Repository History
311 repositories tagged with Python
Jsonformer: Bulletproof Structured JSON Generation from Language Models
Jsonformer is a powerful library designed to generate syntactically correct and schema-conforming JSON from language models. It addresses the common challenge of unreliable JSON output by focusing on generating only content tokens, making the process more efficient and robust. This approach ensures bulletproof structured data generation for various applications.
JailbreakEval: An Integrated Toolkit for Evaluating LLM Jailbreak Attempts
JailbreakEval is an award-winning collection of automated evaluators designed to assess jailbreak attempts against large language models. It addresses the impracticality of manual inspection for large-scale analysis by unifying various evaluation tools. This toolkit is invaluable for both jailbreak researchers and evaluator developers, offering a robust framework for creating and benchmarking new evaluators.
EasyJailbreak: A Python Framework for Adversarial LLM Jailbreak Prompts
EasyJailbreak is an intuitive Python framework designed for generating adversarial jailbreak prompts for Large Language Models (LLMs). It provides a structured approach to decompose the jailbreaking process into iterative steps, offering components for mutation, attack, and evaluation. This tool is ideal for researchers and developers focused on LLM security and understanding model vulnerabilities.
Guardrails: Enhancing LLM Reliability and Structured Data Generation
Guardrails is a Python framework designed to build reliable AI applications by adding guardrails to large language models. It helps detect, quantify, and mitigate risks in LLM inputs/outputs, and facilitates the generation of structured data. This framework ensures more predictable and safer interactions with AI models.
Hiring Agent: An AI Agent for Resume Evaluation and Scoring
Hiring Agent is an open-source AI agent designed to evaluate and score resumes objectively. It extracts structured data from PDF resumes, enriches it with GitHub profile signals, and provides a fair, explainable evaluation with detailed scores and evidence. This tool supports both local LLMs via Ollama and cloud-based options like Google Gemini.
LLM Guard: The Security Toolkit for LLM Interactions
LLM Guard is an open-source security toolkit developed by Protect AI, designed to fortify the safety of Large Language Models. It offers comprehensive protection against various threats, including prompt injection, data leakage, and harmful language, ensuring secure and reliable LLM interactions.
AuditNLG: Auditing Generative AI for Trustworthiness
AuditNLG is an open-source library from Salesforce designed to enhance the trustworthiness of generative AI language models. It provides state-of-the-art techniques to detect and improve factualness, safety, and constraint adherence in AI-generated text. This library simplifies the process of auditing AI outputs, offering explanations and alternative suggestions for problematic content.
Odysseus: A Comprehensive Self-Hosted AI Workspace for Productivity
Odysseus is a powerful self-hosted AI workspace designed to integrate various AI-powered tools into a single platform. It offers functionalities for chat, agents, deep research, document management, email, and calendar, supporting both local and API models. This comprehensive solution aims to enhance productivity and streamline AI workflows in a private environment.
Headroom: Drastically Reduce LLM Token Usage for AI Agents
Headroom is an innovative context compression layer for AI agents, designed to significantly reduce token usage for LLMs. It achieves 60-95% fewer tokens across various inputs like tool outputs, logs, files, and RAG chunks, all while preserving answer accuracy. This powerful tool enhances efficiency and cost-effectiveness for AI interactions.
spacy-llm: Integrating LLMs into Structured NLP Pipelines with spaCy
spacy-llm seamlessly integrates Large Language Models (LLMs) into spaCy, offering a modular system for rapid prototyping and transforming unstructured LLM responses into robust outputs for various NLP tasks. It supports a wide range of LLMs, including OpenAI, Cohere, Anthropic, and open-source models, enabling users to combine the power of LLMs with spaCy's production-ready capabilities. This package allows for quick experimentation and the creation of efficient, reliable, and controlled NLP systems.
PixelRAG: Pixel-Native Search for Visual Retrieval-Augmented Generation
PixelRAG revolutionizes search by enabling pixel-native retrieval, moving beyond traditional text parsing. It renders documents as screenshots, preserving visual context like tables and charts, which is crucial for accurate answers from reader models. This allows for searching any document based on its visual appearance, not just its textual content.
Tiny8: An Educational 8-bit CPU Simulator with Interactive Visualization
Tiny8 is a lightweight and educational 8-bit CPU simulator written in Python. It offers an interactive terminal debugger and graphical animation to visualize program execution, making it ideal for learning computer architecture and assembly programming.