JacksonKearl/gjp-4-gpt
JSON parser for streaming objects live from an LLM's output
This tool helps developers working with large language models (LLMs) to process JSON data as it's being generated, rather than waiting for the entire response. It takes an incomplete JSON string or a data stream from an LLM and outputs partially parsed JSON objects or arrays. This allows developers to build responsive applications that can react to LLM outputs in real-time.
No commits in the last 6 months.
Use this if you are a developer building an application that needs to display or act upon structured JSON data from a large language model as soon as parts of it become available.
Not ideal if you require extremely high-performance JSON parsing for very large files where latency isn't a concern, as native JSON parsers will be faster.
Stars
36
Forks
—
Language
TypeScript
License
MIT
Category
Last pushed
Feb 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/JacksonKearl/gjp-4-gpt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mangiucugna/json_repair
A python module to repair invalid JSON from LLMs
antfu/shiki-stream
Streaming highlighting with Shiki. Useful for highlighting text streams like LLM outputs.
iw4p/partialjson
+1M Downloads! Repair invalid LLM JSON, commonly used to parse the output of LLMs — Parsing...
yokingma/fetch-sse
An easy API for making Event Source requests, with all the features of fetch(), Supports...
kaptinlin/jsonrepair
A high-performance Golang library for easily repairing invalid JSON documents. Designed to fix...