whylabs / langkitLinks
🔍 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. 👀
☆952Updated 11 months ago
Alternatives and similar repositories for langkit
Users that are interested in langkit are comparing it to the libraries listed below
Sorting:
- LLM Prompt Injection Detector☆1,359Updated last year
- A tool for evaluating LLMs☆424Updated last year
- ☆774Updated 3 months ago
- The Security Toolkit for LLM Interactions☆2,164Updated last week
- Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.☆857Updated 11 months ago
- Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)☆397Updated last year
- Evaluation and Tracking for LLM Experiments and AI Agents☆2,862Updated this week
- Retrieval Augmented Generation (RAG) framework and context engine powered by Pinecone☆1,022Updated 11 months ago
- Open-source tool to visualise your RAG 🔮☆1,169Updated 9 months ago
- ☆969Updated 2 months ago
- Fine-Tuning Embedding for RAG with Synthetic Data☆512Updated 2 years ago
- ☆507Updated last year
- Automated Evaluation of RAG Systems☆664Updated 6 months ago
- Fiddler Auditor is a tool to evaluate language models.☆188Updated last year
- ☆897Updated 11 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…☆2,946Updated last year
- Deliver safe & effective language models☆544Updated 3 weeks ago
- Metrics to evaluate the quality of responses of your Retrieval Augmented Generation (RAG) applications.☆318Updated 3 months ago
- ☆464Updated last year
- VectorFlow is a high volume vector embedding pipeline that ingests raw data, transforms it into vectors and writes it to a vector DB of y…☆696Updated last year
- NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.☆5,159Updated this week
- OpenTelemetry Instrumentation for AI Observability☆659Updated this week
- Adala: Autonomous DAta (Labeling) Agent framework☆1,278Updated this week
- 🍰 PromptLayer - Maintain a log of your prompts and OpenAI API requests. Track, debug, and replay old completions.☆682Updated this week
- Evaluation tool for LLM QA chains☆1,087Updated 2 years ago
- wandbot is a technical support bot for Weights & Biases' AI developer tools that can run in Discord, Slack, ChatGPT and Zendesk☆310Updated 2 months ago
- Adding guardrails to large language models.☆5,817Updated last week
- The production toolkit for LLMs. Observability, prompt management and evaluations.☆1,429Updated last week
- 🦜💯 Flex those feathers!☆252Updated last year
- Python SDK for running evaluations on LLM generated responses☆292Updated 4 months ago