langdash 1.0.1a1

A simple library for interfacing with language models.

langdash

Announcement post

A simple library for interfacing with language models.

Currently in alpha!

Features:

• Support for text generation, text classification (through prompting) and vector-based document searching.
• Lightweight, build-it-yourself-style prompt wrappers.
• Token healing and transformers/RNN state reuse for fast inference, like in Microsoft's guidance.
• First-class support for ggml backends.

Documentation: Read on readthedocs.io

Installation

Use pip to install. By default, langdash does not come preinstalled with any additional modules. You will have to specify what you need like in the following command:

pip install --user langdash[embeddings,sentence_transformers]

List of modules:

• core:
  • embeddings: required for running searching through embeddings
• backends:
  • Generation backends: rwkv_cpp, llama_cpp, transformers
  • Embedding backends: sentence_transformers

Note: If running from source, initialize the git submodules in the langdash/extern folder to compile foreign backends.

Usage

Examples:

• Text generation
• Generating TV shows
• Embedding search

See examples folder for full examples.

License

Apache 2.0