Rag Pipeline Python Packages

toon-llm

Token-Oriented Object Notation (TOON) is an LLM-optimized data serialization format implemented in Python.

gvdb

High-performance distributed vector database with gRPC API and high-dimensional vector support

navi-sanitize

Deterministic input sanitization for untrusted text — invisible characters, homoglyphs, and encoding tricks, handled before your code sees them. Zero dependencies, no ML. Python 3.12+.

projectdavid-platform

A single pip installed package will orchestrate a production ready instance of the AI stack in any environment

superagentx

Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools, MCPs, models, data, and policies with consistent observability and governance.

latence-solver

CPU-reference-first Tabu Search Quadratic Knapsack solver with optional accelerator hooks

synapsekit

Minimal, async-first Python framework for production LLM apps- 2 hard deps, no magic, no SaaS.

nanoindex

Agentic RAG Harness for long documents, Tree and Graph based reasoning. Cited answers down to the pixel

helix-context

Agent knowledge index — IDF-weighted retrieval without embedding models. SQLite-only, sub-650ms at 17K+ entries on consumer hardware.

ennoia

Declarative Document Indexing (DDI) Schemas for RAG — LLM-powered pre-indexing and hybrid retrieval.

superagentx-handlers

Move from idea to production in hours with policy-driven autonomous AI agents. Unified Control Plane: Centralised tools, MCPs, models, data, and policies with consistent observability and governance.

rag-forge-core

Production-grade RAG pipelines with evaluation baked in

rag-forge-observability

Production-grade RAG pipelines with evaluation baked in

rag-forge-evaluator

Production-grade RAG pipelines with evaluation baked in

netapp-aide-mcp

MCP server for NetApp AI Data Engine

voyager-index

Shard-first late-interaction retrieval for ColBERT and ColPali style workloads with CPU/GPU modes, Triton MaxSim, BM25 hybrid search, durable CRUD/WAL, multimodal preprocessing, and base64-ready reference APIs.

ragwire

RAGWire — Production-grade RAG toolkit for document ingestion and retrieval with hybrid search support

vrraj-bm25s-retriever

Lexical routing layer for LLM tool selection. Filter MCP-discovered and registry tools before prompt assembly using fast BM25S retrieval.

kektordb-client

An official Python client for KektorDB. AI memory system combining vector search with temporal knowledge graph. Built-in cognitive engine for agents. Supports memory decay, contradiction detection, and MCP integration.

ragit

Correct complete RAG -- built for Highway Workflow Engine

simpleaudit

Lightweight AI Safety Auditing Framework

vrraj-llm-adapter

Provider-agnostic, registry-driven LLM adapter for text generation and embeddings with normalized outputs - includes an interactive test UI.

insta-rag

A python module library that simplifies RAG through abstraction

supavector

Persistent AI memory engine