Use ollama embeddings hosted on a server using weaviate

DudaNogueira · December 29, 2024, 1:56pm

hi @P_K !!

Welcome back

Check out this recipe:

weaviate/recipes/blob/main/weaviate-features/generative-search/local_rag_using_ollama_integration_using_embedded.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Local RAG with Ollama and Weaviate\n",
    "## Using Weaviate integration\n",
    "\n",
    "This example shows how to use the text2vec-ollama as well the generative-ollama "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setup \n",
    "1. Download and install Ollama for your operating system: https://ollama.com/download\n",
    "2. `pip` install the Python library to generate vector embeddings from the model  with `pip install ollama`. (REST API or JavaScript library also available)"
   ]

This file has been truncated. show original

It will use ollama to create a RAG locally.

Let me know if that helps!

Topic		Replies	Views
Text2vec ollama embedding error Support	3	552	November 5, 2024
[Question] Getting Weaviate and Ollama working together running locally Support technical	2	179	February 4, 2025
Issues Configuring weaviate to work with an ollama Docker Instance (v4 client) Support documentation	1	259	January 27, 2025
How to Use different embedding than OpenAI Support	1	218	August 16, 2024
Text2vec-ollama examples General	1	408	June 7, 2024

Use ollama embeddings hosted on a server using weaviate

Related topics