43 lines
1.1 KiB
Markdown
43 lines
1.1 KiB
Markdown
# LocalAI
|
|
|
|
```
|
|
sudo mkdir -p /mnt/data/localai
|
|
```
|
|
|
|
```bash
|
|
cd /mnt/data
|
|
|
|
git clone https://github.com/go-skynet/LocalAI
|
|
|
|
cd LocalAI
|
|
|
|
# (optional) Checkout a specific LocalAI tag
|
|
# git checkout -b build <TAG>
|
|
|
|
# copy your models to models/
|
|
wget https://gpt4all.io/models/ggml-gpt4all-j.bin -O models/ggml-gpt4all-j
|
|
|
|
# cp your-model.bin models/
|
|
|
|
# Use a template from the examples
|
|
cp -rf prompt-templates/ggml-gpt4all-j.tmpl models/
|
|
|
|
# (optional) Edit the .env file to set things like context size and threads
|
|
# vim .env
|
|
|
|
docker-compose up -d --build
|
|
|
|
# Now API is accessible at localhost:8080
|
|
curl http://localhost:8080/v1/models
|
|
# {"object":"list","data":[{"id":"ggml-gpt4all-j","object":"model"}]}
|
|
|
|
curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
|
|
"model": "ggml-gpt4all-j",
|
|
"messages": [{"role": "user", "content": "How are you?"}],
|
|
"temperature": 0.9
|
|
}'
|
|
|
|
# {"model":"ggml-gpt4all-j","choices":[{"message":{"role":"assistant","content":"I'm doing well, thanks. How about you?"}}]}
|
|
```
|
|
|
|
[https://localai.io](https://localai.io "https://localai.io") |