thekaranacharya

langchain

🦜🔗 Build context-aware reasoning applications

gpt4all

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

open-interpreter

A natural language interface for computers

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

Startup-CTO-Handbook

The Startup CTO's Handbook, a book covering leadership, management and technical topics for leaders of software engineering teams

bandit

Bandit is a tool designed to find common security issues in Python code.

opencommit

Generate conventional git commit messages with AI in 1 second 🤯🔫

google-maps-services-python

Python client library for Google Maps API Web Services

gdown

Google Drive Public File Downloader when Curl/Wget Fails

detect-secrets

An enterprise friendly way of detecting and preventing secrets in code.

AlphaCodium

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

reflexion

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

helm

Holistic Evaluation of Language Models (HELM), a framework to increase the transparency of language models (https://arxiv.org/abs/2211.09110). This framework is also used to evaluate text-to-image models in Holistic Evaluation of Text-to-Image Models (HEIM) (https://arxiv.org/abs/2311.04287).

voyager

🛰️ An approximate nearest-neighbor search library for Python and Java with a focus on ease of use, simplicity, and deployability.

detoxify

Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.

indexify

A realtime and indexing and structured extraction engine for Unstructured Data to build Generative AI Applications

ringattention

Transformers with Arbitrarily Large Context

FActScore

A package to evaluate factuality of long-form generation. Original implementation of our EMNLP 2023 paper "FActScore: Fine-grained Atomic Evaluation of Factual Precision in Long Form Text Generation"

better_profanity

Blazingly fast cleaning swear words (and their leetspeak) in strings

fasttext-langdetect

80x faster and 95% accurate language identification with Fasttext

ExpertQA

[Data + code] ExpertQA : Expert-Curated Questions and Attributed Answers

factoid-wiki

Dense X Retrieval: What Retrieval Granularity Should We Use?

json-stream

Simple streaming JSON parser and encoder.

fast-langdetect

⚡️ 80x faster language detection with Fasttext | Split text by language for TTS

flores

The FLORES+ Machine Translation Benchmark

logikon

Analyzing and scoring reasoning traces of LLMs

customer-support-chatbot-for-FAQ-using-RAG

llm-warden

A simple jailbreak detection tool for safeguarding LLMs.

hub