Rag Pipeline Python Packages

toon-llm

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

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+.

gvdb

High-performance distributed vector database with high-dimensional vector support

pyragcore

A reusable, modular RAG (Retrieval-Augmented Generation) core library built on FAISS and Ollama

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.

projectdavid-platform

Deployment orchestrator for the Project David / Entities platform

synapsekit

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

keovil

Private Query Interface for Documents & Structured Data

nanoindex

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

latence-solver

High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, and a FastAPI server — single machine, CPU or GPU.

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.

helix-context

Agent knowledge index — IDF-weighted retrieval with deterministic SLM embedded models. SQLite, 17K+ entries on consumer hardware at 5x compression. Know-vs-Go

vrraj-bm25s-retriever

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

voyager-index

High-performance late-interaction retrieval engine for on-prem AI. ColBERT/ColPali multi-vector search with Rust fused MaxSim, Triton GPU kernels, ROQ quantization, LEMUR routing, WAL-backed CRUD, and a FastAPI server — single machine, CPU or GPU.

ragwire

Production-grade RAG toolkit — ingest PDFs, DOCX, XLSX into Qdrant with LLM metadata extraction, hybrid search, and SHA256 deduplication.

ennoia

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

rag-forge-core

Production-grade RAG pipelines with evaluation baked in

netapp-aide-mcp

MCP server for NetApp AI Data Engine

rag-forge-evaluator

Production-grade RAG pipelines with evaluation baked in

rag-forge-observability

Production-grade RAG pipelines with evaluation baked in

vrraj-llm-adapter

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

kektordb-client

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

cybersec-scanner

A comprehensive security scanner and RAG-based vulnerability analyzer

ragit

Correct complete RAG -- built for Highway Workflow Engine