assume everything is pre-installed',
'action': 'store_true',
},
'--docker': {
'help': 'Run execution task inside a docker (v19.03 and above). Optional args <image> <arguments> or '
'specify default docker image in agent.default_docker.image / agent.default_docker.arguments'
'use --gpus/--cpu-only (or set NVIDIA_VISIBLE_DEVICES) to limit gpu visibility for docker',
'nargs': '*',
'default': False,
},
'--clone': {
'help': 'Clone the experiment before execution, and execute the cloned experiment',
'action': 'store_true',
},
}, **WORKER_ARGS),
},
'build': {
@@ -122,6 +146,12 @@ COMMANDS = {
'help': 'Where to build the task\'s virtual environment and source code. '
'When used with --docker, target docker image name to create',
},
'--install-globally': {
'help': 'Install required python packages before creating the virtual environment used to execute an '
'experiment, and use the \'agent.package_manager.system_site_packages\' virtual env option. '
'Note: when --docker is used, install-globally is always true',
'action': 'store_true',
},
'--docker': {
'help': 'Build the experiment inside a docker (v19.03 and above). Optional args <image> <arguments> or '
'specify default docker image in agent.default_docker.image / agent.default_docker.arguments'
@@ -129,18 +159,15 @@ COMMANDS = {
'nargs': '*',
'default': False,
},
'--gpus': {
'help': 'Specify active GPUs for the docker to use'
'Equivalent to setting NVIDIA_VISIBLE_DEVICES '
'Examples: --gpus 0 or --gpu 0,1,2 or --gpus all',
},
'--cpu-only': {
'help': 'Disable GPU access (cpu only) for the docker',
'action': 'store_true',
},
'--python-version': {
'help': 'Virtual environment python version to use',
},
'--entry-point': {
'help': 'Run the task in the new docker. There are two options:\nEither add "reuse_task" to run the '
'given task in the docker, or "clone_task" to first clone the given task and then run it in the docker',
'default': False,
'choices': ['reuse_task', 'clone_task'],
}
}, **WORKER_ARGS),
},
'list': {

View File

@@ -15,7 +15,7 @@ from pyhocon import ConfigFactory, HOCONConverter, ConfigTree
from trains_agent.backend_api.session import Session as _Session, Request
from trains_agent.backend_api.session.client import APIClient
from trains_agent.backend_config.defs import LOCAL_CONFIG_FILE_OVERRIDE_VAR, LOCAL_CONFIG_FILES
from trains_agent.definitions import ENVIRONMENT_CONFIG, ENV_TASK_EXECUTE_AS_USER
from trains_agent.definitions import ENVIRONMENT_CONFIG, ENV_TASK_EXECUTE_AS_USER, ENVIRONMENT_BACKWARD_COMPATIBLE
from trains_agent.errors import APIError
from trains_agent.helper.base import HOCONEncoder
from trains_agent.helper.process import Argv
@@ -63,6 +63,7 @@ def tree(*args):
class Session(_Session):
version = __version__
force_debug = False
def __init__(self, *args, **kwargs):
# make sure we set the environment variable so the parent session opens the correct file
@@ -77,17 +78,27 @@ class Session(_Session):
os.environ['CUDA_VISIBLE_DEVICES'] = os.environ['NVIDIA_VISIBLE_DEVICES'] = 'none'
if kwargs.get('gpus') and not os.environ.get('KUBERNETES_SERVICE_HOST') \
and not os.environ.get('KUBERNETES_PORT'):
os.environ['CUDA_VISIBLE_DEVICES'] = os.environ['NVIDIA_VISIBLE_DEVICES'] = kwargs.get('gpus')
# CUDA_VISIBLE_DEVICES does not support 'all'
if kwargs.get('gpus') == 'all':
os.environ.pop('CUDA_VISIBLE_DEVICES', None)
os.environ['NVIDIA_VISIBLE_DEVICES'] = kwargs.get('gpus')
else:
os.environ['CUDA_VISIBLE_DEVICES'] = os.environ['NVIDIA_VISIBLE_DEVICES'] = kwargs.get('gpus')
if kwargs.get('only_load_config'):
from trains_agent.backend_api.config import load
self.config = load()
else:
super(Session, self).__init__(*args, **kwargs)
# set force debug mode, if it's on:
if Session.force_debug:
self.config["agent"]["debug"] = True
self.log = self.get_logger(__name__)
self.trace = kwargs.get('trace', False)
self._config_file = kwargs.get('config_file') or \
os.environ.get(LOCAL_CONFIG_FILE_OVERRIDE_VAR) or LOCAL_CONFIG_FILES[0]
self.api_client = APIClient(session=self, api_version="2.4")
self.api_client = APIClient(session=self, api_version="2.5")
# HACK make sure we have python version to execute,
# if nothing was specific, use the one that runs us
def_python = ConfigValue(self.config, "agent.default_python")
@@ -95,8 +106,10 @@ class Session(_Session):
def_python.set("{version.major}.{version.minor}".format(version=sys.version_info))
# HACK: backwards compatibility
os.environ['ALG_CONFIG_FILE'] = self._config_file
os.environ['SM_CONFIG_FILE'] = self._config_file
if ENVIRONMENT_BACKWARD_COMPATIBLE.get():
os.environ['ALG_CONFIG_FILE'] = self._config_file
os.environ['SM_CONFIG_FILE'] = self._config_file
if not self.config.get('api.host', None) and self.config.get('api.api_server', None):
self.config['api']['host'] = self.config.get('api.api_server')
@@ -152,9 +165,16 @@ class Session(_Session):
logger.propagate = True
return TrainsAgentLogger(logger)
@staticmethod
def set_debug_mode(enable):
if enable:
import logging
logging.basicConfig(level=logging.DEBUG)
Session.force_debug = enable
@property
def debug_mode(self):
return self.config.get("agent.debug", False)
return Session.force_debug or self.config.get("agent.debug", False)
@property
def config_file(self):

View File

@@ -1 +1 @@
__version__ = '0.13.3'
__version__ = '0.15.2rc0'