an ambient intelligence library

OpenAI's Structured Outputs with Logprobs

Structured Data Extractor for AI Agents. Search your documents or the web for specific data and get it back in JSON or Markdown in a single tool call.

Iterate over scans of forms, and have gpt-4o pull data from them into a csv file

Job posting parser with structured outputs

This repository demonstrates structured data extraction using various language models and frameworks. It includes examples of generating JSON outputs for name and age extraction from text prompts. The project leverages models like Qwen and frameworks such as LangChain, vLLM, and Outlines for Transformers models.

Demonstrates enforcing structured outputs from LLMs using LangChain (Google Gemini & HuggingFace) with Pydantic, TypedDict, and JSON Schema. Includes standalone examples for data validation and schema‑driven text generation. Quickly run each script to see how to produce reliably formatted AI responses.

A personalized quiz system using retrieval augmented generation.

An extension of the LLM-based spatial layout generation from image description from https://github.com/Attention-Refocusing/attention-refocusing using OpenAI and Ollama structured outputs

Recommender system and using Langchain for book recommendations.

A lite abstraction layer for structured LLM calls