Knowledge Base → Brand Voice

import os, requests, time

NOTION = os.environ["NOTION_API_KEY"]
MV = os.environ["MAVERA_API_KEY"]
NB = "https://api.notion.com/v1"
MB = "https://app.mavera.io/api/v1"
NH = {
    "Authorization": f"Bearer {NOTION}",
    "Notion-Version": "2022-06-28",
    "Content-Type": "application/json",
}
MH = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}

KB_DB_ID = "your-knowledge-base-database-id"
CATEGORIES = ["Product Docs", "Blog Drafts", "Style Guide", "Internal Comms"]

# 1. Query knowledge base pages
all_pages = []
for category in CATEGORIES:
    r = requests.post(f"{NB}/databases/{KB_DB_ID}/query", headers=NH, json={
        "filter": {"property": "Category", "select": {"equals": category}},
        "sorts": [{"property": "Last edited time", "direction": "descending"}],
        "page_size": 10,
    })
    if r.status_code == 429:
        time.sleep(1)
        r = requests.post(f"{NB}/databases/{KB_DB_ID}/query", headers=NH, json={
            "filter": {"property": "Category", "select": {"equals": category}},
            "page_size": 10,
        })
    data = r.json()
    all_pages.extend(data.get("results", []))
    time.sleep(0.4)

print(f"Found {len(all_pages)} knowledge base pages across {len(CATEGORIES)} categories")

# 2. Extract text from pages
def get_blocks_text(block_id):
    texts = []
    cursor = None
    while True:
        params = {"page_size": 100}
        if cursor:
            params["start_cursor"] = cursor
        r = requests.get(f"{NB}/blocks/{block_id}/children", headers=NH, params=params)
        if r.status_code == 429:
            time.sleep(1); continue
        r.raise_for_status()
        data = r.json()
        for block in data.get("results", []):
            btype = block.get("type", "")
            rt = block.get(btype, {}).get("rich_text", [])
            text = "".join(t.get("plain_text", "") for t in rt)
            if text.strip():
                texts.append(text)
        cursor = data.get("next_cursor")
        if not cursor:
            break
        time.sleep(0.4)
    return "\n".join(texts)

samples = []
for page in all_pages[:25]:
    props = page.get("properties", {})
    title_parts = props.get("Name", props.get("Title", {})).get("title", [])
    title = "".join(t.get("plain_text", "") for t in title_parts)
    text = get_blocks_text(page["id"])
    if len(text) > 100:
        samples.append(f"=== {title} ===\n{text[:1500]}")

combined = "\n\n---\n\n".join(samples)
print(f"Collected {len(samples)} pages ({len(combined)} chars)")

# 3. Create Brand Voice
bv = requests.post(f"{MB}/brand-voices", headers=MH, json={
    "name": "Notion Knowledge Base Voice",
    "samples": [combined[:50000]],
    "description": (
        f"Extracted from {len(samples)} internal knowledge base pages "
        f"across categories: {', '.join(CATEGORIES)}. "
        "Captures organizational writing patterns, technical vocabulary, and tone."
    ),
}).json()

print(f"Brand Voice: {bv.get('id', 'error')}")

# 4. Wait and inspect
time.sleep(5)
detail = requests.get(f"{MB}/brand-voices/{bv['id']}", headers=MH).json()
print(f"Status: {detail.get('status', 'unknown')}")
if detail.get("traits"):
    print(f"Traits: {detail['traits']}")

# 5. Test with a generation
from openai import OpenAI
mavera = OpenAI(api_key=MV, base_url=MB)
test = mavera.responses.create(
    model="mavera-1",
    input=[{"role": "user", "content": "Write a 100-word product update announcement for a new API versioning feature."}],
    extra_body={"brand_voice_id": bv["id"]},
)
print(f"\nTest generation:\n{test.output[0].content[0].text}")

const OpenAI = require("openai").default;
const NOTION = process.env.NOTION_API_KEY;
const MV = process.env.MAVERA_API_KEY;
const NB = "https://api.notion.com/v1";
const MB = "https://app.mavera.io/api/v1";
const NH = {
  Authorization: `Bearer ${NOTION}`,
  "Notion-Version": "2022-06-28",
  "Content-Type": "application/json",
};
const MH = { Authorization: `Bearer ${MV}`, "Content-Type": "application/json" };

const KB_DB_ID = "your-knowledge-base-database-id";
const CATEGORIES = ["Product Docs", "Blog Drafts", "Style Guide", "Internal Comms"];

// 1. Query pages per category
const allPages = [];
for (const category of CATEGORIES) {
  const res = await fetch(`${NB}/databases/${KB_DB_ID}/query`, {
    method: "POST", headers: NH,
    body: JSON.stringify({
      filter: { property: "Category", select: { equals: category } },
      sorts: [{ property: "Last edited time", direction: "descending" }],
      page_size: 10,
    }),
  });
  if (res.status === 429) await new Promise(r => setTimeout(r, 1000));
  const data = await (res.status === 429
    ? fetch(`${NB}/databases/${KB_DB_ID}/query`, { method: "POST", headers: NH,
        body: JSON.stringify({ filter: { property: "Category", select: { equals: category } }, page_size: 10 }),
      })
    : Promise.resolve(res)).then(r => r.json());
  allPages.push(...(data.results || []));
  await new Promise(r => setTimeout(r, 400));
}

console.log(`Found ${allPages.length} pages across ${CATEGORIES.length} categories`);

// 2. Extract text
async function getBlocksText(blockId) {
  const texts = [];
  let cursor = null;
  do {
    const params = new URLSearchParams({ page_size: "100" });
    if (cursor) params.set("start_cursor", cursor);
    const res = await fetch(`${NB}/blocks/${blockId}/children?${params}`, { headers: NH });
    if (res.status === 429) { await new Promise(r => setTimeout(r, 1000)); continue; }
    const data = await res.json();
    for (const block of data.results || []) {
      const text = (block[block.type]?.rich_text || []).map(t => t.plain_text).join("");
      if (text.trim()) texts.push(text);
    }
    cursor = data.next_cursor;
    await new Promise(r => setTimeout(r, 400));
  } while (cursor);
  return texts.join("\n");
}

const samples = [];
for (const page of allPages.slice(0, 25)) {
  const props = page.properties || {};
  const titleProp = props.Name || props.Title || {};
  const title = (titleProp.title || []).map(t => t.plain_text).join("");
  const text = await getBlocksText(page.id);
  if (text.length > 100) samples.push(`=== ${title} ===\n${text.slice(0, 1500)}`);
}

const combined = samples.join("\n\n---\n\n");
console.log(`Collected ${samples.length} pages (${combined.length} chars)`);

// 3. Brand Voice
const bv = await fetch(`${MB}/brand-voices`, { method: "POST", headers: MH,
  body: JSON.stringify({
    name: "Notion Knowledge Base Voice",
    samples: [combined.slice(0, 50000)],
    description: `From ${samples.length} pages across: ${CATEGORIES.join(", ")}.`,
  }),
}).then(r => r.json());
console.log(`Brand Voice: ${bv.id}`);

// 4. Test
await new Promise(r => setTimeout(r, 5000));
const mavera = new OpenAI({ apiKey: MV, baseURL: MB });
const test = await mavera.responses.create({
  model: "mavera-1",
  input: [{ role: "user", content: "Write a 100-word product update for a new API versioning feature." }],
  extra_body: { brand_voice_id: bv.id },
});
console.log(`\nTest:\n${test.output[0].content[0].text}`);