AI Observability & Evaluation
OpenLIT: Complete Observability and Evals for the Entire GenAI Stack, from LLMs to GPUs. Improve your LLM apps from playground to production 📈. Supports 20+ monitoring integrations like OpenAI & LangChain. Collect and Send GPU performance, costs, tokens, user activity, LLM traces and metrics to any OpenTelemetry endpoint in just one line of code.
Fiddler Auditor is a tool to evaluate language models.
A comprehensive solution for monitoring your AI models in production
A python library to send data to Arize AI!
A report generator library for the ML models deployed on the Fiddler AI Observability platform
Java client to interact with Arize API
This repo hosts a chatbot that runs in a docker container to demo Okahu AI Observability Cloud
Example projects for Arthur Model Monitoring Platform
This repo hosts a chatbot that runs in Github Codespaces to demo Okahu AI Observability Cloud with OpenAI
The Modelmetry Python SDK allows developers to easily integrate Modelmetry’s advanced guardrails and monitoring capabilities into their LLM-powered applications.
The Modelmetry JS/TS SDK allows developers to easily integrate Modelmetry’s advanced guardrails and monitoring capabilities into their LLM-powered applications.
Official NodeJS library for monitoring LLM Applications with Doku
Official Python Library to monitor your LLM Application with Doku
Add a description, image, and links to the ai-observability topic page so that developers can more easily learn about it.
To associate your repository with the ai-observability topic, visit your repo's landing page and select "manage topics."