mirror of
https://github.com/geoffsee/predict-otron-9001.git
synced 2025-09-08 22:46:44 +00:00
8338750beb
Removed `test_request.sh`, deprecated functionality, and unused imports; introduced a new CLI tool (`cli.ts`) for testing inference engine and adjusted handling of non-streaming/streaming chat completions. - Add CPU fallback support for text generation when primary device is unsupported - Introduce `execute_with_fallback` method to handle device compatibility and shape mismatch errors - Extend unit tests to reproduce tensor shape mismatch errors specific to model configurations - Increase HTTP timeout limits in `curl_chat_stream.sh` script for reliable API testing chat completion endpoint functions with gemma3 (no streaming) Add benchmarking guide with HTML reporting, Leptos chat crate, and middleware for metrics tracking
44 lines
1.2 KiB
TypeScript
Executable File
44 lines
1.2 KiB
TypeScript
Executable File
import OpenAI from "openai";
|
|
import {describe, test, expect} from "bun:test";
|
|
|
|
const supportedModels = ["gemma-3-1b-it"];
|
|
|
|
|
|
async function requestLocalOpenAI(model: string, userPrompt: string) {
|
|
const openai = new OpenAI({
|
|
baseURL: "http://localhost:8080/v1",
|
|
apiKey: "not used",
|
|
});
|
|
try {
|
|
return openai.chat.completions.create({
|
|
model: model,
|
|
max_tokens: 100,
|
|
stream: true,
|
|
messages: [
|
|
{name: "assistant_1", role: "system", content: "I am a helpful assistant" },
|
|
{name: "user_1", role: "user", content: userPrompt}
|
|
]
|
|
});
|
|
} catch (e) {
|
|
console.error(e);
|
|
throw e;
|
|
}
|
|
}
|
|
|
|
describe("Local OpenAI Completions", () => {
|
|
test("Should return a valid message", async () => {
|
|
const model = supportedModels.pop();
|
|
const userPrompt = "Who was the 16th president of the United States?";
|
|
const response = await requestLocalOpenAI(model, userPrompt);
|
|
|
|
const chunks = [];
|
|
for await (const chunk of response) {
|
|
console.log('Received chunk:', chunk);
|
|
chunks.push(chunk);
|
|
}
|
|
|
|
expect(chunks.length).toBeGreaterThan(0);
|
|
})
|
|
})
|
|
|