4lt/docker-compose-cookbooks
1
0
Fork 0
mirror of https://github.com/nickyeoman/docker-compose-cookbooks.git synced 2026-09-04 02:46:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

updated opencode config

Browse Source
This commit is contained in:
nick
2026-06-20 21:17:53 +00:00
parent a3333d344c
commit bc4ed4957e
4 changed files with 28 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ollama/README.md
+17 -4
View File
@@ -25,6 +25,9 @@ docker exec -it ollama ollama run llama3
WEBUI_SECRET_KEY is just a random secret string used to secure sessions, cookies, and auth in your WebUI. ```openssl rand -hex 32``` WEBUI_SECRET_KEY is just a random secret string used to secure sessions, cookies, and auth in your WebUI. ```openssl rand -hex 32```
You could also set OLLAMA_KEEP_ALIVE=5m if you are running multiple models. 5m is default, 0 removes as soon as done (then would have to reload model, so not quick), more than 5m is longer (minutes).
See "Docker Container Cheatsheet" below for how to remove models from memory.
## Use ## Use
- [Ollama Models](https://ollama.com/search) - [Ollama Models](https://ollama.com/search)
@@ -44,17 +47,27 @@ ollamac list
Standard commands Standard commands
```bash ```bash
# Enter a shell
docker exec -it ollama-ollama-1 sh
# Add/Pull a model # Add/Pull a model
docker exec -it ollama-ollama-1 ollama pull llama3.1:8b ollama pull llama3.1:8b
# list models # list models
docker compose exec -it ollama ollama list ollama list
# Remove a model # Remove a model
docker compose exec -it ollama ollama rm <model-name> ollama rm <model-name>
# Run CLI # Run CLI
docker compose exec -it ollama ollama run deebseek-r1:8b "What is Star Trek?" ollama run <model-name> "What is Star Trek?"
# See what's running
ollama ps
# Clear memory
ollama stop <model-name>
``` ```
### API ### API
opencode/compose.yaml
+3 -3
View File
@@ -14,10 +14,10 @@ services:
- OPENCODE_PORT=${OPENCODE_PORT:-4096} - OPENCODE_PORT=${OPENCODE_PORT:-4096}
- OPENCODE_HOSTNAME=${OPENCODE_HOSTNAME:-0.0.0.0} - OPENCODE_HOSTNAME=${OPENCODE_HOSTNAME:-0.0.0.0}
- OPENCODE_CONFIG=/config/config.json - OPENCODE_CONFIG=/config/config.json
- OPENCODE_MODEL=ollama/qwen3:8b-16k - OPENCODE_MODEL=qwen3:8b-16k
- OLLAMA_HOST=http://10.1.1.16:11434 - OLLAMA_HOST=${OLLAMA_HOST_URL:-http://localhost:11434}
ports: ports:
- "${OPENCODE_PORT:-4096}:4096" - "${OPENCODE_PORT:-4096}:4096"
command: ["serve", "--hostname", "0.0.0.0", "--port", "4096"] command: ["serve", "--port", "${OPENCODE_PORT:-4096}"]
opencode/config/config.json
+7 -3
View File
@@ -1,15 +1,19 @@
{ {
"$schema": "https://opencode.ai/config.json", "$schema": "https://opencode.ai/config.json",
"model": "ollama/qwen3:8b-16k", "model": "qwen3:8b-16k",
"provider": { "provider": {
"ollama": { "ollama": {
"npm": "@ai-sdk/openai-compatible", "npm": "@ai-sdk/openai-compatible",
"options": { "options": {
"baseURL": "http://10.1.1.16:11434/v1" "baseURL": "http://localhost:11434/api/v1"
}, },
"models": { "models": {
"qwen3:8b-16k": { "qwen3:8b-16k": {
"tools": true "name": "Qwen3 8B (16k UI-Context)",
"tools": true,
"limit": {
"maxTokens": 8192
}
} }
} }
} }
opencode/sample.env
+1
View File
@@ -3,3 +3,4 @@ OPENCODE_RESTART=unless-stopped
VOL_PATH=/home/youruser/.local/share VOL_PATH=/home/youruser/.local/share
OPENCODE_PORT=4096 OPENCODE_PORT=4096
OPENCODE_HOSTNAME=0.0.0.0 OPENCODE_HOSTNAME=0.0.0.0
OLLAMA_HOST=http://localhost:11434