
Security News
NVD Concedes Inability to Keep Pace with Surging CVE Disclosures in 2025
Security experts warn that recent classification changes obscure the true scope of the NVD backlog as CVE volume hits all-time highs.
Kiri is a Python library that makes it simple to solve AI tasks without requiring any data.
Kiri is built around solving tasks with transfer learning. It implements state-of-the-art AI models that are general enough to solve real world tasks with no data required from the user.
Out of the box tasks you can solve with Kiri:
For more specific use cases, you can adapt a task with little data and a couple of lines of code using finetuning. We are adding finetuning support for all tasks soon.
You can run all tasks locally or in production with our optimised inference API, where you only pay for usage. It includes all the tasks, models in our library and lets you upload your own finetuned models.
⚡ Getting started | Installation, few minute introduction |
---|---|
💡 Examples | Sample problems solved using Kiri |
📙 Docs | In-depth documentation for advanced usage |
Install Kiri via PyPi:
pip install kiri
from kiri import Kiri
context = "Take a look at the examples folder to see use cases!"
# Use our inference API
k = Kiri(api_key="abc")
# Or run locally
k = Kiri(local=True)
# Start building!
answer = k.qa("Where can I see what to build?", context)
print(answer)
# Prints
"the examples folder"
from kiri.models import T5
from kiri.tasks import TextGeneration
tg = TextGeneration(T5, local=True)
# Any text works as training data
inp = ["I really liked the service I received!", "Meh, it was not impressive."]
out = ["positive", "negative"]
# Finetune with a single line of code
tg.finetune(inp, out)
# Use your trained model
prediction = tg("I enjoyed it!")
print(prediction)
# Prints
"positive"
# Upload to Kiri for production ready inference
import kiri
model = tg.model
# Describe your model
model.name = "t5-sentiment"
model.description = "Predicts positive and negative sentiment"
kiri.upload(model, api_key="abc")
No experience needed
Data is a bottleneck
There is an overwhelming amount of models
Deploying models cost effectively is hard work
Take a look at the examples folder.
Check out our docs.
FAQs
Kiri
We found that kiri demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Security News
Security experts warn that recent classification changes obscure the true scope of the NVD backlog as CVE volume hits all-time highs.
Security Fundamentals
Attackers use obfuscation to hide malware in open source packages. Learn how to spot these techniques across npm, PyPI, Maven, and more.
Security News
Join Socket for exclusive networking events, rooftop gatherings, and one-on-one meetings during BSidesSF and RSA 2025 in San Francisco.