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+.

knowledge-rag

Local RAG MCP server for Claude Code — hybrid search (semantic + BM25), cross-encoder reranking, 13 MCP tools, 20 format parsers. Zero external servers, zero API keys.

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

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

gvdb

Python client for GVDB distributed vector database

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.

uscient-mboxer

Local-first MBOX parser that converts Gmail Takeout archives into structured Markdown, SQLite, and JSONL pipelines for NotebookLM and private RAG workflows.

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.

google-okf

google-okf is a production-grade, open-source Python library designed to automatically connect to various enterprise data sources and convert them into the standard Google Open Knowledge Format (OKF).

ragwire

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

insta-rag

A RAG (Retrieval-Augmented Generation) library for document processing and retrieval.

embedrag

A RAG system can be shipped with applications and supports million-scale record retrieval.

ragobserve

A Observability platform for Rag application, supports built in langchain and llamaindex integration

clinical-tabular

Privacy-first clinical intelligence & EHR platform. React 19 Vite portal, FastAPI backend, LangGraph RAG, local Ollama LLM, XGBoost diagnostics (Diabetes, Heart, Liver, Kidney, Lungs), HL7 FHIR R4, ABDM consent stack, PySpark Delta Lake, Terraform AWS EKS IaC, Prometheus telemetry.

intentmind

Language-agnostic associative memory runtime for persistent AI systems

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.

pyragcore

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

ragit

Correct complete RAG -- built for Highway Workflow Engine

vrraj-llm-adapter

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

ennoia

Declarative Document Indexing (DDI) framework for Python. Define schemas, extract structured indices, search smarter.

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.

netapp-aide-mcp

MCP server for NetApp AI Data Engine