biblical-guide.com/lib/vector-search.ts

import { Pool } from 'pg'

const pool = new Pool({
  connectionString: process.env.DATABASE_URL,
})

export interface BibleVerse {
  id: string
  ref: string
  book: string
  chapter: number
  verse: number
  text_raw: string
  similarity?: number
  combined_score?: number
}

export async function getEmbedding(text: string): Promise<number[]> {
  const response = await fetch(
    `${process.env.AZURE_OPENAI_ENDPOINT}/openai/deployments/${process.env.AZURE_OPENAI_EMBED_DEPLOYMENT}/embeddings?api-version=${process.env.AZURE_OPENAI_API_VERSION}`,
    {
      method: 'POST',
      headers: {
        'api-key': process.env.AZURE_OPENAI_KEY!,
        'Content-Type': 'application/json',
      },
      body: JSON.stringify({
        input: [text],
      }),
    }
  )

  if (!response.ok) {
    throw new Error(`Embedding API error: ${response.status}`)
  }

  const data = await response.json()
  return data.data[0].embedding
}

export async function searchBibleSemantic(
  query: string,
  limit: number = 10
): Promise<BibleVerse[]> {
  try {
    const queryEmbedding = await getEmbedding(query)

    const client = await pool.connect()
    try {
      const result = await client.query(
        `
        SELECT ref, book, chapter, verse, text_raw,
               1 - (embedding <=> $1) AS similarity
        FROM bible_passages
        WHERE embedding IS NOT NULL
        ORDER BY embedding <=> $1
        LIMIT $2
        `,
        [JSON.stringify(queryEmbedding), limit]
      )

      return result.rows
    } finally {
      client.release()
    }
  } catch (error) {
    console.error('Error in semantic search:', error)
    throw error
  }
}

export async function searchBibleHybrid(
  query: string,
  limit: number = 10
): Promise<BibleVerse[]> {
  try {
    const queryEmbedding = await getEmbedding(query)

    const client = await pool.connect()
    try {
      const result = await client.query(
        `
        WITH vector_search AS (
          SELECT id, 1 - (embedding <=> $1) AS vector_sim
          FROM bible_passages
          WHERE embedding IS NOT NULL
          ORDER BY embedding <=> $1
          LIMIT 100
        ),
        text_search AS (
          SELECT id, ts_rank(tsv, plainto_tsquery('romanian', $3)) AS text_rank
          FROM bible_passages
          WHERE tsv @@ plainto_tsquery('romanian', $3)
        )
        SELECT bp.ref, bp.book, bp.chapter, bp.verse, bp.text_raw,
               COALESCE(vs.vector_sim, 0) * 0.7 + COALESCE(ts.text_rank, 0) * 0.3 AS combined_score
        FROM bible_passages bp
        LEFT JOIN vector_search vs ON vs.id = bp.id
        LEFT JOIN text_search ts ON ts.id = bp.id
        WHERE vs.id IS NOT NULL OR ts.id IS NOT NULL
        ORDER BY combined_score DESC
        LIMIT $2
        `,
        [JSON.stringify(queryEmbedding), limit, query]
      )

      return result.rows
    } finally {
      client.release()
    }
  } catch (error) {
    console.error('Error in hybrid search:', error)
    throw error
  }
}

export async function getContextVerses(
  book: string,
  chapter: number,
  verse: number,
  contextSize: number = 2
): Promise<BibleVerse[]> {
  const client = await pool.connect()
  try {
    const result = await client.query(
      `
      SELECT ref, book, chapter, verse, text_raw
      FROM bible_passages
      WHERE book = $1 AND chapter = $2
      AND verse BETWEEN $3 AND $4
      ORDER BY verse
      `,
      [book, chapter, verse - contextSize, verse + contextSize]
    )

    return result.rows
  } finally {
    client.release()
  }
}