Deepseek Local RAG via Flowise

This talk demonstrates building a fully local RAG system using Deepseek-r1:7b and Flowise to generate SQL queries and user-friendly answers from an SQL database in a low-code environment.

Overview

With the recent evolution in small performant models, it is quite possible now to replace openai api with a locally running deepseek-r1:7b model. In this demo will showcase how you can quickly run a completely locally Hosted RAG flow retreiving data from an sql based database when prompting for data such as list the companies with highest sales last year in technology sector, the flow will extraxt the ddl, understand the schema, generate the required sql query statement and then return the results and run them through deepseek again to generate a user friendly answer in a chat experience.

Tech stack

Related projects

RAGistotle - a multi modal RAG

Dubai

This talk demonstrates a multi-modal RAG system handling text, audio, video, images, data files, and YouTube links, integrating…

AI-Native: Live Coding an Agentic RAG That Thinks and Adapts

Abu Dhabi

Live coding an agentic RAG that parses user intent into structured retrieval workflows, demonstrated through a mental‑health therapist…

SlateFront AI: A new way to learn with AI, visually.

Abu Dhabi

Learn how SlateFront uses AI to instantly turn text or sketches into accurate math and physics animations, enabling…

Agents using Advanced RAG Capabilities

Dubai

Demonstrates a proof‑of‑concept using modern retrieval methods—late interaction, OCR‑free pipelines, reasoning retrievers, and hypothetical embeddings—to improve agentic systems…

From Crawl to Chat: Building AI Assistants with Web Crawlers, RAG, and LLMs

Dubai

Learn to build domain-specific AI assistants using web crawling, pgvector storage, and RAG with OpenAI, covering deployment and…

Qdash

Abu Dhabi

This talk demonstrates how to create interactive dashboards directly from natural language inputs, simplifying data visualization and analysis…