breakpilot-compliance/admin-compliance/lib/sdk/drafting-engine/rag-query.ts

/**
 * Shared RAG query utility for the Drafting Engine.
 *
 * Fragt die ai-compliance-sdk (`/sdk/v1/rag/search`, bge-m3) nach Rechtskontext.
 * Frueher: bp-core-rag-service:8097 — der existiert auf prod NICHT (nur macmini/dev),
 * dadurch lieferte die Drafting-Engine dort keinen RAG-Kontext. Die ai-sdk embeddet
 * mit bge-m3 und ist prod-erreichbar. Genutzt von draft-, chat- und vendor-review-Routes.
 */

const SDK_URL =
  process.env.SDK_API_URL || process.env.SDK_URL || 'http://ai-compliance-sdk:8090'
const DEFAULT_USER = '00000000-0000-0000-0000-000000000001'
const DEFAULT_TENANT =
  process.env.DEFAULT_TENANT_ID || '9282a473-5c95-4b3a-bf78-0ecc0ec71d3e'

interface SdkRagResult {
  text?: string
  regulation_code?: string
  regulation_name?: string
  regulation_short?: string
  // Rueckwaerts-kompatibel, falls eine Quelle noch das alte rag-service-Format liefert:
  content?: string
  source_name?: string
  source_code?: string
}

/**
 * Query the RAG corpus for relevant legal documents.
 *
 * @param query - The search query (e.g. "Art. 35 DSGVO Risikobewertung")
 * @param topK - Number of results to return (default: 3)
 * @param collection - Optional RAG collection name (e.g. "bp_dsfa_corpus")
 * @returns Formatted string of legal context, or empty string on error
 */
export async function queryRAG(query: string, topK = 3, collection?: string): Promise<string> {
  try {
    const body: Record<string, unknown> = { query, top_k: topK }
    if (collection) body.collection = collection

    const res = await fetch(`${SDK_URL}/sdk/v1/rag/search`, {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'X-User-ID': DEFAULT_USER,
        'X-Tenant-ID': DEFAULT_TENANT,
      },
      body: JSON.stringify(body),
      signal: AbortSignal.timeout(10000),
    })

    if (!res.ok) return ''

    const data = await res.json()
    const results: SdkRagResult[] = data.results || []
    if (results.length === 0) return ''

    return results
      .map((r, i) => {
        const source =
          r.regulation_short ||
          r.regulation_name ||
          r.regulation_code ||
          r.source_name ||
          r.source_code ||
          'Unbekannt'
        const content = r.text || r.content || ''
        return `[Quelle ${i + 1}: ${source}]\n${content}`
      })
      .join('\n\n---\n\n')
  } catch {
    return ''
  }
}