Documentation

Overview

Broad-Cast.ai provides two main capabilities:

Quickstart

1. 1

   Create an Account

   Sign up at broad-cast.ai/register to get started.

2. 2

   Add Data Sources

   Connect RSS feeds, websites, or upload documents from your Dashboard.

3. 3

   Generate API Key

   Go to Settings → API Keys and create a new key for your application.

4. 4

   Make Your First Request

   Use the vector search API to query your indexed content.

Authentication

All API requests require an API key in the X-API-Key header.

curl https://broad-cast.ai/v1/vector/search \
  -H "X-API-Key: bcast_your_api_key" \
  -H "Content-Type: application/json" \
  -d '{"query": "your search"}'

Vector Search

Search your indexed content using semantic similarity. Returns the most relevant documents based on meaning, not just keywords.

Request Body

{
  "query": "How do I configure authentication?",
  "limit": 10,
  "doc_types": ["topics", "replies"]
}

Response

{
  "results": [
    {
      "id": "doc_12345",
      "content": "To configure authentication, you need to...",
      "doc_type": "topic",
      "connector_uuid": "abc123-def456",
      "distance": 0.234,
      "metadata": {
        "title": "Authentication Guide",
        "author": "JohnDoe",
        "url": "https://example.com/docs/auth"
      }
    }
  ],
  "total": 1,
  "query": "How do I configure authentication?"
}

List Sources

Get a list of your connected data sources with document counts.

Response

{
  "collections": [
    {
      "connector_uuid": "abc123-def456",
      "connector_name": "Tech Blog RSS",
      "topics_count": 1542,
      "replies_count": 0
    }
  ]
}

Error Handling

The API returns standard HTTP status codes and JSON error responses.

Error Response Format

{
  "detail": "Invalid API key"
}

Python Examples

Basic Search

import requests

API_KEY = "bcast_your_api_key"
BASE_URL = "https://broad-cast.ai"

response = requests.post(
    f"{BASE_URL}/v1/vector/search",
    headers={"X-API-Key": API_KEY},
    json={
        "query": "How do I implement user authentication?",
        "limit": 5
    }
)

data = response.json()
for result in data["results"]:
    print(f"Score: {1 - result['distance']:.3f}")
    print(f"Content: {result['content'][:200]}...")
    print("---")

RAG Integration

import requests
import openai

def get_context(query: str, api_key: str) -> str:
    """Retrieve relevant context from Broad-Cast.ai"""
    response = requests.post(
        "https://broad-cast.ai/v1/vector/search",
        headers={"X-API-Key": api_key},
        json={"query": query, "limit": 3}
    )
    results = response.json()["results"]
    return "\n\n".join([r["content"] for r in results])

def answer_question(question: str):
    context = get_context(question, "bcast_your_api_key")

    response = openai.ChatCompletion.create(
        model="gpt-4",
        messages=[
            {"role": "system", "content": f"Answer based on this context:\n{context}"},
            {"role": "user", "content": question}
        ]
    )
    return response.choices[0].message.content

print(answer_question("How do I configure OAuth?"))

Node.js Examples

Basic Search

const API_KEY = "bcast_your_api_key";
const BASE_URL = "https://broad-cast.ai";

async function search(query) {
    const response = await fetch(`${BASE_URL}/v1/vector/search`, {
        method: "POST",
        headers: {
            "X-API-Key": API_KEY,
            "Content-Type": "application/json"
        },
        body: JSON.stringify({ query, limit: 5 })
    });

    const data = await response.json();

    data.results.forEach(result => {
        console.log(`Score: ${(1 - result.distance).toFixed(3)}`);
        console.log(`Content: ${result.content.slice(0, 200)}...`);
        console.log("---");
    });
}

search("How do I implement user authentication?");

Express.js Middleware

const express = require('express');
const app = express();

const API_KEY = process.env.BROADCAST_API_KEY;

async function searchContext(query) {
    const res = await fetch("https://broad-cast.ai/v1/vector/search", {
        method: "POST",
        headers: {
            "X-API-Key": API_KEY,
            "Content-Type": "application/json"
        },
        body: JSON.stringify({ query, limit: 5 })
    });
    return res.json();
}

app.post('/api/chat', async (req, res) => {
    const { question } = req.body;

    // Get relevant context
    const context = await searchContext(question);

    // Use context with your LLM
    // ... your LLM integration here

    res.json({ answer: "..." });
});

app.listen(3000);