varunshenoy/super-json-mode
Low latency JSON generation using LLMs ⚡️
This tool helps developers efficiently extract structured data, like property details or financial figures, from unstructured text using large language models (LLMs). You input raw text and a predefined schema (like a Pydantic object), and it outputs a JSON object with the extracted information. Developers and data engineers who build applications relying on fast and accurate information extraction from text will find this useful.
398 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to rapidly extract specific pieces of information from text into a structured JSON format, especially when processing large volumes of data or requiring low-latency responses from LLMs.
Not ideal if your data extraction schema has dependencies between fields (e.g., one field's value dictates another's content), as this tool currently processes fields independently.
Stars
398
Forks
14
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 10, 2024
Commits (30d)
0
Dependencies
5
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/varunshenoy/super-json-mode"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
automorphic-ai/trex
Enforce structured output from LLMs 100% of the time
Giulz85/JsonToLLM
JsonToLLM is a C# library that transforms standard JSON into a format optimized for...
taranjeet/llmformatter
Get deterministic output in any format like json from any LLM.
arrangedev/jsonformer-ts
Structured JSON outputs from LLMs