SaiAkhil066/CORTEX-AI-SUPER-RAG

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1962 stars · 291 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

CORTEX RAG is a local-first, agentic retrieval-augmented generation application that lets users upload PDFs and ask questions with cited answers, running entirely on their machine via Ollama. It combines nine RAG techniques including contextual retrieval, RAG-Fusion with reciprocal rank fusion, GraphRAG knowledge graphs, and corrective RAG chunk grading.

Use cases

• ask questions about pdf documents with citations
• build a local rag chatbot without api keys
• chat with company documents privately offline
• retrieve answers from documents using knowledge graphs
• run a document question answering system with ollama
• improve rag recall with query fusion and reranking

When to choose

• you need private, on-machine document Q&A with no cloud upload
• you want advanced RAG techniques like GraphRAG and CRAG in one pipeline
• you want cited answers from PDFs using local LLMs

When to avoid

• you need a managed cloud RAG service with enterprise SSO
• you have no hardware to run local LLMs
• you need non-PDF enterprise connectors out of the box

Facets

application · maturity active

rag search-engine llm-inference chatbot pdf nlp large-language-models artificial-intelligence pdf python cross-platform self-hosted rag-fusion graphrag corrective-rag ollama streamlit local-llm knowledge-graph citations privacy-first retrieval-augmented-generation natural-language-processing

Member repositories

For agents

markdown · JSON · MCP: product_card(name="SaiAkhil066/CORTEX-AI-SUPER-RAG")