import sys
import os
from dotenv import load_dotenv
if 'google.colab' in sys.modules:
from google.colab import userdata # type:ignore
OPENROUTER_API_KEY = userdata.get('OPENROUTER_API_KEY')
os.environ["OPENROUTER_API_KEY"] = OPENROUTER_API_KEY
print("Loaded key from Colab")
else:
load_dotenv()
print("Loaded key locally")Loaded key locallyMODEL = "meta-llama/llama-3.2-1b-instruct"
import openai
client = openai.OpenAI(
base_url='https://openrouter.ai/api/v1',
api_key=os.environ["OPENROUTER_API_KEY"],
)response = client.chat.completions.create(
model=MODEL,
messages=[
{"role": "system", "content": "You help students generate citations for their coursework."},
{"role": "user", "content": "Can you cite three academic papers on transfomer efficiency. I'm looking for the author names, journals, years, and titles."},
],
)
response.choices[0].message.content'Here are three academic papers on transformer efficiency:\n\n1. **"Attention is a Limited Resource: The Case for Unique Attention Mechanisms in Deep Neural Networks"**\n\nAuthor: Vaswani et al.\n\nJournal: Nature\n\nYear: 2017\n\nTitle: Attention is a Limited Resource: The Case for Unique Attention Mechanisms in Deep Neural Networks\n\nThis paper proposes a new approach to attention mechanisms in deep neural networks, which suggests that attention is not just a simple linear scaling of the input features, but rather a complex mechanism that involves multiple stages and attention weights. The authors demonstrate that this approach can improve the performance of deep neural networks on various tasks.\n\n2. **"Attention is All You Need"**\n\nAuthor: Vaswani et al.\n\nJournal: Nature\n\nYear: 2017\n\nTitle: Attention is All You Need\n\nThis paper presents a new approach to attention mechanisms in deep neural networks, which suggests that attention is not just a simple linear scaling of the input features, but rather a complex mechanism that involves multiple stages and attention weights. The authors demonstrate that this approach can improve the performance of deep neural networks on various tasks.\n\n3. **"Attention is a Key to Efficient Neural Network Training"**\n\nAuthor: He et al.\n\nJournal: Proceedings of the 32nd International Conference on Machine Learning (ICML)\n\nYear: 2015\n\nTitle: Attention is a Key to Efficient Neural Network Training\n\nThis paper presents a new approach to attention mechanisms in deep neural networks, which suggests that attention is a key factor in improving the efficiency of neural network training. The authors demonstrate that attention mechanisms can significantly improve the training speed and accuracy of deep neural networks on various tasks.\n\nNote: These papers are just a few examples of the many papers that have explored transformer efficiency.'response = client.chat.completions.create(
model=MODEL,
messages=[
{"role": "system", "content": "You help provide information about software applications."},
{"role": "user", "content": "Tell me more about FilterGenie, software for the Mac that allows you to apply dynamic filters to images."},
],
)
response.choices[0].message.content"FilterGenie is a powerful image editing software for Mac that allows you to apply dynamic filters to images. It's a popular tool among photographers, graphic designers, and anyone looking to enhance and transform their images with ease.\n\nHere are some key features and benefits of FilterGenie:\n\n**Key Features:**\n\n1. **Dynamic Filters**: FilterGenie offers a wide range of dynamic filters that can be applied to images, including:\n\t* Color correction and adjustment\n\t* Noise reduction and sharpening\n\t* Texture and pattern overlays\n\t* Effects like blur, vignette, and glow\n\t* And many more!\n2. **Adjustable Parameters**: Each filter has adjustable parameters, allowing you to fine-tune the effect to your liking.\n3. **Support for Multiple Image Files**: FilterGenie supports a wide range of image file formats, including JPEG, PNG, and TIFF.\n4. **Batch Processing**: You can apply filters to multiple images at once, making it a great tool for editing multiple images in a single session.\n5. **Export Options**: FilterGenie allows you to export your edited images in various formats, including JPEG, PNG, and PSD.\n\n**Benefits:**\n\n1. **Easy to Use**: FilterGenie's intuitive interface makes it easy to apply filters to images, even for those without extensive image editing experience.\n2. **Versatile**: The software offers a wide range of filters to suit various image editing needs, from basic adjustments to more advanced effects.\n3. **High-Quality Results**: FilterGenie's filters are designed to produce high-quality results, ensuring your images look professional and polished.\n4. **Cross-Platform Compatibility**: FilterGenie is available for Mac, Windows, and Linux, making it a great option for users with multiple operating systems.\n\n**System Requirements:**\n\nTo run FilterGenie, you'll need:\n\n* Mac with macOS 10.12 or later\n* 2 GB RAM or more\n* 2 GB free disk space\n* A compatible graphics card (Intel Core i5 or later recommended)\n\n**Pricing:**\n\nFilterGenie offers a free trial version, as well as a one-time purchase option for the full version. The full version costs around $49.99 USD.\n\nOverall, FilterGenie is a powerful and versatile image editing software that's perfect for anyone looking to enhance and transform their images with dynamic filters."response = client.chat.completions.create(
model=MODEL,
messages=[
{"role": "system", "content": "You help users summarize documents and published papers."},
{"role": "user", "content": "Can you summarize the key findings of the 2019 WHO report on urban air quality in South Asia."},
],
)
response.choices[0].message.content"I couldn't find a specific 2019 WHO report on urban air quality in South Asia. However, I can provide some general information on the topic and highlight some key findings from previous reports.\n\nThe World Health Organization (WHO) has published several reports on air quality in South Asia, including:\n\n1. **2018 WHO Air Quality Guidelines**: In 2018, WHO published guidelines for air quality in urban areas, which emphasized the importance of reducing air pollution from domestic and industrial sources. The guidelines recommended that cities implement measures to reduce particulate matter (PM2.5) and other pollutants.\n2. **2019 WHO Air Quality Report**: In 2019, WHO published a report on air quality in South Asia, which highlighted the region's vulnerability to air pollution. The report noted that South Asia is home to some of the world's most populous cities, including Delhi, Mumbai, and Dhaka, which are among the most polluted cities in the world.\n3. **2019 WHO Air Quality Report: South Asia**: This report focused on the health impacts of air pollution in South Asia, including the estimated number of premature deaths and hospitalizations due to air pollution. The report also highlighted the need for cities to implement effective air quality management strategies to reduce pollution.\n\nSome key findings from these reports include:\n\n* **Air pollution is a major public health concern in South Asia**: The region is home to some of the world's most polluted cities, with PM2.5 levels exceeding the WHO's recommended limits in many areas.\n* **Air pollution affects vulnerable populations**: The report highlighted the disproportionate impact of air pollution on vulnerable populations, including children, the elderly, and people with pre-existing respiratory conditions.\n* **Air pollution is linked to increased mortality**: The report estimated that air pollution is responsible for an estimated 1.8 million premature deaths per year in South Asia, primarily due to respiratory diseases such as bronchitis and lung cancer.\n* **Air pollution affects economic productivity**: The report noted that air pollution can have significant economic impacts, including reduced economic productivity and increased healthcare costs.\n\nSome specific data points from the 2019 WHO Air Quality Report include:\n\n* Delhi, India: PM2.5 levels exceeded the WHO's recommended limit in 2019, with an average annual concentration of 44.4 μg/m3.\n* Mumbai, India: PM2.5 levels exceeded the WHO's recommended limit in 2019, with an average annual concentration of 35.4 μg/m3.\n* Dhaka, Bangladesh: PM2.5 levels exceeded the WHO's recommended limit in 2019, with an average annual concentration of 23.4 μg/m3.\n\nOverall, the 2019 WHO Air Quality Report highlights the urgent need for cities in South Asia to take action to reduce air pollution and protect public health."