@aid-on/unillm

Features

Installation

npm install @aid-on/unillm

yarn add @aid-on/unillm

pnpm add @aid-on/unillm

Quick Start

import { unillm } from "@aid-on/unillm";
// Fluent API with type safety
const response = await unillm()
 .model("openai:gpt-4o-mini")
 .credentials({ openaiApiKey: process.env.OPENAI_API_KEY })
 .temperature(0.7)
 .generate("Explain quantum computing in simple terms");
console.log(response.text);

Streaming with nagare

import { unillm } from "@aid-on/unillm";
import type { Stream } from "@aid-on/nagare";
const stream: Stream<string> = await unillm()
 .model("groq:llama-3.3-70b-versatile")
 .credentials({ groqApiKey: "..." })
 .stream("Write a story about AI");
// Use nagare's reactive operators
const enhanced = stream
 .map(chunk => chunk.trim())
 .filter(chunk => chunk.length > 0)
 .throttle(16) // ~60fps for UI updates
 .tap(chunk => console.log(chunk))
 .toSSE(); // Convert to Server-Sent Events

Structured Output

import { z } from "zod";
const PersonSchema = z.object({
 name: z.string(),
 age: z.number(),
 skills: z.array(z.string())
});
const result = await unillm()
 .model("groq:llama-3.1-8b-instant")
 .credentials({ groqApiKey: "..." })
 .schema(PersonSchema)
 .generate("Generate a software engineer profile");
// Type-safe access
console.log(result.object.name); // string
console.log(result.object.skills); // string[]

Provider Shortcuts

import { anthropic, openai, groq, gemini, cloudflare } from "@aid-on/unillm";
// One-liners for quick prototyping
await anthropic.sonnet("sk-ant-...").generate("Hello");
await openai.mini("sk-...").generate("Hello");
await groq.instant("gsk_...").generate("Hello");
await gemini.flash("AIza...").generate("Hello");
await cloudflare.llama({ accountId: "...", apiToken: "..." }).generate("Hello");

Supported Models (48 Models)

Anthropic (8 models) - v0.4.0

OpenAI (9 models)

Groq (7 models)

Google Gemini (8 models)

Cloudflare Workers AI (13 models)

Advanced Usage

Fluent Builder Pattern

const builder = unillm()
 .model("groq:llama-3.3-70b-versatile")
 .credentials({ groqApiKey: "..." })
 .temperature(0.7)
 .maxTokens(1000)
 .topP(0.9)
 .system("You are a helpful assistant")
 .messages([
 { role: "user", content: "Previous question..." },
 { role: "assistant", content: "Previous answer..." }
 ]);
// Reusable configuration
const response1 = await builder.generate("New question");
const response2 = await builder.stream("Another question");

Memory Optimization

import { createMemoryOptimizedStream } from "@aid-on/unillm";
const stream = await createMemoryOptimizedStream(
 largeResponse,
 { 
 maxMemory: 1024 * 1024, // 1MB limit
 chunkSize: 512 // Optimal chunk size
 }
);

Error Handling

import { UnillmError, RateLimitError } from "@aid-on/unillm";
try {
 const response = await unillm()
 .model("groq:llama-3.3-70b-versatile")
 .credentials({ groqApiKey: "..." })
 .generate("Hello");
} catch (error) {
 if (error instanceof RateLimitError) {
 console.log(`Rate limited. Retry after ${error.retryAfter}ms`);
 } else if (error instanceof UnillmError) {
 console.log(`LLM error: ${error.message}`);
 }
}

Integration Examples

With React

import { useState } from "react";
import { unillm } from "@aid-on/unillm";
export default function ChatComponent() {
 const [response, setResponse] = useState("");
 const [loading, setLoading] = useState(false);
 
 const handleGenerate = async () => {
 setLoading(true);
 const stream = await unillm()
 .model("groq:llama-3.1-8b-instant")
 .credentials({ groqApiKey: import.meta.env.VITE_GROQ_API_KEY })
 .stream("Write a haiku");
 
 for await (const chunk of stream) {
 setResponse(prev => prev + chunk);
 }
 setLoading(false);
 };
 
 return (
 <div>
 <button onClick={handleGenerate} disabled={loading}>
 {loading ? "Generating..." : "Generate"}
 </button>
 <p>{response}</p>
 </div>
 );
}

With Cloudflare Workers

export default {
 async fetch(request: Request, env: Env) {
 const stream = await unillm()
 .model("cloudflare:@cf/meta/llama-3.1-8b-instruct")
 .credentials({
 accountId: env.CF_ACCOUNT_ID,
 apiToken: env.CF_API_TOKEN
 })
 .stream("Hello from the edge!");
 
 return new Response(stream.toReadableStream(), {
 headers: { "Content-Type": "text/event-stream" }
 });
 }
};

API Reference

unillm() Builder Methods

License