%global _empty_manifest_terminate_build 0
Name: python-kiri
Version: 0.5.1
Release: 1
Summary: Kiri
License: Apache Software License
URL: https://github.com/kiri-ai/kiri
Source0: https://mirrors.aliyun.com/pypi/web/packages/b5/79/eae397e390aa440b6e6eb84bcef45d02ca0d18a991515a38d7f7e1e78821/kiri-0.5.1.tar.gz
BuildArch: noarch
Requires: python3-dill
Requires: python3-ftfy
Requires: python3-pytorch-lightning
Requires: python3-sentence-transformers
Requires: python3-torch
Requires: python3-torchvision
Requires: python3-transformers
%description
Kiri
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:
- Conversational question answering in English (for FAQ chatbots, text analysis, etc.)
- Text Classification in 100+ languages (for email sorting, intent detection, etc.)
- Image Classification (for object recognition, OCR, etc.)
- Text Vectorisation in 50+ languages (semantic search for ecommerce, documentation, etc.)
- Summarisation in English (TLDRs for long documents)
- Emotion detection in English (for customer satisfaction, text analysis, etc.)
- Text Generation (for idea, story generation and broad task solving)
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](https://kiri.ai), 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](#getting-started) | Installation, few minute introduction |
| :---------------------------------------------------------------- | :---------------------------------------- |
| 💡 [Examples](https://github.com/kiri-ai/kiri/tree/main/examples) | Sample problems solved using Kiri |
| 📙 [Docs](https://kiri.readthedocs.io/en/latest/) | In-depth documentation for advanced usage |
## Getting started
### Installation
Install Kiri via PyPi:
```bash
pip install kiri
```
### Basic task solving
```python
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"
```
### Basic finetuning and uploading
```python
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")
```
## Why Kiri?
1. No experience needed
- Entrance to practical AI should be simple
- Get state-of-the-art performance in your task without being an expert
2. Data is a bottleneck
- Use AI without needing access to "big data"
- With transfer learning, no data is required, but even a small amount can adapt a task to your niche.
3. There is an overwhelming amount of models
- We implement the best ones for various tasks
- A few general models can accomplish more with less optimisation
4. Deploying models cost effectively is hard work
- If our models suit your use case, no deployment is needed
- Adapt and deploy your own model with a couple of lines of code
- Our API scales, is always available, and you only pay for usage
## Examples
Take a look at the [examples folder](https://github.com/kiri-ai/kiri/tree/main/examples).
## Documentation
Check out our [docs](https://kiri.readthedocs.io/en/latest/).
%package -n python3-kiri
Summary: Kiri
Provides: python-kiri
BuildRequires: python3-devel
BuildRequires: python3-setuptools
BuildRequires: python3-pip
%description -n python3-kiri
Kiri
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:
- Conversational question answering in English (for FAQ chatbots, text analysis, etc.)
- Text Classification in 100+ languages (for email sorting, intent detection, etc.)
- Image Classification (for object recognition, OCR, etc.)
- Text Vectorisation in 50+ languages (semantic search for ecommerce, documentation, etc.)
- Summarisation in English (TLDRs for long documents)
- Emotion detection in English (for customer satisfaction, text analysis, etc.)
- Text Generation (for idea, story generation and broad task solving)
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](https://kiri.ai), 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](#getting-started) | Installation, few minute introduction |
| :---------------------------------------------------------------- | :---------------------------------------- |
| 💡 [Examples](https://github.com/kiri-ai/kiri/tree/main/examples) | Sample problems solved using Kiri |
| 📙 [Docs](https://kiri.readthedocs.io/en/latest/) | In-depth documentation for advanced usage |
## Getting started
### Installation
Install Kiri via PyPi:
```bash
pip install kiri
```
### Basic task solving
```python
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"
```
### Basic finetuning and uploading
```python
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")
```
## Why Kiri?
1. No experience needed
- Entrance to practical AI should be simple
- Get state-of-the-art performance in your task without being an expert
2. Data is a bottleneck
- Use AI without needing access to "big data"
- With transfer learning, no data is required, but even a small amount can adapt a task to your niche.
3. There is an overwhelming amount of models
- We implement the best ones for various tasks
- A few general models can accomplish more with less optimisation
4. Deploying models cost effectively is hard work
- If our models suit your use case, no deployment is needed
- Adapt and deploy your own model with a couple of lines of code
- Our API scales, is always available, and you only pay for usage
## Examples
Take a look at the [examples folder](https://github.com/kiri-ai/kiri/tree/main/examples).
## Documentation
Check out our [docs](https://kiri.readthedocs.io/en/latest/).
%package help
Summary: Development documents and examples for kiri
Provides: python3-kiri-doc
%description help
Kiri
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:
- Conversational question answering in English (for FAQ chatbots, text analysis, etc.)
- Text Classification in 100+ languages (for email sorting, intent detection, etc.)
- Image Classification (for object recognition, OCR, etc.)
- Text Vectorisation in 50+ languages (semantic search for ecommerce, documentation, etc.)
- Summarisation in English (TLDRs for long documents)
- Emotion detection in English (for customer satisfaction, text analysis, etc.)
- Text Generation (for idea, story generation and broad task solving)
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](https://kiri.ai), 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](#getting-started) | Installation, few minute introduction |
| :---------------------------------------------------------------- | :---------------------------------------- |
| 💡 [Examples](https://github.com/kiri-ai/kiri/tree/main/examples) | Sample problems solved using Kiri |
| 📙 [Docs](https://kiri.readthedocs.io/en/latest/) | In-depth documentation for advanced usage |
## Getting started
### Installation
Install Kiri via PyPi:
```bash
pip install kiri
```
### Basic task solving
```python
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"
```
### Basic finetuning and uploading
```python
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")
```
## Why Kiri?
1. No experience needed
- Entrance to practical AI should be simple
- Get state-of-the-art performance in your task without being an expert
2. Data is a bottleneck
- Use AI without needing access to "big data"
- With transfer learning, no data is required, but even a small amount can adapt a task to your niche.
3. There is an overwhelming amount of models
- We implement the best ones for various tasks
- A few general models can accomplish more with less optimisation
4. Deploying models cost effectively is hard work
- If our models suit your use case, no deployment is needed
- Adapt and deploy your own model with a couple of lines of code
- Our API scales, is always available, and you only pay for usage
## Examples
Take a look at the [examples folder](https://github.com/kiri-ai/kiri/tree/main/examples).
## Documentation
Check out our [docs](https://kiri.readthedocs.io/en/latest/).
%prep
%autosetup -n kiri-0.5.1
%build
%py3_build
%install
%py3_install
install -d -m755 %{buildroot}/%{_pkgdocdir}
if [ -d doc ]; then cp -arf doc %{buildroot}/%{_pkgdocdir}; fi
if [ -d docs ]; then cp -arf docs %{buildroot}/%{_pkgdocdir}; fi
if [ -d example ]; then cp -arf example %{buildroot}/%{_pkgdocdir}; fi
if [ -d examples ]; then cp -arf examples %{buildroot}/%{_pkgdocdir}; fi
pushd %{buildroot}
if [ -d usr/lib ]; then
find usr/lib -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
if [ -d usr/lib64 ]; then
find usr/lib64 -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
if [ -d usr/bin ]; then
find usr/bin -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
if [ -d usr/sbin ]; then
find usr/sbin -type f -printf "\"/%h/%f\"\n" >> filelist.lst
fi
touch doclist.lst
if [ -d usr/share/man ]; then
find usr/share/man -type f -printf "\"/%h/%f.gz\"\n" >> doclist.lst
fi
popd
mv %{buildroot}/filelist.lst .
mv %{buildroot}/doclist.lst .
%files -n python3-kiri -f filelist.lst
%dir %{python3_sitelib}/*
%files help -f doclist.lst
%{_docdir}/*
%changelog
* Tue Jun 20 2023 Python_Bot - 0.5.1-1
- Package Spec generated