All checks were successful
CI / go-lint (push) Has been skipped
CI / python-lint (push) Has been skipped
CI / nodejs-lint (push) Has been skipped
CI / test-go-ai-compliance (push) Successful in 35s
CI / test-python-backend-compliance (push) Successful in 31s
CI / test-python-document-crawler (push) Successful in 22s
CI / test-python-dsms-gateway (push) Successful in 18s
Compliance Advisor, Drafting Agent und Validator haben nicht geantwortet weil qwen3.5 standardmaessig im Thinking-Mode laeuft (interne Chain-of- Thought > 2min Timeout). Keiner der Agenten benoetigt Thinking-Mode — alle Aufgaben sind Chat/Textgenerierung/JSON-Validierung ohne tiefes Reasoning. think:false sorgt fuer direkte schnelle Antworten. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
249 lines
7.9 KiB
TypeScript
249 lines
7.9 KiB
TypeScript
/**
|
|
* Compliance Advisor Chat API
|
|
*
|
|
* Connects the ComplianceAdvisorWidget to:
|
|
* 1. Multi-Collection RAG search (rag-service) for context across 6 collections
|
|
* 2. Ollama LLM (32B) for generating answers
|
|
*
|
|
* Supports country-specific filtering (DE, AT, CH, EU).
|
|
* Streams the LLM response back as plain text.
|
|
*/
|
|
|
|
import { NextRequest, NextResponse } from 'next/server'
|
|
import { readSoulFile } from '@/lib/sdk/agents/soul-reader'
|
|
|
|
const RAG_SERVICE_URL = process.env.RAG_SERVICE_URL || 'http://rag-service:8097'
|
|
const OLLAMA_URL = process.env.OLLAMA_URL || 'http://host.docker.internal:11434'
|
|
const LLM_MODEL = process.env.COMPLIANCE_LLM_MODEL || 'qwen2.5vl:32b'
|
|
|
|
// All compliance-relevant collections (without NiBiS)
|
|
const COMPLIANCE_COLLECTIONS = [
|
|
'bp_compliance_gesetze',
|
|
'bp_compliance_ce',
|
|
'bp_compliance_datenschutz',
|
|
'bp_dsfa_corpus',
|
|
'bp_compliance_recht',
|
|
'bp_legal_templates',
|
|
] as const
|
|
|
|
type Country = 'DE' | 'AT' | 'CH' | 'EU'
|
|
|
|
// Fallback SOUL prompt (used when .soul.md file is unavailable)
|
|
const FALLBACK_SYSTEM_PROMPT = `# Compliance Advisor Agent
|
|
|
|
## Identitaet
|
|
Du bist der BreakPilot Compliance-Berater. Du hilfst Nutzern des AI Compliance SDK,
|
|
Datenschutz- und Compliance-Fragen in verstaendlicher Sprache zu beantworten.
|
|
|
|
## Kernprinzipien
|
|
- Quellenbasiert: Verweise auf DSGVO-Artikel, BDSG-Paragraphen
|
|
- Verstaendlich: Einfache, praxisnahe Sprache
|
|
- Ehrlich: Bei Unsicherheit empfehle Rechtsberatung
|
|
- Deutsch als Hauptsprache`
|
|
|
|
const COUNTRY_LABELS: Record<Country, string> = {
|
|
DE: 'Deutschland',
|
|
AT: 'Oesterreich',
|
|
CH: 'Schweiz',
|
|
EU: 'EU-weit',
|
|
}
|
|
|
|
interface RAGSearchResult {
|
|
content: string
|
|
source_name?: string
|
|
source_code?: string
|
|
attribution_text?: string
|
|
score: number
|
|
collection?: string
|
|
metadata?: Record<string, unknown>
|
|
}
|
|
|
|
/**
|
|
* Query multiple RAG collections in parallel, with optional country filter
|
|
*/
|
|
async function queryMultiCollectionRAG(query: string, country?: Country): Promise<string> {
|
|
try {
|
|
const searchPromises = COMPLIANCE_COLLECTIONS.map(async (collection) => {
|
|
const searchBody: Record<string, unknown> = {
|
|
query,
|
|
collection,
|
|
top_k: 3,
|
|
}
|
|
|
|
// Apply country filter for gesetze collection
|
|
if (collection === 'bp_compliance_gesetze' && country && country !== 'EU') {
|
|
searchBody.metadata_filter = {
|
|
must: [
|
|
{
|
|
key: 'country',
|
|
match: { any: [country, 'EU'] },
|
|
},
|
|
],
|
|
}
|
|
}
|
|
|
|
const res = await fetch(`${RAG_SERVICE_URL}/api/v1/search`, {
|
|
method: 'POST',
|
|
headers: { 'Content-Type': 'application/json' },
|
|
body: JSON.stringify(searchBody),
|
|
signal: AbortSignal.timeout(10000),
|
|
})
|
|
|
|
if (!res.ok) return []
|
|
|
|
const data = await res.json()
|
|
return (data.results || []).map((r: RAGSearchResult) => ({
|
|
...r,
|
|
collection,
|
|
}))
|
|
})
|
|
|
|
const settled = await Promise.allSettled(searchPromises)
|
|
const allResults: RAGSearchResult[] = []
|
|
|
|
for (const result of settled) {
|
|
if (result.status === 'fulfilled') {
|
|
allResults.push(...result.value)
|
|
}
|
|
}
|
|
|
|
// Sort by score descending, take top 8
|
|
allResults.sort((a, b) => b.score - a.score)
|
|
const topResults = allResults.slice(0, 8)
|
|
|
|
if (topResults.length === 0) return ''
|
|
|
|
return topResults
|
|
.map((r, i) => {
|
|
const source = r.source_name || r.source_code || 'Unbekannt'
|
|
return `[Quelle ${i + 1}: ${source}]\n${r.content || ''}`
|
|
})
|
|
.join('\n\n---\n\n')
|
|
} catch (error) {
|
|
console.warn('Multi-collection RAG query error (continuing without context):', error)
|
|
return ''
|
|
}
|
|
}
|
|
|
|
export async function POST(request: NextRequest) {
|
|
try {
|
|
const body = await request.json()
|
|
const { message, history = [], currentStep = 'default', country } = body
|
|
|
|
if (!message || typeof message !== 'string') {
|
|
return NextResponse.json({ error: 'Message is required' }, { status: 400 })
|
|
}
|
|
|
|
// Validate country parameter
|
|
const validCountry = ['DE', 'AT', 'CH', 'EU'].includes(country) ? (country as Country) : undefined
|
|
|
|
// 1. Query RAG across all collections
|
|
const ragContext = await queryMultiCollectionRAG(message, validCountry)
|
|
|
|
// 2. Build system prompt with RAG context + country
|
|
const soulPrompt = await readSoulFile('compliance-advisor')
|
|
let systemContent = soulPrompt || FALLBACK_SYSTEM_PROMPT
|
|
|
|
if (validCountry) {
|
|
const countryLabel = COUNTRY_LABELS[validCountry]
|
|
systemContent += `\n\n## Laenderspezifische Auskunft
|
|
Der Nutzer hat "${countryLabel} (${validCountry})" gewaehlt.
|
|
- Beziehe dich AUSSCHLIESSLICH auf ${validCountry}-Recht + anwendbares EU-Recht
|
|
- Nenne IMMER explizit das Land in deiner Antwort
|
|
- Verwende NIEMALS Gesetze eines anderen Landes
|
|
- Bei ${validCountry === 'EU' ? 'EU-weiten Fragen: Beziehe dich auf EU-Verordnungen und -Richtlinien' : `${countryLabel}: Beziehe nationale Gesetze (${validCountry === 'DE' ? 'BDSG, TDDDG, TKG, UWG' : validCountry === 'AT' ? 'AT DSG, ECG, TKG, KSchG, MedienG' : 'CH DSG, DSV, OR, UWG, FMG'}) mit ein`}`
|
|
}
|
|
|
|
if (ragContext) {
|
|
systemContent += `\n\n## Relevanter Kontext aus dem RAG-System\n\nNutze die folgenden Quellen fuer deine Antwort. Verweise in deiner Antwort auf die jeweilige Quelle:\n\n${ragContext}`
|
|
}
|
|
|
|
systemContent += `\n\n## Aktueller SDK-Schritt\nDer Nutzer befindet sich im SDK-Schritt: ${currentStep}`
|
|
|
|
// 3. Build messages array (limit history to last 6 messages)
|
|
const messages = [
|
|
{ role: 'system', content: systemContent },
|
|
...history.slice(-6).map((h: { role: string; content: string }) => ({
|
|
role: h.role === 'user' ? 'user' : 'assistant',
|
|
content: h.content,
|
|
})),
|
|
{ role: 'user', content: message },
|
|
]
|
|
|
|
// 4. Call Ollama with streaming
|
|
const ollamaResponse = await fetch(`${OLLAMA_URL}/api/chat`, {
|
|
method: 'POST',
|
|
headers: { 'Content-Type': 'application/json' },
|
|
body: JSON.stringify({
|
|
model: LLM_MODEL,
|
|
messages,
|
|
stream: true,
|
|
think: false,
|
|
options: {
|
|
temperature: 0.3,
|
|
num_predict: 8192,
|
|
num_ctx: 8192,
|
|
},
|
|
}),
|
|
signal: AbortSignal.timeout(120000),
|
|
})
|
|
|
|
if (!ollamaResponse.ok) {
|
|
const errorText = await ollamaResponse.text()
|
|
console.error('Ollama error:', ollamaResponse.status, errorText)
|
|
return NextResponse.json(
|
|
{ error: `LLM nicht erreichbar (Status ${ollamaResponse.status}). Ist Ollama mit dem Modell ${LLM_MODEL} gestartet?` },
|
|
{ status: 502 }
|
|
)
|
|
}
|
|
|
|
// 5. Stream response back as plain text
|
|
const encoder = new TextEncoder()
|
|
const stream = new ReadableStream({
|
|
async start(controller) {
|
|
const reader = ollamaResponse.body!.getReader()
|
|
const decoder = new TextDecoder()
|
|
|
|
try {
|
|
while (true) {
|
|
const { done, value } = await reader.read()
|
|
if (done) break
|
|
|
|
const chunk = decoder.decode(value, { stream: true })
|
|
const lines = chunk.split('\n').filter((l) => l.trim())
|
|
|
|
for (const line of lines) {
|
|
try {
|
|
const json = JSON.parse(line)
|
|
if (json.message?.content) {
|
|
controller.enqueue(encoder.encode(json.message.content))
|
|
}
|
|
} catch {
|
|
// Partial JSON line, skip
|
|
}
|
|
}
|
|
}
|
|
} catch (error) {
|
|
console.error('Stream read error:', error)
|
|
} finally {
|
|
controller.close()
|
|
}
|
|
},
|
|
})
|
|
|
|
return new NextResponse(stream, {
|
|
headers: {
|
|
'Content-Type': 'text/plain; charset=utf-8',
|
|
'Cache-Control': 'no-cache',
|
|
'Connection': 'keep-alive',
|
|
},
|
|
})
|
|
} catch (error) {
|
|
console.error('Compliance advisor chat error:', error)
|
|
return NextResponse.json(
|
|
{ error: 'Verbindung zum LLM fehlgeschlagen. Bitte pruefen Sie ob Ollama laeuft.' },
|
|
{ status: 503 }
|
|
)
|
|
}
|
|
}
|