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.

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models locally with an OpenAI-compatible interface.

Universal Python library for Structured Outputs with any LLM provider

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

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

Fast structured data extraction from text using LLMs. Pre-built templates for common use cases + custom schema support.

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.

Prompt (cue) management and execution for tabular data.

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.

A lite abstraction layer for structured LLM calls

Recommender system and using Langchain for book recommendations.

Local Codex CLI prompt refinery: ingest JSON/JSONL histories, dedupe, embed (OpenAI), cluster (sqlite-vec), synthesize atomic/workflow prompts via Responses API (Structured Outputs). FTS5+vector search; Streamlit UI; Typer CLI.

🛠️ Refine and organize your OpenAI Codex CLI prompts effortlessly, using SQLite for fast search and a user-friendly interface for better productivity.