# 1. Create the index with FIXED dimensions and metric
bunx wrangler vectorize create my-index \
  --dimensions=768 \
  --metric=cosine

# 2. Create metadata indexes IMMEDIATELY (before inserting vectors!)
bunx wrangler vectorize create-metadata-index my-index \
  --property-name=category \
  --type=string

bunx wrangler vectorize create-metadata-index my-index \
  --property-name=timestamp \
  --type=number

# Dimensions MUST match your embedding model output:
# - Workers AI @cf/baai/bge-base-en-v1.5: 768 dimensions
# - OpenAI text-embedding-3-small: 1536 dimensions
# - OpenAI text-embedding-3-large: 3072 dimensions

# Metrics determine similarity calculation:
# - cosine: Best for normalized embeddings (most common)
# - euclidean: Absolute distance between vectors
# - dot-product: For non-normalized vectors

{
  "name": "my-vectorize-worker",
  "main": "src/index.ts",
  "compatibility_date": "2025-10-21",
  "vectorize": [
    {
      "binding": "VECTORIZE_INDEX",
      "index_name": "my-index"
    }
  ],
  "ai": {
    "binding": "AI"
  }
}

export interface Env {
  VECTORIZE_INDEX: VectorizeIndex;
  AI: Ai;
}

interface VectorizeVector {
  id: string;
  values: number[] | Float32Array | Float64Array;
  namespace?: string;
  metadata?: Record<string, string | number | boolean | string[]>;
}

interface VectorizeMatches {
  matches: Array<{
    id: string;
    score: number;
    values?: number[];
    metadata?: Record<string, any>;
    namespace?: string;
  }>;
  count: number;
}

export default {
  async fetch(request: Request, env: Env): Promise<Response> {
    const { question } = await request.json();

    // 1. Generate embedding for user question
    const questionEmbedding = await env.AI.run('@cf/baai/bge-base-en-v1.5', {
      text: question
    });

    // 2. Search vector database for similar content
    const results = await env.VECTORIZE_INDEX.query(
      questionEmbedding.data[0],
      {
        topK: 3,
        returnMetadata: 'all',
        filter: { type: "documentation" }
      }
    );

    // 3. Build context from retrieved documents
    const context = results.matches
      .map(m => m.metadata.content)
      .join('\n\n---\n\n');

    // 4. Generate answer with LLM using context
    const answer = await env.AI.run('@cf/meta/llama-3-8b-instruct', {
      messages: [
        {
          role: "system",
          content: `Answer based on this context:\n\n${context}`
        },
        {
          role: "user",
          content: question
        }
      ]
    });

    return Response.json({
      answer: answer.response,
      sources: results.matches.map(m => m.metadata.title)
    });
  }
};

Problem: Filtering doesn't work on existing vectors
Solution: Delete and re-insert vectors OR create metadata indexes BEFORE inserting

Problem: "Vector dimensions do not match index configuration"
Solution: Ensure embedding model output matches index dimensions:
  - Workers AI bge-base: 768
  - OpenAI small: 1536
  - OpenAI large: 3072

Problem: "Invalid metadata key"
Solution: Keys cannot:
  - Be empty
  - Contain . (dot)
  - Contain " (quote)
  - Start with $ (dollar sign)

Problem: "Filter exceeds 2048 bytes"
Solution: Simplify filter or split into multiple queries

Problem: Slow queries or reduced accuracy
Solution: Use lower cardinality fields for range queries, or use seconds instead of milliseconds for timestamps

Problem: Updates not reflecting in index
Solution: Use upsert() to overwrite existing vectors, not insert()

Problem: "VECTORIZE_INDEX is not defined"
Solution: Add [[vectorize]] binding to wrangler.jsonc

Problem: Unclear when to use namespace vs metadata filtering
Solution:
  - Namespace: Partition key, applied BEFORE metadata filters
  - Metadata: Flexible key-value filtering within namespace

# Create index (dimensions/metric are PERMANENT)
bunx wrangler vectorize create <name> --dimensions=768 --metric=cosine

# Create metadata index (MUST be before inserting vectors!)
bunx wrangler vectorize create-metadata-index <name> --property-name=category --type=string

# Get index info
bunx wrangler vectorize info <name>