This tool extracts knowledge from unstructured text documents by generating Subject-Predicate-Object triplets and visualizes them as an interactive graph. It features chunking for processing, entity standardization, and relationship inference, making it suitable for any OpenAI compatible API.

Monitor and visualize the performance of various LLM APIs over time to identify regressions and quality changes, particularly during peak load periods. By comparing different models and providers, users can proactively detect issues that may impact production applications.

LangExtract is a Python library designed to extract structured information from unstructured text using large language models (LLMs) based on user-defined prompts. It features precise source grounding, reliable output formats, interactive visualizations, and supports both cloud-based and local LLMs, making it adaptable to various domains without the need for fine-tuning. Users can easily set up API keys for cloud models and extend functionality with custom model providers.