Skip to main content

MTLLM Provides Easy to use APIs for different LLM Providers to be used with Jaseci's Jaclang Programming Language.

Project description

MTLLM API library

PyPI version tests

The MTLLM Python library provides convenient access to a large number of easy to use and customizable APIs to be used in Jaseci's Jaclang by llm feature. The Library provides automatic output fixing, output type validation, different prompting techniques, and more.

Documentation

The documentation on how to use this library with Jaseci's Jaclang can be found here.

Installation

[!IMPORTANT] Though this is can be used with python projects, it is primarily intended to be used with Jaseci's Jaclang.

# install from PyPI
pip install mtllm

Usage

The full API of this library can be found here.

Using Different LLMs

import:py from mtllm.llms, OpenAI;

glob llm = OpenAI();

can "Translate English to French"
translate(word: "English Word": str) -> "French Word": str by llm();

Based on your LLM of choice, make sure to set the API Key in the environment variable. For example, for OpenAI:

export OPENAI_API_KEY="your-api-key"

Using Tools

import:py from mtllm.llms, OpenAI;
import:py from mtllm.tools, wikipedia;

glob llm = OpenAI();

can "Answer History Questions"
history_qa(question: "History Question": str) -> "Detailed Answer": str by llm(tools=[wikipedia]);

Supported LLMs and Tools

TBA

Contributing

Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.

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

mtllm-0.1.14.tar.gz (12.3 kB view details)

Uploaded Source

Built Distribution

mtllm-0.1.14-py3-none-any.whl (18.6 kB view details)

Uploaded Python 3

File details

Details for the file mtllm-0.1.14.tar.gz.

File metadata

  • Download URL: mtllm-0.1.14.tar.gz
  • Upload date:
  • Size: 12.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.12.4 Linux/6.5.0-1022-azure

File hashes

Hashes for mtllm-0.1.14.tar.gz
Algorithm Hash digest
SHA256 fc7e32ba263f776a389a823d5ed318b324583bb8d3252c10dcd78d8d71ba6ae2
MD5 cf79c7d652756d2d6d5229867934a018
BLAKE2b-256 5f6e491daf60039e7789159f8f235b2163222f5903dae143701d63e9210f524a

See more details on using hashes here.

File details

Details for the file mtllm-0.1.14-py3-none-any.whl.

File metadata

  • Download URL: mtllm-0.1.14-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/3.12.4 Linux/6.5.0-1022-azure

File hashes

Hashes for mtllm-0.1.14-py3-none-any.whl
Algorithm Hash digest
SHA256 77468f34f5768a4da29d04db2f34ad019830fef5cb01dc46e911f1df8e1d1344
MD5 a2aa67be1ac8cbb69b97d78719532388
BLAKE2b-256 2a40a55572adf4929fdf5829b190c5d27f14d342827312034cf5b9879d586e1c

See more details on using hashes here.

Supported by

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