update JavaScript openai client to demonstrate both Hermes and Qwen with both streaming and non-streaming modes

This commit is contained in:
Russell Ballestrini 2025-10-15 15:51:11 -04:00
parent df3d76738e
commit 8841bacb0b

View file

@ -21,13 +21,44 @@ const hermesResponse = await hermesClient.chat.completions.create({
console.log(`Response: ${hermesResponse.choices[0].message.content}\n`);
// Streaming chat with Qwen
console.log('=== Streaming Chat (Qwen) ===');
// Streaming chat with Hermes
console.log('=== Streaming Chat (Hermes) ===');
const hermesStream = await hermesClient.chat.completions.create({
model: 'adamo1139/Hermes-3-Llama-3.1-8B-FP8-Dynamic',
messages: [
{ role: 'user', content: 'Explain quantum entanglement in one sentence.' }
],
temperature: 0.5,
max_tokens: 150,
stream: true
});
process.stdout.write('Response: ');
for await (const chunk of hermesStream) {
process.stdout.write(chunk.choices[0]?.delta?.content || '');
}
console.log('\n');
// Non-streaming chat with Qwen
console.log('=== Non-Streaming Chat (Qwen) ===');
const qwenClient = new OpenAI({
apiKey: 'dummy-key',
baseURL: 'https://qwen.ai.unturf.com/v1'
});
const qwenResponse = await qwenClient.chat.completions.create({
model: 'hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M',
messages: [
{ role: 'user', content: 'Write a JavaScript function to check if a number is prime' }
],
temperature: 0.5,
max_tokens: 150
});
console.log(`Response: ${qwenResponse.choices[0].message.content}\n`);
// Streaming chat with Qwen
console.log('=== Streaming Chat (Qwen) ===');
const qwenStream = await qwenClient.chat.completions.create({
model: 'hf.co/unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF:Q4_K_M',
messages: [