.svg)
Scan your ML models with 4 lines of code
Quickly and easily scan, test and debug your ML models by using our Python library and testing server. We integrate with any Python model.
import giskard
from sklearn.pipeline import Pipeline
# Pipeline for the sklearn model
clf = Pipeline(...)
clf.fit(...)
# Wrap your Pandas DataFrame
dataset = giskard.Dataset(
df=titanic_df, target="Survived"
)
# Wrap your model
model = giskard.Model(
model=clf.predict_proba,
model_type="classification"
)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
from sklearn.pipeline import Pipeline
# Pipeline for the sklearn model
clf = Pipeline(...)
clf.fit(...)
# Wrap your Pandas DataFrame
dataset = giskard.Dataset(
df=titanic_df, target="Survived"
)
# Wrap your model
model = giskard.Model(
model=clf.predict_proba,
model_type="classification"
)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
import giskard
from transformers import AutoTokenizer
from transformers import TFAutoModel
tk = AutoTokenizer.from_pretrained(...)
hf = TFAutoModel.from_pretrained(...)
# Pipeline for the model prediction
def pred_func(df):
return softmax(hf(**tk(...).logits))
# Wrap your Pandas DataFrame and model
dataset = giskard.Dataset(df=text_df, ...)
model = giskard.Model(model=pred_func, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
from transformers import AutoTokenizer
from transformers import TFAutoModel
tk = AutoTokenizer.from_pretrained(...)
hf = TFAutoModel.from_pretrained(...)
# Pipeline for the model prediction
def pred_func(df):
return softmax(hf(**tk(...).logits))
# Wrap your Pandas DataFrame and model
dataset = giskard.Dataset(df=text_df, ...)
model = giskard.Model(model=pred_func, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
import giskard
from torchtext.models
import XLMR_BASE_ENCODER
model = XLMR_BASE_ENCODER.get_model(head=h)
# Pipeline for the model prediction
def pred_func(df):
output_df = DataLoader(df.map(T)) return [model(i) for i in output_df]
# Wrap your Pandas DataFrame and model
dataset = giskard.Dataset(df=text_df, ...)
model = giskard.Model(model=pred_func, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
from torchtext.models
import XLMR_BASE_ENCODER
model = XLMR_BASE_ENCODER.get_model(head=h)
# Pipeline for the model prediction
def pred_func(df):
output_df = DataLoader(df.map(T)) return [model(i) for i in output_df]
# Wrap your Pandas DataFrame and model
dataset = giskard.Dataset(df=text_df, ...)
model = giskard.Model(model=pred_func, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
import giskard
model = ... # tensorflow model
# Define a custom wrapper
class MyTensorFlowModel(giskard.Model): def model_predict(self, df):
return self.model.predict(
pipeline.transform(df))
# Wrap your Pandas DataFrame and model
dataset = giskard.Dataset(df, ...)
model = MyTensorFlowModel(model, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
model = ... # tensorflow model
# Define a custom wrapper
class MyTensorFlowModel(giskard.Model): def model_predict(self, df):
return self.model.predict(
pipeline.transform(df))
# Wrap your Pandas DataFrame and model
dataset = giskard.Dataset(df, ...)
model = MyTensorFlowModel(model, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
import giskard
from langchain import chains, prompts
llm = ...
prompt = prompts.PromptTemplate( input_variables=["product"], template="..."
)
chain = chains.LLMChain(
llm=llm,
prompt=prompt
)
# Wrap your Pandas DataFrame and model
dataset = giskard.Dataset(df, ...)
model = giskard.Model(chain, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
from langchain import chains, prompts
llm = ...
prompt = prompts.PromptTemplate( input_variables=["product"], template="..."
)
chain = chains.LLMChain(
llm=llm,
prompt=prompt
)
# Wrap your Pandas DataFrame and model
dataset = giskard.Dataset(df, ...)
model = giskard.Model(chain, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
import giskard, requests
def pred_func(input_data):
# Set up the API endpoint URL
api = "https://api.example.com/predict"
# Send GET request to API & get response
response = requests.get(
api, params={"input": input_data}
)
# Extract predictions from JSON response
return ...
# Wrap your Pandas DataFrame and model dataset = giskard.Dataset(df, ...)
model = giskard.Model(pred_func, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
def pred_func(input_data):
# Set up the API endpoint URL
api = "https://api.example.com/predict"
# Send GET request to API & get response
response = requests.get(
api, params={"input": input_data}
)
# Extract predictions from JSON response
return ...
# Wrap your Pandas DataFrame and model dataset = giskard.Dataset(df, ...)
model = giskard.Model(pred_func, ...)
# Scan for vulnerabilities
results = giskard.scan(model, dataset)
Product workflow
Eliminate risks of biases, performance issues, and errors.
Become a ML superhero.
Become a ML superhero.
Integrate
API for any Python model, from tabular to LLMs: Torch, HuggingFace, Langchain, etc.
Scan
Automatically find vulnerabilities in your AI model directly in your notebook.
Test
Ready-made & extensible test suites, backed by State-of-the-Art ML research.
Automate
Protect your ML models against the risk of regressions, drift and bias.
Key features
.png)
Easy installation
Quickly install our Python library, compatible with any environment.
.png)
Model evaluation
Scan your model, from tabular to LLMs, with a few lines of code to instantly detect vulnerabilities.
.png)
Compliance with AI regulations
Avoid hefty fines for non-compliance by using our AI Quality Management System.
.png)
Secure & Fast
On-premise, with user authentification and encryption, so your data stays with you.
.png)
Collaboration
Create a human feedback loop with re-usable test components and visual debugging dashboards.
.png)
CI/CD integration
Automate and monitor your tests with each new model version to avoid regressions.
.svg)
Supported Data and Model types
Data type
.svg)
Tabular
LLMs, NLP
coming soon: Computer vision
Model type
Classification
Regression
Data
- Tabular data
- Text data
- Images (coming soon)
- Audio (coming soon)
- Time series (coming soon)
ML model task
- Classification
- Regression
- Text generation
- Image generation (coming soon)
- Time series forecasting (coming soon)
Integrates with your favorite Machine Learning tools
Join the community
This is an inclusive place where anyone interested in ML Quality is welcome! Leverage best practices from the community, contribute new tests, build the future of AI safety standards.
