A Gradio web UI for Large Language Models with support for multiple inference backends.

LlamaIndex is the leading framework for building LLM-powered agents over your data.

DSPy: The framework for programming—not prompting—language models

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Python scraper based on AI

Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.

Private chat with local GPT with document, images, video, etc. 100% private, Apache 2.0. Supports oLLaMa, Mixtral, llama.cpp, and more. Demo: https://gpt.h2o.ai/ https://gpt-docs.h2o.ai/

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

news-please - an integrated web crawler and information extractor for news that just works

Optimizing inference proxy for LLMs

Enforce the output format (JSON Schema, Regex etc) of a language model

High-performance retrieval engine for unstructured data

Custom component to calculate estimated power consumption of lights and other appliances

A FastAPI service for semantic text search using precomputed embeddings and advanced similarity measures, with built-in support for various file types through textract.

Toolkit to segment text into sentences or other semantic units in a robust, efficient and adaptable way.

VectorDBBench is a benchmark designed to compare the performance and cost-effectiveness of popular vector databases.

A collection of prompts to challenge the reasoning abilities of large language models in presence of misguiding information

Search your codebase with natural language • CLI • No data leaves your computer

Formatron empowers everyone to control the format of language models' output with minimal overhead.

Making openapi spec swagger documents friendly for GPT and other LLMs.

Full Text Search Benchmark, a tool for comparing and evaluating full-text search engines.