Your First API Call
The Arcee Platform API is OpenAI compatible. It can be accessed through your command line, or, with minor configuration changes, through the OpenAI SDK.
Parameter
Value
api_key
1. Generate an API Key
Create an API key from your Arcee Platform dashboard. This key authenticates all API requests.
2. Choose a Model
Specify the model you want to run inference with. Arcee currently provides the following production models:
trinity-nano-6b
trinity-mini-26b
3. Run the Code Snippet
Use your API key and model name in the sample code below to make your first request.
curl -X POST "https://api.arcee.ai/api/v1/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer <Arcee Platform API Key>" \
-d '{
"model": "<Model Name>",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Greetings!"}
],
"stream": false
}'from openai import OpenAI
client = OpenAI(
api_key="<Arcee Platform API Key>",
base_url="https://api.arcee.ai/api/v1")
response = client.chat.completions.create(
model = "<Model Name>", # Change to whichever Arcee AI model you want to invoke
messages = [
{"role":"system", "content":"You are a helpful assistant"},
{"role":"user", "conent": "Hello"},
],
steam = false
)
print(response.choices[0].message.content)
import OpenAI from "openai";
const openai = new OpenAI({
baseURL: 'https://api.arcee.ai/api/v1',
apiKey: '<Arcee Platform API Key>'
});
async function main() {
const completion = await openai.chat.completions.create({
messages: [{ role: "system", content: "You are a helpful assistant." }],
model: "<Model Name>",
});
console.log(completion.choices[0].message.content);
}
main();Last updated