Quick Start Tutorial

1. Start the Server

cd Beep.AI.Server/Beep.AI.Server
python run.py

The server starts at http://localhost:5000. On first run, complete the Setup Wizard to initialize the database and create an admin account.

2. Install an LLM Model

Navigate to LLM in the admin panel and download a model, or use the API:

curl -X POST http://localhost:5000/api/v1/llm/models/download \
  -H "Content-Type: application/json" \
  -d '{"model_id": "microsoft/phi-2"}'

3. Make Your First Chat Request

curl -X POST http://localhost:5000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -d '{
    "model": "phi-2",
    "messages": [
      {"role": "user", "content": "Hello! What can you do?"}
    ]
  }'

4. Try RAG (Retrieval-Augmented Generation)

Create a RAG Collection

curl -X POST http://localhost:5000/v1/rag/collections \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -d '{
    "name": "my-docs",
    "provider": "faiss",
    "embedding_model": "all-MiniLM-L6-v2"
  }'

Query the Collection

curl -X POST http://localhost:5000/v1/rag/query \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_TOKEN" \
  -d '{
    "collection_id": "my-docs",
    "query": "What is retrieval augmented generation?",
    "top_k": 5
  }'

5. Use a Client SDK

Python

from beep_ai_sdk import BeepClient

client = BeepClient(base_url="http://localhost:5000", api_key="YOUR_API_TOKEN")
response = client.chat.completions.create(
    model="phi-2",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

JavaScript

import { BeepClient } from '@beep-ai/sdk';

const client = new BeepClient({
    baseURL: 'http://localhost:5000',
    apiKey: 'YOUR_API_TOKEN'
});

const response = await client.chat.completions.create({
    model: 'phi-2',
    messages: [{ role: 'user', content: 'Hello!' }]
});
console.log(response.choices[0].message.content);