FuzzAI The tool implements various attack techniques to test how LLMs respond to adversarial prompts, including: Taxonomy-based paraphrasing - Using persuasive language techniques to bypass sa...
Sentiment Analysis Sentiment analysis is a crucial task in Natural Language Processing (NLP) that involves determining the emotional tone behind a text. It helps identify whether a given piece of t...
Text Classification Text classification is the task of assigning a label or category to a piece of text, such as an email, document, or sentence. In Natural Language Processing, text classification...
Building a Speech To Text System Requirements To convert speech to text, the two most important libraries we need are: torch transformers And to load an audio file, we will need the soundfi...
pytest-evals Powerful testing framework designed specifically for AI model evaluation. We’ll implement a mock LLM system to enable testing without requiring external API keys. As AI models become i...
Text Classification A RAG system usually works on top of an LLM, with additional documents, so it can answer user queries based on the content present inside the documents. RAG systems work in the...
Simple Scrapper import requests import sys from bs4 import BeautifulSoup def scrape(url, max_chars): response = requests.get(url) soup = BeautifulSoup(response.text, 'html.parser') ...
Understanding the Ollama API Ollama provides a simple REST API accessible at http://localhost:11434/api. The main endpoints include: /api/generate - Generate text from a prompt /api/chat - H...
How Ollama Works Ollama works in the following way: You install Ollama on your local machine You pull model weights for specific LLMs (like Llama 2, Mistral, or Gemma) Ollama sets up a loc...
Understanding Modelfiles A basic Modelfile structure: FROM <base-model> # Base model to customize PARAMETER <key> <value> # Model parameters SYST...
