staff-cli


Namestaff-cli JSON
Version 0.1.1 PyPI version JSON
download
home_pageNone
SummaryStaff is a toolkit for dead-simple usage out of the box promts and llms in your project and command line.
upload_time2024-08-02 14:41:45
maintainerNone
docs_urlNone
authorIurii Zatsepin <522287+Partysun@users.noreply.github.com>
requires_pythonNone
licenseNone
keywords llm ai ollama
VCS
bugtrack_url
requirements No requirements were recorded.
Travis-CI No Travis.
coveralls test coverage No coveralls.
            **Staff** is a toolkit for dead-simple usage out of the box promts and llms in your project and command line.

DRY & magic flow is a core principle.

Current state is WIP.

## Idea/Vision

Any good prompt combined with a llm is a pure magic. And you don't need to repeat yourself and find a good prompt, you can find well-prepared by community grimoires (combination of prompt, agents, functions & llms or only a prompt) then you learn this grimoire and can you use it on any text. Staff can help you with mastering your grimoires. Be brave in your path.

Structure of the Grimoire 0.1 version:

```md
---
title:
description:
tags: []
author:
---

[//]: # (SYSTEM)\n
Here any System prompt...

[//]: # (USER)\n
Here any User prompt...
```

You can use a grimoire with such packed of knowledge structure or it can be just a simple text without any metatags or SYSTEM/USER prompts. In that case everything is a SYSTEM prompt.

In the future version I want to add support for models & functions.

## Installation

You can install it from [pip](https://pypi.org/), [cargo](https://doc.rust-lang.org/cargo/getting-started/installation.html)

```bash
# pip install staff-cli
# cargo install staff-cli --locked # Not available yet
```

Or you can build ast-grep from source. You need to install rustup, clone the repository and then

````bash
cargo install --path ./crates/cli --locked


## USAGE

How to get ideas from the youtube video? You need to have installed [youtube_transcript_api](https://github.com/jdepoix/youtube-transcript-api)

```bash
youtube_transcript_api TY0o3Zs8u78 --languages en --format text | tr '\n' ' ' | xargs cargo run -- cast -n extract_wisdom
````

## FOR CONTRIBUTORS

About GigaChat model:

On UBUNTU/DEBIAN we need to install libssl-dev

```bash
sudo apt-get install libssl-dev
```

Install certificates

https://www.gosuslugi.ru/crt


            

Raw data

            {
    "_id": null,
    "home_page": null,
    "name": "staff-cli",
    "maintainer": null,
    "docs_url": null,
    "requires_python": null,
    "maintainer_email": null,
    "keywords": "llm, ai, ollama",
    "author": "Iurii Zatsepin <522287+Partysun@users.noreply.github.com>",
    "author_email": "Iurii Zatsepin <522287+Partysun@users.noreply.github.com>",
    "download_url": "https://files.pythonhosted.org/packages/e4/5b/f373ac85de912815c906a74704f5cff7ceb6e71010fab6312dff2fd9ec38/staff_cli-0.1.1.tar.gz",
    "platform": null,
    "description": "**Staff** is a toolkit for dead-simple usage out of the box promts and llms in your project and command line.\n\nDRY & magic flow is a core principle.\n\nCurrent state is WIP.\n\n## Idea/Vision\n\nAny good prompt combined with a llm is a pure magic. And you don't need to repeat yourself and find a good prompt, you can find well-prepared by community grimoires (combination of prompt, agents, functions & llms or only a prompt) then you learn this grimoire and can you use it on any text. Staff can help you with mastering your grimoires. Be brave in your path.\n\nStructure of the Grimoire 0.1 version:\n\n```md\n---\ntitle:\ndescription:\ntags: []\nauthor:\n---\n\n[//]: # (SYSTEM)\\n\nHere any System prompt...\n\n[//]: # (USER)\\n\nHere any User prompt...\n```\n\nYou can use a grimoire with such packed of knowledge structure or it can be just a simple text without any metatags or SYSTEM/USER prompts. In that case everything is a SYSTEM prompt.\n\nIn the future version I want to add support for models & functions.\n\n## Installation\n\nYou can install it from [pip](https://pypi.org/), [cargo](https://doc.rust-lang.org/cargo/getting-started/installation.html)\n\n```bash\n# pip install staff-cli\n# cargo install staff-cli --locked # Not available yet\n```\n\nOr you can build ast-grep from source. You need to install rustup, clone the repository and then\n\n````bash\ncargo install --path ./crates/cli --locked\n\n\n## USAGE\n\nHow to get ideas from the youtube video? You need to have installed [youtube_transcript_api](https://github.com/jdepoix/youtube-transcript-api)\n\n```bash\nyoutube_transcript_api TY0o3Zs8u78 --languages en --format text | tr '\\n' ' ' | xargs cargo run -- cast -n extract_wisdom\n````\n\n## FOR CONTRIBUTORS\n\nAbout GigaChat model:\n\nOn UBUNTU/DEBIAN we need to install libssl-dev\n\n```bash\nsudo apt-get install libssl-dev\n```\n\nInstall certificates\n\nhttps://www.gosuslugi.ru/crt\n\n",
    "bugtrack_url": null,
    "license": null,
    "summary": "Staff is a toolkit for dead-simple usage out of the box promts and llms in your project and command line.",
    "version": "0.1.1",
    "project_urls": {
        "Repository": "https://github.com/Partysun/staff"
    },
    "split_keywords": [
        "llm",
        " ai",
        " ollama"
    ],
    "urls": [
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "18860c170581e2ed2b47ba8ff1e6076e0ea1b15fb75f3882021c5882dc131183",
                "md5": "a998050af7a326a9f109e83d9d5bdb70",
                "sha256": "1f03e3979dd47e817180d8ac536817165c013678b37ca567b54046c4d1a66474"
            },
            "downloads": -1,
            "filename": "staff_cli-0.1.1-py3-none-manylinux_2_34_x86_64.whl",
            "has_sig": false,
            "md5_digest": "a998050af7a326a9f109e83d9d5bdb70",
            "packagetype": "bdist_wheel",
            "python_version": "py3",
            "requires_python": null,
            "size": 6280317,
            "upload_time": "2024-08-02T14:41:42",
            "upload_time_iso_8601": "2024-08-02T14:41:42.490263Z",
            "url": "https://files.pythonhosted.org/packages/18/86/0c170581e2ed2b47ba8ff1e6076e0ea1b15fb75f3882021c5882dc131183/staff_cli-0.1.1-py3-none-manylinux_2_34_x86_64.whl",
            "yanked": false,
            "yanked_reason": null
        },
        {
            "comment_text": null,
            "digests": {
                "blake2b_256": "e45bf373ac85de912815c906a74704f5cff7ceb6e71010fab6312dff2fd9ec38",
                "md5": "3acacfc1acdf09216139cd0f75e9e058",
                "sha256": "9ee140b48840a1a8946b172f8d7901d2be44c21df1b996e89cedfcc6117fe93a"
            },
            "downloads": -1,
            "filename": "staff_cli-0.1.1.tar.gz",
            "has_sig": false,
            "md5_digest": "3acacfc1acdf09216139cd0f75e9e058",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 25533,
            "upload_time": "2024-08-02T14:41:45",
            "upload_time_iso_8601": "2024-08-02T14:41:45.191814Z",
            "url": "https://files.pythonhosted.org/packages/e4/5b/f373ac85de912815c906a74704f5cff7ceb6e71010fab6312dff2fd9ec38/staff_cli-0.1.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2024-08-02 14:41:45",
    "github": true,
    "gitlab": false,
    "bitbucket": false,
    "codeberg": false,
    "github_user": "Partysun",
    "github_project": "staff",
    "travis_ci": false,
    "coveralls": false,
    "github_actions": false,
    "lcname": "staff-cli"
}
        
Elapsed time: 0.98205s