1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
const axios = require('axios');
const fs = require('fs');
const path = require('path');
// helper function to help you convert your local images into base64 format
async function toB64(imgPath) {
const data = fs.readFileSync(path.resolve(imgPath));
return Buffer.from(data).toString('base64');
}
const api_key = "YOUR API-KEY";
const url = "https://api.segmind.com/v1/gpt-4o";
const data = {
"messages": [
{
"role": "user",
"content" : "tell me a joke on cats"
},
{
"role": "assistant",
"content" : "here is a joke about cats..."
},
{
"role": "user",
"content" : "now a joke on dogs"
},
]
};
(async function() {
try {
const response = await axios.post(url, data, { headers: { 'x-api-key': api_key } });
console.log(response.data);
} catch (error) {
console.error('Error:', error.response.data);
}
})();Attributes
An array of objects containing the role and content
Could be "user", "assistant" or "system".
A string containing the user's query or the assistant's response.
To keep track of your credit usage, you can inspect the response headers of each API call. The x-remaining-credits property will indicate the number of remaining credits in your account. Ensure you monitor this value to avoid any disruptions in your API usage.
GPT-4o
GPT-4o is the next iteration of GPT-4 language model. While inheriting the core transformer-based encoder-decoder architecture, GPT-4o prioritizes improved processing efficiency. This translates to faster inference speeds and potentially lower computational requirements compared to its predecessor.
GPT-4o uses a transformer architecture. This architecture processes linguistic structures. GPT-4o generates text similar to human writing, useful for tasks such as content creation. The attention mechanism in GPT-4o helps the model understand the relevance of data. This leads to responses that contain necessary information, improving user interaction.
Popular Models
