Python SDK

WARNING

This SDK tool is under heavy development! Currently there has yet to be a stable version release, please feel free to open any issue regarding this SDK in our community repo

#Requirements

  • Python 3.8+
  • Pip | Poetry

#Installation

Install it directly into an activated virtual environment:

pip
poetry
Copy

pip install instill-sdk

WARNING

If your host machine is on arm64 architecture (including Apple silicon machines, equipped with m1/m2 processors), there are some issues when installing grpcio within conda environment. You will have to manually build and install it like below. Read more about this issue here.


GRPC_PYTHON_LDFLAGS=" -framework CoreFoundation" pip install grpcio --no-binary :all:

#Check Import

After installation, you can check if it has been installed correctly:


python
>>> import instill
>>> instill.__version__

#Config Instill Core or Instill Cloud Instance

Before we can start using this SDK, you will need to create a config file under this path ${HOME}/.config/instill/config.yaml, and within that path you will need to fill in some basic parameters for your desired host.1

Within the config file, you can define multiple instances with the alias of your liking, later in the SDK you can refer to this alias to switch between instances.2


hosts:
alias1:
url: str
secure: bool
token: str
alias2:
url: str
secure: bool
token: str
...
...

Example:


hosts:
default:
url: localhost:8080
secure: false
token: instill_sk***
cloud:
url: api.instill.tech
secure: true
token: instill_sk***

#Usage

You can also find some notebook examples on our GitHub repo

#Create Client

Simply import the get_client function to get the client that are connected to all services with the config you setup previously.


from instill.clients import get_client
client = get_client()

If you have not set up Instill VDP or Instill Model, you will get a warning like this:


2023-09-27 18:49:04,871.871 WARNING Instill VDP is not serving, VDP functionalities will not work
2023-09-27 18:49:04,907.907 WARNING Instill Model is not serving, Model functionalities will not work

You can check the readiness of each service:


client.mgmt_service.is_serving()
# True
client.connector_service.is_serving()
# True
client.pipeline_service.is_serving()
# True
client.model_service.is_serving()
# True

INFO

Depends on which project(Instill VDP or Instill Model or both) you had launched locally, some services might not be available.

After making sure all desired services are serving, we can check the user status by:


client.mgmt_service.get_user()

If you have a valid api_token in your config file, you should see something like this:


name: "users/admin"
uid: "4767b74d-640a-4cdf-9c6d-7bb0e36098a0"
id: "admin"
type: OWNER_TYPE_USER
create_time {
seconds: 1695589596
nanos: 36522000
}
update_time {
seconds: 1695589749
nanos: 544980000
}
email: "hello@instill.tech"
first_name: "Instill"
last_name: "AI"
org_name: "Instill AI"
role: "hobbyist"
newsletter_subscription: true
cookie_token: ""

#Create Resource

#Create Model

Let's say we want to serve a yolov7 model from github with the following configs


model = {
"model_name": "yolov7",
"model_repo": "instill-ai/model-yolov7-dvc",
"model_tag": "v1.0-cpu",
}

Simply import the GithubModel resource and fill in the corresponding fields


from instill.resources.model import GithubModel
yolov7 = GithubModel(
client=client,
name=model["model_name"],
model_repo=model["model_repo"],
model_tag=model["model_tag"],
)

After the creation is done, we can check the state of the model3


yolov7.get_state()
# 1
# means STATE_OFFLINE

Now we can deploy the model


yolov7.deploy()

Check the status


yolov7.get_state()
# 2
# means STATE_ONLINE

Trigger the model with the correct task type4


from instill.resources import model_pb, task_detection
task_inputs = [
model_pb.TaskInput(
detection=task_detection.DetectionInput(
image_url="https://artifacts.instill.tech/imgs/dog.jpg"
)
),
model_pb.TaskInput(
detection=task_detection.DetectionInput(
image_url="https://artifacts.instill.tech/imgs/bear.jpg"
)
),
model_pb.TaskInput(
detection=task_detection.DetectionInput(
image_url="https://artifacts.instill.tech/imgs/polar-bear.jpg"
)
),
]
outputs = yolov7(task_inputs=task_inputs)

Now if you print the outputs, you will get a list of specific task output, in this case is a list of TASK_DETECTION output


[detection {
objects {
category: "dog"
score: 0.958271801
bounding_box {
top: 102
left: 324
width: 208
height: 403
}
}
objects {
category: "dog"
score: 0.945684791
bounding_box {
top: 198
left: 130
width: 198
height: 236
}
}
}
, detection {
objects {
category: "bear"
score: 0.968335629
bounding_box {
top: 85
left: 291
width: 554
height: 756
}
}
}
, detection {
objects {
category: "bear"
score: 0.948612273
bounding_box {
top: 458
left: 1373
width: 1298
height: 2162
}
}
}
]

#Create Connector

With similiar conecpt as creating model, below is the steps to create a instill model connector

First import our predefined InstillModelConnector


from instill.resources import InstillModelConnector, connector_pb

Then we set up the connector resource information5


# specify the `Instill Model` host url
instill_model = InstillModelConnector(
client,
name="instill",
server_url="http://api-gateway:8080",
)

After the connector is created, the state should be STATE_DISCONNECTED


instill_model.get_state() == connector_pb.ConnectorResource.STATE_DISCONNECTED
# True

Now we can test the connection for the newly configured connector, to make sure the connection with the host can be established


instill_model.test() == connector_pb.ConnectorResource.STATE_CONNECTED
# True

#Create Pipeline

Since we have created a Instill Model Connector that connect to our Instill Model instance, we can now create a pipeline that utilize both Instill VDP and Instill Model

First we import Pipeline class and other helper functions


from instill.resources import (
Pipeline,
pipeline_pb,
create_start_operator,
create_end_operator,
create_recipe,
)

To Form a pipeine, it required a start operator and a end operator, we have helper functions to create both


# create start operator
start_operator_component = create_start_operator(
{"metadata": {"input": {"title": "input", "type": "image"}}}
)
# create end operator
end_operator_component = create_end_operator(
config={
"input": {"output": "{ yolov7.output.objects }"},
"metadata": {"output": {}},
}
)

Now that we have both start operator and end operator ready, we can move out to create a model component. From the already defined instill Model Connector, we can now utilize the models serving on Instill Model, import them as a component.


# create model connector component from the connector resource we had previously
# here we need to specify which model we want to use on our `Instill Model` instance
# in this case there is only one model we deployed, which is the yolov7 model
instill_model_connector_component = instill_model.create_component(
name="yolov7",
config={
"input": {
"task": "TASK_DETECTION",
"image_base64": "{ start.input }",
"model_namespace": "admin",
"model_id": "yolov7",
},
},
)

We now have all the components ready for the pipeline. Next, we add them into the recipe and create a pipeline.


# create a recipe to construct the pipeline
recipe = create_recipe([start_operator_component, instill_model_connector_component, end_operator_component])
# create pipeline
instill_model_pipeline = Pipeline(
client=client, name="instill-model-pipeline", recipe=recipe
)

Finally the pipeline is done, now let us test it by triggering it!


# we can trigger the pipeline now
i = Struct()
i.update(
{
"input": base64.b64encode(
requests.get(
"https://artifacts.instill.tech/imgs/dog.jpg", timeout=5
).content
).decode("ascii")
}
)
# verify the output
instill_model_pipeline([i])[0][0]["output"][0]["category"] == "dog"

#Footnotes

  1. You can obtain an api_token, by simply going to Settings > API Tokens page from the console, no matter it is Instill Core or Instill Cloud.

  2. SDK will load the configs for alias named default when start up. So it is required to have at least one instance named default.

  3. Deploy model

  4. Check out our supported tasks to learn more, or read our json schema directly

  5. Find out the resource definition in our json schema

Last updated: 1/2/2024, 4:47:25 PM