LLM/self-hosted-ai-starter-kit
1
0
Fork 0
mirror of https://github.com/n8n-io/self-hosted-ai-starter-kit.git synced 2025-11-29 00:23:13 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: Minor Clarifications to README (#10)

Browse Source 
Co-authored-by: Kate Mueller <freakwriter@users.noreply.github.com>
This commit is contained in:
Yonatan Mark Liudmirsky
2024-09-24 13:16:35 +03:00
committed by GitHub
parent d62f899c29
commit 6a3d5a0920
1 changed files with 23 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

41
README.md
View File

@@ -1,8 +1,6 @@
# Self-hosted AI starter kit # Self-hosted AI starter kit
**Self-hosted AI Starter Kit** is an open, docker compose template that **Self-hosted AI Starter Kit** is an open-source Docker Compose template designed to swiftly initialize a comprehensive local AI and low-code development environment.
quickly bootstraps a fully featured Local AI and Low Code development
environment.
![n8n.io - Screenshot](https://raw.githubusercontent.com/n8n-io/self-hosted-ai-starter-kit/main/assets/n8n-demo.gif) ![n8n.io - Screenshot](https://raw.githubusercontent.com/n8n-io/self-hosted-ai-starter-kit/main/assets/n8n-demo.gif)
@@ -29,17 +27,26 @@ Engineering world, handles large amounts of data safely.
### What you can build ### What you can build
⭐️ AI Agents which can schedule appointments ⭐️ **AI Agents** for scheduling appointments
⭐️ Summarise company PDFs without leaking data ⭐️ **Summarize Company PDFs** securely without data leaks
⭐️ Smarter slack bots for company comms and IT-ops ⭐️ **Smarter Slack Bots** for enhanced company communications and IT operations
⭐️ Analyse financial documents privately and for little cost ⭐️ **Private Financial Document Analysis** at minimal cost
## Installation ## Installation
### For Nvidia GPU users ### Cloning the Repository
```bash
git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git
cd self-hosted-ai-starter-kit
```
### Running n8n using Docker Compose
#### For Nvidia GPU users
``` ```
git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git
@@ -51,7 +58,7 @@ docker compose --profile gpu-nvidia up
> If you have not used your Nvidia GPU with Docker before, please follow the > If you have not used your Nvidia GPU with Docker before, please follow the
> [Ollama Docker instructions](https://github.com/ollama/ollama/blob/main/docs/docker.md). > [Ollama Docker instructions](https://github.com/ollama/ollama/blob/main/docs/docker.md).
### For Mac / Apple Silicon users #### For Mac / Apple Silicon users
If you’re using a Mac with an M1 or newer processor, you can't expose your GPU If you’re using a Mac with an M1 or newer processor, you can't expose your GPU
to the Docker instance, unfortunately. There are two options in this case: to the Docker instance, unfortunately. There are two options in this case:
@@ -74,7 +81,7 @@ docker compose up
After you followed the quick start set-up below, change the Ollama credentials After you followed the quick start set-up below, change the Ollama credentials
by using `http://host.docker.internal:11434/` as the host. by using `http://host.docker.internal:11434/` as the host.
### For everyone else #### For everyone else
``` ```
git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git git clone https://github.com/n8n-io/self-hosted-ai-starter-kit.git
@@ -84,10 +91,8 @@ docker compose --profile cpu up
## ⚡️ Quick start and usage ## ⚡️ Quick start and usage
The main component of the self-hosted AI starter kit is a docker compose file The core of the Self-hosted AI Starter Kit is a Docker Compose file, pre-configured with network and storage settings, minimizing the need for additional installations.
pre-configured with network and disk so there isn’t much else you need to After completing the installation steps above, simply follow the steps below to get started.
install. After completing the installation steps above, follow the steps below
to get started.
1. Open <http://localhost:5678/> in your browser to set up n8n. You’ll only 1. Open <http://localhost:5678/> in your browser to set up n8n. You’ll only
have to do this once. have to do this once.
@@ -116,9 +121,9 @@ language model and Qdrant as your vector store.
## Upgrading ## Upgrading
### For Nvidia GPU users * ### For Nvidia GPU setups:
``` ```bash
docker compose --profile gpu-nvidia pull docker compose --profile gpu-nvidia pull
docker compose create && docker compose --profile gpu-nvidia up docker compose create && docker compose --profile gpu-nvidia up
``` ```
@@ -130,9 +135,9 @@ docker compose pull
docker compose create && docker compose up docker compose create && docker compose up
``` ```
### For everyone else * ### For Non-GPU setups:
``` ```bash
docker compose --profile cpu pull docker compose --profile cpu pull
docker compose create && docker compose --profile cpu up docker compose create && docker compose --profile cpu up
``` ```