import { createCompletion, loadModel } from "../src/gpt4all.js";

const model = await loadModel("orca-mini-3b-gguf2-q4_0.gguf", {
    verbose: true, // logs loaded model configuration
    device: "gpu", // defaults to 'cpu'
    nCtx: 2048, // the maximum sessions context window size.
});

// initialize a chat session on the model. a model instance can have only one chat session at a time.
const chat = await model.createChatSession({
    // any completion options set here will be used as default for all completions in this chat session
    temperature: 0.8,
    // a custom systemPrompt can be set here. note that the template depends on the model.
    // if unset, the systemPrompt that comes with the model will be used.
    systemPrompt: "### System:\nYou are an advanced mathematician.\n\n",
});

// create a completion using a string as input
const res1 = await createCompletion(chat, "What is 1   1?");
console.debug(res1.choices[0].message);

// multiple messages can be input to the conversation at once.
// note that if the last message is not of role 'user', an empty message will be returned.
await createCompletion(chat, [
    {
        role: "user",
        content: "What is 2   2?",
    },
    {
        role: "assistant",
        content: "It's 5.",
    },
]);

const res3 = await createCompletion(chat, "Could you recalculate that?");
console.debug(res3.choices[0].message);

model.dispose();

import { createCompletion, loadModel } from "../src/gpt4all.js";

const model = await loadModel("orca-mini-3b-gguf2-q4_0.gguf");

// createCompletion methods can also be used on the model directly.
// context is not maintained between completions.
const res1 = await createCompletion(model, "What is 1   1?");
console.debug(res1.choices[0].message);

// a whole conversation can be input as well.
// note that if the last message is not of role 'user', an error will be thrown.
const res2 = await createCompletion(model, [
    {
        role: "user",
        content: "What is 2   2?",
    },
    {
        role: "assistant",
        content: "It's 5.",
    },
    {
        role: "user",
        content: "Could you recalculate that?",
    },
]);
console.debug(res2.choices[0].message);

import { loadModel, createEmbedding } from '../src/gpt4all.js'

const embedder = await loadModel("nomic-embed-text-v1.5.f16.gguf", { verbose: true, type: 'embedding'})

console.log(createEmbedding(embedder, "Maybe Minecraft was the friends we made along the way"));

import { loadModel, createCompletionStream } from "../src/gpt4all.js";

const model = await loadModel("mistral-7b-openorca.gguf2.Q4_0.gguf", {
    device: "gpu",
});

process.stdout.write("Output: ");
const stream = createCompletionStream(model, "How are you?");
stream.tokens.on("data", (data) => {
    process.stdout.write(data);
});
//wait till stream finishes. We cannot continue until this one is done.
await stream.result;
process.stdout.write("\n");
model.dispose();

import { loadModel, createCompletionGenerator } from "../src/gpt4all.js";

const model = await loadModel("mistral-7b-openorca.gguf2.Q4_0.gguf");

process.stdout.write("Output: ");
const gen = createCompletionGenerator(
    model,
    "Redstone in Minecraft is Turing Complete. Let that sink in. (let it in!)"
);
for await (const chunk of gen) {
    process.stdout.write(chunk);
}

process.stdout.write("\n");
model.dispose();

import { createCompletion, loadModel } from 'gpt4all'

//make sure u downloaded the models before going offline!
const model = await loadModel('mistral-7b-openorca.gguf2.Q4_0.gguf', {
    verbose: true,
    device: 'gpu',
    modelConfigFile: "./models3.json"
});

await createCompletion(model, 'What is 1   1?', { verbose: true })

model.dispose();