whylabs / langkit
🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀
☆840Updated this week
Related projects ⓘ
Alternatives and complementary repositories for langkit
- A tool for evaluating LLMs☆389Updated 5 months ago
- LLM Prompt Injection Detector☆1,116Updated 3 months ago
- ☆796Updated 2 weeks ago
- ☆742Updated 10 months ago
- Automated Evaluation of RAG Systems☆479Updated this week
- Fine-Tuning Embedding for RAG with Synthetic Data☆466Updated last year
- OpenTelemetry Instrumentation for AI Observability☆214Updated this week
- Evaluation and Tracking for LLM Experiments☆2,141Updated this week
- Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.☆778Updated 2 weeks ago
- The Security Toolkit for LLM Interactions☆1,229Updated 2 weeks ago
- This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!☆558Updated this week
- ☆433Updated 10 months ago
- Superfast AI decision making and intelligent processing of multi-modal data.☆2,077Updated last week
- Open-source tool to visualise your RAG 🔮☆1,083Updated 7 months ago
- Evaluate your LLM's response with Prometheus and GPT4 💯☆792Updated 2 months ago
- Ship RAG based LLM web apps in seconds.☆974Updated 9 months ago
- LLM abstractions that aren't obstructions☆747Updated this week
- Python SDK for running evaluations on LLM generated responses☆214Updated this week
- Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verifi…☆1,609Updated this week
- ☆773Updated last month
- Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)☆389Updated 11 months ago
- 🍰 PromptLayer - Maintain a log of your prompts and OpenAI API requests. Track, debug, and replay old completions.☆515Updated last week
- 🦙 Integrating LLMs into structured NLP pipelines☆1,120Updated 3 months ago
- Open-source tools for prompt testing and experimentation, with support for both LLMs (e.g. OpenAI, LLaMA) and vector databases (e.g. Chro…☆2,700Updated 2 months ago
- ☆488Updated 2 months ago
- A lightweight, low-dependency, unified API to use all common reranking and cross-encoder models.☆1,035Updated this week
- Adding guardrails to large language models.☆4,053Updated this week
- RayLLM - LLMs on Ray☆1,233Updated 5 months ago
- wandbot is a technical support bot for Weights & Biases' AI developer tools that can run in Discord, Slack, ChatGPT and Zendesk☆274Updated this week