A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
Repository Index
98,836 visible repositories in the index
1–13 of 13 · Most stars
The Generative UI framework
Structured Outputs
- generative-ai
- llms
- prompt-engineering
- symbolic-ai
TypeChat is a library that makes it easy to build natural language interfaces using types.
Open-source framework for building agentic apps in JavaScript, Go, Dart, and Python, built and used in production by Google
- ai
- genkit
- vector-database
- embedders
Repair malformed JSON from LLMs, APIs, logs, and user input in Python.
A Bulletproof Way to Generate Structured JSON from Language Models
🤖 Type-safe, provider-agnostic TypeScript AI SDK for streaming chat, tool calling, agents, and multimodal apps across OpenAI, Anthropic, Gemini, React, Vue, Svelte, and Solid.
The pretty much "official" DSPy framework for Typescript
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema on the model output on the generation level
AICI: Prompts as (Wasm) Programs
Enforce the output format (JSON Schema, Regex etc) of a language model
Open-source platform for extracting structured data from documents using AI.