Skip to main content

CLI tool to give quick step-by-step answers to tech questions. Powered by the LLMs and StackOverflow.

Project description

TLDR AI CLI Tool

PyPI version License

Overview

TLDR AI CLI Tool is a command-line interface (CLI) designed to provide quick and efficient solutions to complex queries using Large Language Models (LLMs). The tool integrates various AI models to fetch, process, and summarize information from sources like Stack Overflow.

The TLDR AI CLI Tool is inspired by howdoi. Unlike howdoi, this tool leverages the power of LLMs and can even work offline if Stack Overflow is not used.

Features

  • Summarizes complex topics into concise, understandable summaries.
  • Fetches and processes Stack Overflow questions and answers.
  • Utilizes multiple LLMs, including Ollama and other transformers.
  • Configurable via YAML files.
  • Supports real-time response streaming.

Installation

Prerequisites

  • Python 3.8+
  • Ollama

Install Ollama

Ollama is required for some functionalities of this tool. Please install Ollama according to your operating system by following the instructions provided in their Documentation.

Install TLDR AI CLI Tool

You can install the TLDR AI CLI Tool via pip:

pip install tldrai

Usage

To use the tool, simply run:

tldrai apply function to pandas column

You can also override specific configuration settings using the --set argument:

tldrai apply function to pandas column --set summarization_pipeline.model=stable-code precision=float32 -v

CLI Options

  • question: The question or query to process.
  • --config: Path to the configuration file (default: config/config.yaml).
  • --set: Override configuration key-value pairs (e.g., key=value).
  • -v, --verbose: Output all logs verbose.
  • -s, --search: Search for similar quetions on Stack Overflow and feed it to the model as suggestions

Configuration

The TLDR AI CLI Tool is highly configurable. Configuration settings are managed through YAML files. Currently, the default configuration file used is config/ollama_stable_code.yml.

Forming questions

I found two distinct ways to form the questions, depending on if you use StackOverflow search or not:

  • Without searching StackOverflow I found it more useful to form a full sentence (omitting the 'how to' part), for example tldrai solve \'ModuleNotFound\' error
  • To search StackOverflow (using the -s or --search flag) it's better to form a question as if you wanted to google it, for example tldrai \'ModuleNotFound\' -s

The examples are simply for illustrative purpose only and sometimes the question can be formed in a way that simultaneously satisfies the both ways described above.

Contributing

We welcome contributions to the TLDR AI CLI Tool! If you have any suggestions or find any issues, please open an issue or subApache 2.0 a pull request on our GitHub repository.

License

This project is licensed under the Apache 2.0 License. See the LICENSE file for details.

Acknowledgements


Thank you for using TLDR AI CLI Tool. We hope it enhances your productivity and makes working with complex information easier and more efficient.

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

tldrai-0.2.4.tar.gz (15.4 kB view details)

Uploaded Source

Built Distribution

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

tldrai-0.2.4-py3-none-any.whl (18.6 kB view details)

Uploaded Python 3

File details

Details for the file tldrai-0.2.4.tar.gz.

File metadata

  • Download URL: tldrai-0.2.4.tar.gz
  • Upload date:
  • Size: 15.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.11.9 Linux/6.5.0-1025-azure

File hashes

Hashes for tldrai-0.2.4.tar.gz
Algorithm Hash digest
SHA256 91f03cfc5eda3e084ca67d66dafa675abe346b1e250797fd0c1f446b252eb701
MD5 0ae71387713d2e45f9ac551424f20e9a
BLAKE2b-256 fd41aab77269471338bd13b16755f9fc1239719786d0f19961d9be6dec41e60d

See more details on using hashes here.

File details

Details for the file tldrai-0.2.4-py3-none-any.whl.

File metadata

  • Download URL: tldrai-0.2.4-py3-none-any.whl
  • Upload date:
  • Size: 18.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.11.9 Linux/6.5.0-1025-azure

File hashes

Hashes for tldrai-0.2.4-py3-none-any.whl
Algorithm Hash digest
SHA256 d83c073ab42809011e0efe0542294a6a089da2b05f6cca660489981286eedcf5
MD5 aa0d17ba866d70ffc315ddb1a10c1d82
BLAKE2b-256 d4fd31dc40497ed52e50e24b715159f924c798912b968b87e5af8b2a1f439fd9

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