Skip to main content

Simple types & utilities built for the OpenAI Chat Completions API specification.

Project description

💭 prompted | (*formerly chatspec)

A tiny & rapid prototyping library for working with the OpenAI Chat Completions, Google A2A & Anthropic Model Context Protocol protocols.

This library was built for my own personal use, but provides an interface that is incredibly simple to master & understand.

chatspec's base implementation is meant to provide non-client utilities and types for these various protocols, both for common utilities as well as helpers for implementations of patterns found commonly within LLM & agent based applications. Optionally, you can install the chatspec[create] package to install a very flexible & easy to user interface built from litellm & instructor.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

prompted-0.0.3.tar.gz (211.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

prompted-0.0.3-py3-none-any.whl (79.4 kB view details)

Uploaded Python 3

File details

Details for the file prompted-0.0.3.tar.gz.

File metadata

  • Download URL: prompted-0.0.3.tar.gz
  • Upload date:
  • Size: 211.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.8

File hashes

Hashes for prompted-0.0.3.tar.gz
Algorithm Hash digest
SHA256 6eee7cc02d55fbfb1c36aefcfd91c03e2eb7c2e6cca2de1b069b63ee306af263
MD5 d921dbd547904095ab4abdaf2f0af9e3
BLAKE2b-256 4cb3c328c866ef5bcc5563310d501628c86e1ce4fcc34e80f493d7564ad46152

See more details on using hashes here.

File details

Details for the file prompted-0.0.3-py3-none-any.whl.

File metadata

  • Download URL: prompted-0.0.3-py3-none-any.whl
  • Upload date:
  • Size: 79.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.8

File hashes

Hashes for prompted-0.0.3-py3-none-any.whl
Algorithm Hash digest
SHA256 cbd0f3bc5a60ae454c1a53a9f2839086bbb1e8e222e26f5a83cc936ff9d3b7e0
MD5 fd9eae1486c0b6d190eb6dacde23909c
BLAKE2b-256 e312b4492345e0135308c1a68a0cbc10aacb886f9c772ed31a4d32f894f8f3e9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page