interviewer / docs /instruction.py
IliaLarchenko's picture
Huge refactoring
3667c7a
raw
history blame
No virus
2.13 kB
# I will change it into proper format later
instruction = {
"intro": """
This project leverages the latest AI models to simulate a realistic tech interview experience,
allowing you to practice your coding interview skills in an environment that closely mimics the real thing.
While it's not designed to replace a human interviewer or the essential steps of interview preparation, such as studying algorithms and practicing coding,
it serves as a valuable addition to your preparation arsenal.
""",
"demo": """
### Demo Version Notice
**This is a demo version running on limited resources, which may respond slower than usual.**
It's primarily for demonstration purposes.
For optimal performance, we recommend running this application on your local machine using your own OpenAI API_KEY or local models.
See the instructions below on how to set up and run this application locally for the best experience.
I also recommend to read this introduction page first.
If you proceed to the interview interface right now, just click on the 'Coding' tab.
""",
"acknowledgements": """
The library can be used with a wide variety of models and APIs depending on configuration.
But I would like to acknowledge the following models in particular:
* OpenAI: GPT-3.5, GPT-4, Whisper, TTS-1, etc.
* Meta: Llama family, especially Meta-Llama-3-70B-Instruct and Meta-Llama-3-8B-Instruct.
* HuggingFace: for providing a wide range of models and APIs that can be used with this library.
Please, make sure to check the documentation of the models and APIs you are using to understand their capabilities and limitations.
Also, make sure to comply with the terms of service and acceptable use policies of the models and APIs you are using.
""",
}