Fara 7B

from openai import OpenAI

# Initialize the OpenAI client with Qubrid base URL
client = OpenAI(
  base_url="https://platform.qubrid.com/v1",
  api_key="QUBRID_API_KEY",
)

# Create a streaming chat completion
stream = client.chat.completions.create(
  model="microsoft/Fara-7B",
  messages=[
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  max_tokens=4096,
  temperature=0.7,
  top_p=1,
  stream=True
)

# If stream = False comment this out
for chunk in stream:
  if chunk.choices and chunk.choices[0].delta.content:
      print(chunk.choices[0].delta.content, end="", flush=True)
print("\n")

# If stream = True comment this out
print(stream.choices[0].message.content)

import OpenAI from 'openai';

// Initialize the OpenAI client with Qubrid base URL
const client = new OpenAI({
  baseURL: 'https://platform.qubrid.com/v1',
  apiKey: 'QUBRID_API_KEY',
});

// Create a streaming chat completion
const stream = await client.chat.completions.create({
  model: 'microsoft/Fara-7B',
  messages: [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  max_tokens: 4096,
  temperature: 0.7,
  top_p: 1,
  stream: true
});

// If stream = false comment this out
for await (const chunk of stream) {
  if (chunk.choices[0]?.delta?.content) {
    process.stdout.write(chunk.choices[0].delta.content);
  }
}
console.log('\n');

// If stream = true comment this out
console.log(stream.choices[0].message.content);

package main

import (
	"bufio"
	"bytes"
	"encoding/json"
	"fmt"
	"net/http"
)

func main() {
	url := "https://platform.qubrid.com/v1/chat/completions"

	data := map[string]interface{}{
		"model": "microsoft/Fara-7B",
		"messages": []map[string]string{
			{
				"role":    "user",
				"content": "Explain quantum computing in simple terms",
			},
		},
		"temperature": 0.7,
		"max_tokens":  4096,
		"stream":      true,
		"top_p":       1,
	}

	jsonData, _ := json.Marshal(data)
	req, _ := http.NewRequest("POST", url, bytes.NewBuffer(jsonData))
	req.Header.Set("Authorization", "Bearer QUBRID_API_KEY")
	req.Header.Set("Content-Type", "application/json")

	client := &http.Client{}
	res, _ := client.Do(req)
	defer res.Body.Close()

	scanner := bufio.NewScanner(res.Body)
	for scanner.Scan() {
		line := scanner.Text()
		if line != "" {
			fmt.Println(line)
		}
	}
}

curl -X POST "https://platform.qubrid.com/v1/chat/completions" \
  -H "Authorization: Bearer QUBRID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "microsoft/Fara-7B",
  "messages": [
    {
      "role": "user",
      "content": "Explain quantum computing in simple terms"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 4096,
  "stream": true,
  "top_p": 1
}'

Quantum computing uses quantum mechanics to process information differently
from classical computers.

Classical computers use bits — each is a 0 or a 1.
Quantum computers use qubits, which can be 0, 1, or both at once
(called superposition).

This means a quantum computer can explore many solutions at the same time,
rather than checking them one by one — making it exponentially faster
for certain types of problems:

  - Encryption and cybersecurity
  - Simulating molecular structures for drug discovery
  - Optimization in finance and logistics

Another key property: entanglement — two qubits can be linked so that
knowing the state of one instantly tells you something about the other,
enabling highly coordinated computation at scale.

Quantum computers aren't replacing laptops anytime soon.
They're a precision tool for problems that would take classical machines
millions of years to solve.

Example: "You are a helpful product assistant for an e-commerce store.
Only answer questions about products, orders, and returns.
Always respond in a friendly, concise tone."