44 dependents
| Package | Description | Downloads/month |
|---|---|---|
| Pythonic class-based interface to LLMs | 17K | |
| Fast and Accurate Code Search for Agents. Uses ~98% fewer tokens than grep+read | 8K | |
| Advanced Artificial Intelligence Tools is a package meant to develop and enable ... | 6K | |
| search through files with fts5, vectors and get reranked results. Fast | 6K | |
| A library for efficient Retrieval-Augmented Generation research | 3K | |
| A perfect AI powered RAG for document query and summary. Supports ~all LLM and ~... | 3K | |
| Modern Data Centric AI system for Large Language Models | 3K | |
| Plug-and-play document AI with zero-shot models. | 2K | |
| The testing platform for AI teams. Bring engineers, PMs, and domain experts toge... | 2K | |
| 2K | ||
| A powerful CLI super agent | 1K | |
| Deterministic text generation and embeddings with zero configuration | 1K | |
| GraWiki is an open source Python project for graph-backed knowledge extraction, ... | 1K | |
| Client-side toolkit for using large language models, including where self-hosted | 1K | |
| A minimalistic RAG system that prevents hallucination by ensuring all generated ... | 1K | |
| Hybrid BM25+dense RAG for Python — streaming, agent tools, and multi-tenancy on ... | 1K | |
| Easy Data Preparation with latest LLMs-based Operators and Pipelines. | 1K | |
| 921 | ||
| Local document/photo search with WhatsApp bot | 873 | |
| Local vector store for Obsidian notes with semantic search via MCP server | 749 | |
| Give your AI coding agent memory across sessions | 639 | |
| From data to vector database effortlessly | 571 | |
| Production-grade RAG in 4 lines — hybrid search, streaming, and agent tools on b... | 517 | |
| PDFStract - Extract, Chunking and Embedding Layer in Your RAG Pipeline - Availab... | 504 | |
| Additional packages (components, document stores and the likes) to extend the ca... | 427 | |
| llama-index embeddings AutoEmbeddings integration | 426 | |
| AI Search tools. | 303 | |
| ⚡ Debug your RAG pipeline without leaving the terminal. Real-time chunking visua... | 265 | |
| llama-index Chonkie integration | 242 | |
| Synapso Core | 240 | |
| Fast, efficient, minimal, extendible and elegant RAG system | 216 | |
| A powerful CLI tool to manage, test, and optimize RAG pipelines. Streamline your... | 212 | |
| Lightweight RAG library with Milvus vector store | 203 | |
| Judge and evaluate your chunk quality with Judie, the Owl! Quick, easy, and effe... | 104 | |
| Nowledge Graph MCP Server - Local-first personal memory management | 103 | |
| Agent 记忆模块 — 记忆演化：自动去重、合并、衰减 | 101 | |
| A library for working with UK Parliamentary data | 94 | |
| 🤔 wondering if your chunks are good? 🦉 Judie is here to Judge and Evaluate your ... | 91 | |
| Smart feed extraction and processing tool with DSPy-powered LLM extraction | 87 | |
| Some widgets to start developping advanced functionalities in Orange Data Mining... | 84 | |
| Utility functions for managing and processing chonkie Chunk objects | 79 | |
| Directly Parse and Chunk all the office files inside the folders | 65 | |
| Code Context — plug-and-play codebase indexing and semantic search for AI coding... | 4 | |
| Intelligent RAG system with advanced OCR, semantic chunking, and production-read... | 1 |
