npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2024 – Pkg Stats / Ryan Hefner

slashgpt

v0.1.5

Published

This is ported from Python. This runs in the browser and Node.js. Unlike the Python version, it does not support chat in the cli. This is software used as a library.

Downloads

1,287

Readme

SlashGPT js

This is ported from Python. This runs in the browser and Node.js. Unlike the Python version, it does not support chat in the cli. This is software used as a library.

It does not support the feature to execute Python native code.

The current status is...

Supported manifest items

  • title (string, required): Title for the user to see
  • about (string, optional): About the manifest (URL, email, github id, or twitter id)
  • description (string, optional): Human/LLM readable description of this agent
  • bot (string, optional): Agent name. The default is Agent({agent_name}).
  • temperature (number, optional): Temperature (the default is 0.7)
  • model (string or dict, optional): LLM model (such as "gpt-4-613", the default is "gpt-3-turbo")
  • prompt (array of strings, required): The system prompts which define the agent (required)
  • functions (string or list, optional): string - location of the function definitions, list - function definitions
  • actions (object, optional): Template-based function processor (see details below)
  • skip_function_result (boolean): skip the chat completion right after the function call.

Not supported manifest items

for chat

  • sample or smaple... (string, optional): Sample question (type "/sample" to submit it as the user message)
  • you (string, optional): User name. The default is You({agent_name}).
  • intro (array of strings, optional): Introduction statements (will be randomly selected)

little used

  • form (string): format string to extend user's query (e.g. "Write python code to {question}").

  • result_form (string): format string to extend function call result.

  • list (array of string, optional): {random} will put one of them randomly into the prompt

  • function_call (string, optional): the name of tne function LLM should call

  • logprobs (number, optional): Number of "next probable tokens" + associated log probabilities to return alongside the output

  • num_completions (number, optional): Number of different completions to request from the model per prompt

  • resource (string, optional): location of the resource file. Use {resource} to paste it into the prompt

Not supported by browser

  • embeddings (object, optional):
    • name (string, optional): index name of the embedding vector database

for python

  • module (string, optional): location of the Python script to be loaded for function calls

  • notebook (boolean): create a new notebook at the beginning of each session (for code_palm2)

  • stream (boolean, optional): Enable LLM output streaming (not yet implemented)