UniqAI/open-webui
1
0
Fork 0
mirror of https://github.com/open-webui/open-webui synced 2024-11-21 23:57:51 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

added the drop capability and updated readme accordingly

Browse Source
This commit is contained in:
Daniele Viti 2023-12-24 14:21:34 +01:00
parent 567b88bb00
commit 7063f00b71
2 changed files with 18 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
README.md
View File

@ -73,13 +73,22 @@ Don't forget to explore our sibling project, [OllamaHub](https://ollamahub.com/)
### Installing Both Ollama and Ollama Web UI Using Docker Compose
If you don't have Ollama installed yet, you can use the provided Docker Compose file for a hassle-free installation. Simply run the following command:
If you don't have Ollama installed yet, you can use the provided bash script for a hassle-free installation. Simply run the following command:
For cpu-only container
```bash
docker compose up -d --build
chmod +x run-compose.sh && ./run-compose.sh
```
This command will install both Ollama and Ollama Web UI on your system. Ensure to modify the `compose.yaml` file for GPU support and Exposing Ollama API outside the container stack if needed.
For gpu-enabled container (to enable this you must have your gpu driver for docker, it mostly works with nvidia so this is the official install guide: [nvidia-container-toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html))
```bash
chmod +x run-compose.sh && ./run-compose.sh --enable-gpu[count=1]
```
Note that both the above commands will use the latest production docker image in repository, to be able to build the latest local version you'll need to append the `--build` parameter, for example:
```bash
./run-compose.sh --build --enable-gpu[count=1]
```
### Installing Ollama Web UI Only

10
run-compose.sh
View File

@ -80,10 +80,12 @@ usage() {
echo " -h, --help Show this help message."
echo ""
echo "Examples:"
echo " $0 --enable-gpu[count=1]"
echo " $0 --enable-api[port=11435]"
echo " $0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000]"
echo " $0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000] --data[folder=./ollama-data]"
echo " ./$0 --drop"
echo " ./$0 --enable-gpu[count=1]"
echo " ./$0 --enable-api[port=11435]"
echo " ./$0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000]"
echo " ./$0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000] --data[folder=./ollama-data]"
echo " ./$0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000] --data[folder=./ollama-data] --build"
echo ""
echo "This script configures and runs a docker-compose setup with optional GPU support, API exposure, and web UI configuration."
echo "About the gpu to use, the script automatically detects it using the "lspci" command."