Comments (1)
Hello @aldrinjenson
This is due to how giskard is currently serializing models. It uses cloudpickle to serializes all the code inside of the model module, and assumes that other modules will be dependencies of your python env.
Since giskard_tests.py
is outside of any module, then it won't serialize any code inside of src
module. You should adapt a proper module structure to ensure that everything is automatically serialized (see Structuring Your Project):
.
├── pages
├── requirements.txt
├── giskard_tests # Rename src into your module name
|├── giskard_tests.py # Move giskard_tests.py inside your module
│ ├── init.py
│ ├── assets
│ ├── components
│ ├── evaluation
│ ├── guards
│ ├── modules
│ ├── observability
│ ├── prompt
│ └── utils
|── tests
│ ├── init.py
── 🏠_Home.py
Note that you can enfore serializing any module by using the following piece of code (but it's not recommended):
import src
import cloudpickle
cloudpickle.register_pickle_by_value(src)
model = giskard.model(...)
model.save(...)
from giskard.
Related Issues (20)
- Add Data Leakage Assessment HOT 1
- generate_test does not work with Azure Open AI key HOT 2
- Is there a way to test the LLM-based models for stereotypes and discrimination using a saved dataset HOT 3
- giskard.scan is failing for azure openai & langchain HOT 2
- Implement a Gemini `LLMClient` HOT 7
- Wrapping custom application endpoint not working HOT 2
- Scan is not working with OpenAI when running quickstart_llm.ipynb. AttributeError: module 'openai' has no attribute 'Client' HOT 6
- Raget: Possible miscalculation of all Ragas metrics, in particular Precision and Recall HOT 2
- huggingface models as client? HOT 1
- "generate_test" function with Bedrock client (for Claud03) HOT 1
- Contributing to examples/tutorials HOT 2
- Generate synthetic questions with listing choices
- Unresolved Version Conflict for Langchain-community HOT 1
- dataset has a column ```question``` but Dataset constructor is throwing an Error that it doesn't HOT 1
- giskard.scan() defaults back to OpenAI, when I have been using LM Studio (Solution suggested) HOT 4
- Giskard Scan crush when tested for a large number of features HOT 1
- Support python 3.12 HOT 1
- Set any groq model as default LLMClient for giskard
- Documentation: Add the list of tags available for the `only` param of the `scan` method
- when ı am creating knowledgebase, my codes here: HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from giskard.