Vectorless, Reasoning-Based Retrieval-Augmented Generation (RAG)
-
Updated
Mar 26, 2026 - Python
#
vectorless-rag
Here are 29 public repositories matching this topic...
Agentic RAG Harness for long documents, Tree and Graph based reasoning. Cited answers down to the pixel
pdf ocr graph indexing citations knowledge-graph question-answering vlm nanonets rag document-ai llm rag-pipeline vlm-ocr vectorless-rag
-
Updated
Apr 15, 2026 - Python
Tree-based, vectorless document RAG framework. Connect any LLM via URL/API key.
-
Updated
Apr 7, 2026 - TypeScript
Local-first AI paper reader with vectorless PDF RAG, page/bbox citations, OCR/TSR table evidence, PDF translation, and local Codex/Claude agents.
agent pdf research-tool pdf-reader paper-reading rag local-first academic-papers pdf-translation llm agentic-rag vectorless-rag
-
Updated
Jul 6, 2026 - Rust
PageIndex-inspired agentic RAG app for vectorless document QA, FastAPI, multi-document retrieval, context compaction, and self-hosted AI workspaces.
self-hosted document-retrieval pageindex rag fastapi long-context document-qa pdf-qa react-agent agentic-rag retrival-augmented-generation pdf-rag vectorless-rag pageindex-web markdown-qa docx-qa pageindex-app document-rag
-
Updated
Jul 8, 2026 - Python
AI-first manual checklist builder using PageIndex-style vectorless retrieval + local Gemma4 to generate grounded maintenance checklists with strict citations.
redis pageindex rag applied-ai document-ai local-llm rag-pipeline docker-model-runner vectorless-rag gemma4 maintenance-ai
-
Updated
Apr 22, 2026 - TypeScript
Implements a vectorless RAG architecture using PageIndex APIs and Groq LLMs, enabling efficient document retrieval and response generation without traditional vector databases.
-
Updated
Apr 9, 2026 - Jupyter Notebook
Reasoning-based, vectorless RAG over a large document using a hierarchical tree (PageIndex) and a Vision-Language Model (Llama 4 Scout), no embeddings, no vector store, no text chunking.
-
Updated
Mar 13, 2026 - Jupyter Notebook
RAG on PDF documents without a vector database. Uploads are indexed into a hierarchical document tree via the PageIndex API — at query time, Llama 3.1 (Groq) walks the tree to select the most relevant sections, then generates a grounded answer from their full content. Includes a FastAPI backend and a simple web UI.
embeddings artificial-intelligence language-model langchain retrieval-augmented-generation rag-pipeline langsmith-tracing data-retriever-step-by-step vectorless-rag
-
Updated
Jun 9, 2026 - HTML
A production-grade, LangGraph-orchestrated fraud detection system built for regulated financial environments. Combines ML risk scoring, LLM-powered document forensics, and a Human-in-the-Loop compliance workflow — end-to-end.
python ci-cd fintech multi-agent-systems fraud-detection human-in-the-loop mlflow fastapi triton-inference-server ollama langgraph vectorless-rag
-
Updated
Apr 14, 2026 - Python
Vector RAG vs. Vectorless RAG vs. OKF
-
Updated
Jul 12, 2026 - Python
Vectorless RAG using reasoning over hierarchical document structure instead of embeddings or vector databases.
-
Updated
Apr 6, 2026 - Python
Vectorless RAG for SEC 10-K filings using PageIndex — tree-based reasoning retrieval with Claude, no vector DB, no embeddings, no chunking
python flask finance tree-search pageindex claude sec-filings rag llm anthropic retrieval-augmented-generation vectorless-rag
-
Updated
Apr 18, 2026 - HTML
Vectorless semantic indexing SDK that converts large text into searchable knowledge trees for fast, structured retrieval.
-
Updated
Apr 25, 2026 - TypeScript
A retrieval-augmented generation (RAG) system for querying ML/AI research papers using BM25 sparse retrieval — no vector embeddings or external APIs required. Users ask natural language questions and receive grounded answers with citations to the source papers.
python nlp arxiv bm25 qna scientific-papers rag streamlit local-llm retrieval-augmented-generation ollama vectorless-rag
-
Updated
Apr 6, 2026 - Python
Serverless Vectorless RAG on AWS — upload documents, ask questions, get grounded answers using LLM reasoning instead of embeddings or vector databases. Built with Amazon Bedrock (Claude 3 Haiku), Lambda, DynamoDB, API Gateway, React, and Terraform.
-
Updated
Apr 10, 2026 - Python
Document Q&A system using LLM Tree RAG — no vector embeddings needed. Upload files (PDF, DOCX, XLSX), build hierarchical summary trees, and ask questions with cited answers. Supports Ollama, OpenAI, Gemini & Anthropic.
-
Updated
Jun 18, 2026 - TypeScript
An autonomous support triage agent powered by Vectorless RAG (PageIndex) and local LLMs to intelligently classify, route, and resolve customer tickets.
-
Updated
May 19, 2026 - Python
Enterprise-grade vectorless retrieval platform engineered for deterministic knowledge orchestration, explainable AI search, contextual document intelligence, and scalable enterprise retrieval workflows without vector embeddings.
react redis elasticsearch postgresql bm25 enterprise-search opensearch ai-search explainable-ai knowledge-engine retrieval-systems fastapi contextual-search document-intelligence enterprise-ai enterprise-platforms llm-infrastructure vectorless-rag knowledge-orchestration deterministic-retrieval
-
Updated
Jul 10, 2026
⚡ The Agent-Native Retrieval Engine — Hybrid Vector + Reasoning + Memory for AI Agents. HNSW indexing, tree-based reasoning retrieval, multi-agent orchestration, MCP server, and built-in RAG.
multi-agent semantic-search ai-agents rag hnsw hybrid-retrieval mcp-server agent-memory vectorless-rag reasoning-rag hybrid-rtree-index
-
Updated
Mar 10, 2026 - JavaScript
Improve this page
Add a description, image, and links to the vectorless-rag topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the vectorless-rag topic, visit your repo's landing page and select "manage topics."