74 lines
2.5 KiB
Markdown
74 lines
2.5 KiB
Markdown
# AI Council Review: Research Bridge
|
|
|
|
## Reviewers
|
|
- **Architect:** System design, API contracts, data flow
|
|
- **DevOps:** Deployment, monitoring, infrastructure
|
|
- **QA:** Testing strategy, edge cases, validation
|
|
- **Security:** Authentication, abuse prevention, data handling
|
|
- **Cost Analyst:** Pricing, efficiency, ROI
|
|
|
|
---
|
|
|
|
## Review Questions
|
|
|
|
### Architect
|
|
1. **Q:** Is the async pattern throughout the stack justified?
|
|
**A:** Yes. SearXNG + LLM calls are I/O bound; async prevents blocking.
|
|
|
|
2. **Q:** Why FastAPI over Flask/Django?
|
|
**A:** Native async, automatic OpenAPI docs, Pydantic validation.
|
|
|
|
3. **Q:** Should the synthesizer be a separate service?
|
|
**A:** Not initially. Monolith first, extract if scale demands.
|
|
|
|
4. **Q:** Kimi for Coding API compatibility?
|
|
**A:** OpenAI-compatible, but requires special User-Agent header. Handled in client config.
|
|
|
|
### DevOps
|
|
1. **Q:** SearXNG self-hosted requirements?
|
|
**A:** 1 CPU, 512MB RAM, ~5GB disk. Can run on same host or separate.
|
|
|
|
2. **Q:** Monitoring strategy?
|
|
**A:** Prometheus metrics + structured logging. Alert on error rate >1%.
|
|
|
|
### QA
|
|
1. **Q:** How to test LLM responses deterministically?
|
|
**A:** Mock Kimi responses in unit tests. E2E uses real API (no cost concerns with existing subscription).
|
|
|
|
2. **Q:** What defines "acceptable" answer quality?
|
|
**A:** Blind test: 20 queries, human rates Research Bridge vs Perplexity. Target: ≥80% parity.
|
|
|
|
### Security
|
|
1. **Q:** API key exposure risk?
|
|
**A:** Kimi key in env vars only. Rotate if compromised. No client-side exposure.
|
|
|
|
2. **Q:** Rate limiting sufficient?
|
|
**A:** 30 req/min per IP prevents casual abuse. Global limit as circuit breaker.
|
|
|
|
3. **Q:** User-Agent header leak risk?
|
|
**A:** Header is hardcoded in backend, never exposed to clients. Low risk.
|
|
|
|
### Cost Analyst
|
|
1. **Q:** Realistic monthly cost at 1000 queries/month?
|
|
**A:** **$0** - Kimi for Coding via existing subscription, SearXNG self-hosted. vs $15-30 with Perplexity.
|
|
|
|
2. **Q:** When does this NOT make sense?
|
|
**A:** If setup effort (~10h) not justified for expected query volume. But at $0 marginal cost, break-even is immediate.
|
|
|
|
---
|
|
|
|
## Consensus
|
|
|
|
**Proceed with Phase 1.** Architecture is sound, risks identified and mitigated. **Zero marginal cost** makes this compelling even at low query volumes.
|
|
|
|
**Conditions for Phase 2:**
|
|
- Phase 1 latency <2s for search-only
|
|
- Test coverage >80%
|
|
- SearXNG stable for 48h continuous operation
|
|
- User-Agent header handling verified
|
|
|
|
---
|
|
|
|
**Review Date:** 2026-03-14
|
|
**Status:** ✅ Approved for implementation
|