Play 56
Semantic Code Search
Medium✅ Ready
Natural language codebase search with intent-based function discovery.
Natural language code search engine that understands code semantics beyond keyword matching. Indexes repositories into Azure AI Search with code-specific embeddings for intent-based function discovery and cross-repo navigation. Features dependency mapping, automated code documentation generation, and MCP tool integration for IDE-native search experiences.
Architecture Pattern
Code-aware RAG: specialized embeddings, cross-repo semantic indexing
Azure Services
Azure OpenAIAzure AI SearchBlob StorageContainer Apps
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Code Search Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (251 lines), evaluate (126 lines), tune (191 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + AI Search inputs + envFile
TuneKit (AI Config)
- config/openai.json — embedding model, search relevance
- config/guardrails.json — result quality, freshness thresholds
- evaluation/eval.py — MRR >0.75, Query latency <200ms
Tuning Parameters
Embedding chunk sizeSearch relevance thresholdIndex refresh intervalCross-repo depthDocumentation detail level
Estimated Cost
Dev/Test
$40–70/mo
Production
$800–2K/mo