mirror of
https://github.com/mudler/LocalAI.git
synced 2024-12-22 14:02:24 +00:00
f37a4ec9c8
**Description** This PR fixes #1038 Added Streamlit example and also updated readme for examples. **[Signed commits](../CONTRIBUTING.md#signing-off-on-commits-developer-certificate-of-origin)** - [X] Yes, I signed my commits. <!-- Thank you for contributing to LocalAI! Contributing Conventions: 1. Include descriptive PR titles with [<component-name>] prepended. 2. Build and test your changes before submitting a PR. 3. Sign your commits By following the community's contribution conventions upfront, the review process will be accelerated and your PR merged more quickly. -->
1.5 KiB
1.5 KiB
Streamlit bot
This is an example to deploy a Streamlit bot with LocalAI instead of OpenAI. Instructions are for Windows.
# Install & run Git Bash
# Clone LocalAI
git clone https://github.com/go-skynet/LocalAI.git
cd LocalAI
# (optional) Checkout a specific LocalAI tag
# git checkout -b build <TAG>
# 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
# Download model
curl --progress-bar -C - -O https://gpt4all.io/models/ggml-gpt4all-j.bin > models/ggml-gpt4all-j.bin
# Install & Run Docker Desktop for Windows
https://www.docker.com/products/docker-desktop/
# start with docker-compose
docker-compose up -d --pull always
# or you can build the images with:
# 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?"}}]}
cd examples/streamlit-bot
install_requirements.bat
# run the bot
start_windows.bat
# UI will be launched automatically (http://localhost:8501/) in browser.