Skip to main content
POST
/
ai
/
chat
/
completions
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'http://localhost:3030/api/v1/ai/chat',
  apiKey: process.env.GAIA_API_KEY
});

const response = await client.chat.completions.create({
  chatId: 'chat-123',
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is RAG?' }
  ],
  temperature: 0.7
});

console.log(response.choices[0].message.content);

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "RAG stands for Retrieval-Augmented Generation..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 100,
    "total_tokens": 120
  }
}
Create a chat completion with your configured AI agent. This endpoint is fully compatible with OpenAI’s API, allowing you to use existing OpenAI SDKs and tools.

​
Request Body

​
chatId
string
required
Chat session identifier for conversation continuity
​
messages
array
required
Array of message objects representing the conversation history
​
model
string
default:"gpt-4o"
Model identifier to use for completion
​
provider
string
Provider name (e.g., “openai”, “anthropic”, “ollama”)
​
temperature
number
Sampling temperature between 0 and 2. Higher values make output more random
​
max_tokens
number
Maximum number of tokens to generate
​
stream
boolean
default:"false"
Whether to stream the response

​
Response

​
success
boolean
Indicates if the request was successful
​
id
string
Unique identifier for the completion
​
choices
array
Array of completion choices
​
usage
object
Token usage information
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'http://localhost:3030/api/v1/ai/chat',
  apiKey: process.env.GAIA_API_KEY
});

const response = await client.chat.completions.create({
  chatId: 'chat-123',
  model: 'gpt-4o',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is RAG?' }
  ],
  temperature: 0.7
});

console.log(response.choices[0].message.content);

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "RAG stands for Retrieval-Augmented Generation..."
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 100,
    "total_tokens": 120
  }
}

​
Streaming

Set stream: true to receive Server-Sent Events (SSE) instead of a single response: 
const stream = await client.chat.completions.create({
  chatId: 'chat-123',
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Hello!' }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

​
Notes

  • Your agent will automatically use configured knowledge bases, tools, and MCP servers
  • The chatId maintains conversation context and history
  • Compatible with all OpenAI client libraries and tools