Skip to content

Commit 057bbb0

Browse files
authored
Ai model (#55)
* Added AI Model example application * Skipping AI Model tests due to model sizes and image sizes * Included compose
1 parent c7f180a commit 057bbb0

File tree

4 files changed

+38
-0
lines changed

4 files changed

+38
-0
lines changed

ai-model/.skiptest

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1 @@
1+
Skips the current directory during automated test runs.

ai-model/README.md

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
# Introduction
2+
3+
This is an example on how to run an AI model with [Ollama](https://ollama.com/)

ai-model/compose.yml

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,3 @@
1+
services:
2+
gcb-ai-model:
3+
image: ollama/ollama

ai-model/usage_scenario.yml

Lines changed: 31 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,31 @@
1+
---
2+
name: AI model
3+
author: Arne Tarara <[email protected]>
4+
description: Run an inference with a small AI model
5+
6+
compose-file: !include compose.yml
7+
8+
flow:
9+
- name: Download gemma3:1b
10+
container: gcb-ai-model
11+
commands:
12+
- type: console
13+
command: ollama pull gemma3:1b
14+
read-notes-stdout: true
15+
log-stdout: true
16+
17+
- name: Load gemma3:1b into memory
18+
container: gcb-ai-model
19+
commands:
20+
- type: console
21+
command: ollama run gemma3:1b "?"
22+
read-notes-stdout: true
23+
log-stdout: true
24+
25+
- name: Run Inference on gemma3:1b
26+
container: gcb-ai-model
27+
commands:
28+
- type: console
29+
command: ollama run gemma3:1b "Tell me a long joke?"
30+
read-notes-stdout: true
31+
log-stdout: true

0 commit comments

Comments
 (0)