Embeddings → Knowledge Base Gap Filling

import os, requests, time, math
from openai import OpenAI

client = OpenAI(api_key=os.environ["OPENAI_API_KEY"])
MV = os.environ["MAVERA_API_KEY"]
MV_BASE = "https://app.mavera.io/api/v1"
MV_H = {"Authorization": f"Bearer {MV}", "Content-Type": "application/json"}

CONTENT_LIBRARY = [
    {"title": "Getting Started with Marketing Automation",
     "text": "Marketing automation platforms help teams scale personalized outreach..."},
    {"title": "Email Segmentation Best Practices",
     "text": "Segmenting your email list by behavior and demographics drives higher open rates..."},
    {"title": "A/B Testing Your Landing Pages",
     "text": "Statistical significance matters. Run tests for at least two weeks..."},
    {"title": "How Acme Corp Increased Pipeline 340%",
     "text": "Acme Corp migrated from manual outreach to automated sequences..."},
    {"title": "API Authentication Guide",
     "text": "All API requests require a Bearer token in the Authorization header..."},
]

TARGET_TOPICS = [
    "social media advertising strategy", "content marketing ROI measurement",
    "customer retention and churn prevention", "SEO keyword research methodology",
    "video marketing for B2B", "marketing attribution modeling",
]

def cosine_sim(a, b):
    dot = sum(x * y for x, y in zip(a, b))
    na = math.sqrt(sum(x * x for x in a))
    nb = math.sqrt(sum(x * x for x in b))
    return dot / (na * nb) if na and nb else 0.0

# 1. Embed existing content
lib_texts = [f"{c['title']}: {c['text'][:500]}" for c in CONTENT_LIBRARY]
lib_resp = client.embeddings.create(model="text-embedding-3-large", input=lib_texts)
lib_vectors = [item.embedding for item in lib_resp.data]
print(f"Embedded {len(lib_vectors)} documents (dim={len(lib_vectors[0])})")

time.sleep(1)

# 2. Embed target topics and find gaps
topic_resp = client.embeddings.create(model="text-embedding-3-large", input=TARGET_TOPICS)
topic_vectors = [item.embedding for item in topic_resp.data]

gaps = []
for i, topic in enumerate(TARGET_TOPICS):
    max_sim = max(cosine_sim(topic_vectors[i], lv) for lv in lib_vectors)
    closest_idx = max(range(len(lib_vectors)),
                      key=lambda j: cosine_sim(topic_vectors[i], lib_vectors[j]))
    gaps.append({"topic": topic, "max_similarity": max_sim,
                 "closest": CONTENT_LIBRARY[closest_idx]["title"]})
    print(f"  {topic:42s} → sim {max_sim:.3f} (nearest: {CONTENT_LIBRARY[closest_idx]['title'][:30]})")

gaps.sort(key=lambda g: g["max_similarity"])
threshold = 0.35
content_gaps = [g for g in gaps if g["max_similarity"] < threshold]
print(f"\nContent gaps (sim < {threshold}): {len(content_gaps)} topics")

time.sleep(1)

# 3. Generate content for top gaps via Mavera
for gap in content_gaps[:3]:
    gen = requests.post(f"{MV_BASE}/generations", headers=MV_H, json={
        "prompt": f"Write a 200-word blog post outline about: {gap['topic']}. "
            f"Our closest content is '{gap['closest']}' (similarity: {gap['max_similarity']:.2f}). "
            "Cover angles our library doesn't address. Include: headings, key points, data, CTA.",
    }).json()
    text = gen.get("output") or gen.get("content") or ""
    print(f"\n{'='*60}\nGAP FILL: {gap['topic']}\n{'='*60}")
    print(text[:1500])
    time.sleep(2)

import OpenAI from "openai";

const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });
const MV = process.env.MAVERA_API_KEY;
const MV_BASE = "https://app.mavera.io/api/v1";
const MV_H = { Authorization: `Bearer ${MV}`, "Content-Type": "application/json" };

const LIBRARY = [
  { title: "Getting Started with Marketing Automation", text: "Marketing automation platforms..." },
  { title: "Email Segmentation Best Practices", text: "Segmenting your email list..." },
  { title: "A/B Testing Your Landing Pages", text: "Statistical significance matters..." },
  { title: "How Acme Corp Increased Pipeline 340%", text: "Acme Corp migrated from manual..." },
  { title: "API Authentication Guide", text: "All API requests require a Bearer token..." },
];
const TOPICS = [
  "social media advertising strategy", "content marketing ROI measurement",
  "customer retention and churn prevention", "video marketing for B2B",
];

function cosineSim(a, b) {
  let dot = 0, na = 0, nb = 0;
  for (let i = 0; i < a.length; i++) { dot += a[i] * b[i]; na += a[i] ** 2; nb += b[i] ** 2; }
  return na && nb ? dot / (Math.sqrt(na) * Math.sqrt(nb)) : 0;
}

const libResp = await client.embeddings.create({
  model: "text-embedding-3-large", input: LIBRARY.map(c => `${c.title}: ${c.text}`),
});
const libVecs = libResp.data.map(d => d.embedding);
await new Promise(r => setTimeout(r, 1000));

const topicVecs = (await client.embeddings.create({
  model: "text-embedding-3-large", input: TOPICS,
})).data.map(d => d.embedding);

const gaps = TOPICS.map((topic, i) => {
  const sims = libVecs.map(lv => cosineSim(topicVecs[i], lv));
  const maxSim = Math.max(...sims);
  return { topic, maxSimilarity: maxSim, closest: LIBRARY[sims.indexOf(maxSim)].title };
}).sort((a, b) => a.maxSimilarity - b.maxSimilarity).filter(g => g.maxSimilarity < 0.35);

for (const gap of gaps.slice(0, 3)) {
  const gen = await fetch(`${MV_BASE}/generations`, { method: "POST", headers: MV_H,
    body: JSON.stringify({
      prompt: `Write a 200-word blog outline about: ${gap.topic}. Nearest: '${gap.closest}'. Cover new angles.`,
    }),
  }).then(r => r.json());
  console.log(`GAP FILL: ${gap.topic}\n${(gen.output || gen.content || "").slice(0, 1500)}`);
  await new Promise(r => setTimeout(r, 2000));
}