RAG & Knowledge Basesfree

Self hosted RAG using Ollama and Qdrant

by Mabura Ze GuruUpdated Aug 2026

RequiresOllama

Share Post Share

1/5

STEPS · 8

Starts from a chat message

On a chat message, a self-hosted Ollama RAG agent answers questions using a Qdrant vector store of uploaded documents.

Related workflows

See all RAG & Knowledge Bases→

FluxonLab libraryfree

Gemini RAG Email And Chat Assistant

On a form submission, runs Google Gemini over aggregated input, emails results via Gmail, and indexes documents into Pinecone for chat-based retrieval.

by FluxonLab Import

FluxonLab libraryfree

Build a Chatbot, Voice Agent and Phone Agent with Voiceflow, Google Calendar and RAG

On a webhook, an OpenAI RAG agent over Qdrant answers questions, checks Google Calendar, and replies; indexes Google Drive docs.

by FluxonLab Import

FluxonLab librarypro

Create AI Ready Vector Datasets for Llms with Bright Data, Gemini & Pinecone

On manual run, fetches and extracts web content with Google Gemini, then embeds it and upserts the vectors into a Pinecone store.

by FluxonLab Import

Self hosted RAG using Ollama and Qdrant

Tags

Related workflows

Gemini RAG Email And Chat Assistant

Build a Chatbot, Voice Agent and Phone Agent with Voiceflow, Google Calendar and RAG

Create AI Ready Vector Datasets for Llms with Bright Data, Gemini & Pinecone