Recommended deployment is with Vercel. But you can deploy it anywhere you want.
You can also deploy it with Netlify.
[!NOTE] This project is an experimental one. While it has been optimized, caution is still advised, and any consequences of use are at your own risk!
Just deploy the project and you are ready to go.
for OpenAI just change the baseURL
from https://api.openai.com/v1
to YOUR_DEPLOYED_URL/v1
for example if you deployed the project to https://stake-vlad-dracula.vercel.app
then change the baseURL
to https://stake-vlad-dracula.vercel.app/v1
.
import OpenAI from 'openai';
const openai = new OpenAI({
apiKey: 'YOUR_API_KEY sk-XXXXXX-XXXXXX-XXXXXX-XXXXXX',
// change the baseURL to your deployed URL, for example: https://stake-vlad-dracula.vercel.app/v1
+ baseURL: 'https://stake-vlad-dracula.vercel.app/v1',
});
for Gemini change https://generativelanguage.googleapis.com/v1beta
to YOUR_DEPLOYED_URL/v1beta
export API_KEY="YOUR_API_KEY"
- export BASE_URL="https://generativelanguage.googleapis.com/v1beta"
+ export BASE_URL="YOUR_DEPLOYED_URL/v1beta"
curl https://${BASE_URL}/models/gemini-pro:generateContent?key=${API_KEY} \
-H 'Content-Type: application/json' \
-X POST \
-d '{
"contents": [{
"parts":[{
"text": "Write a story about a magic backpack."}]}]}' 2> /dev/null
for Groq change https://api.groq.com/openai/v1
to YOUR_DEPLOYED_URL/openai/v1
export API_KEY="YOUR_API_KEY"
- export BASE_URL="https://api.groq.com/openai/v1"
+ export BASE_URL="YOUR_DEPLOYED_URL/openai/v1"
curl https://${BASE_URL}/chat/completions \
-H "Authorization: Bearer $GROQ_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d '{"messages": [{"role": "user", "content": "Explain the importance of low latency LLMs"}], "model": "mixtral-8x7b-32768"}'
If you found this Implementation helpful or used it in your Projects, do give it a star. Thanks! 🌟
[!TIP] You can use GitHub Action to keep the forked repository up to date with the original repository. For more information, see Syncing a fork.