# Portfolio Bot Configuration # Documentation: https://github.com/VictorVargas/rony-llm-agent/pkg/llm server: host: "0.0.0.0" port: 7331 read_timeout_ms: 30000 cors_origins: - "http://localhost:4321" # Astro dev server - "https://victorvargas.dev" # Production (when it exists) rate_limit: requests_per_minute: 30 # Per IP burst: 5 # LLM providers (at least one configured) providers: # === Ollama (recommended for development) === - name: ollama-local type: ollama model: qwen2.5:1.5b # Small model for Q&A endpoint: http://localhost:11434 default: true # === llama.cpp direct (GGUF) === - name: llamacpp-local type: llamacpp model_path: ${RONY_MODELS_PATH}/qwen2.5-1.5b-instruct-q5_k_m.gguf context_size: 4096 n_gpu_layers: 999 # === Anthropic (if you want quality > privacy) === - name: anthropic-api type: anthropic model: claude-haiku-4 # Cheap model api_key_env: ANTHROPIC_API_KEY # RAG: how projects are indexed rag: enabled: true data_path: ./data/projects # Directory with .md chunk_size: 500 # characters per chunk chunk_overlap: 50 embedding_provider: ollama # or llamacpp embedding_model: nomic-embed-text vector_db_path: ./chroma # Local persistence top_k: 5 # Documents to retrieve per query rerank: false # Phase 2 # Persona: who the bot is persona: name: "Rony Chat Bot" tone: "Professional, knowledgeable, friendly" language: "English" constraints: - "Only answer about Victor and his projects" - "If you don't know, say 'I don't have that information'" - "Be concise but informative" - "Use markdown format for lists and code" intro: "Hi! I'm Rony, Victor Hugo Vargas's virtual assistant. Ask me about his projects, skills or experience." # Base system prompt (concatenated with RAG content) system_prompt: | You are Rony Chat Bot, the virtual assistant of Victor Hugo Vargas, a Mexican software engineer. Your job is to answer questions about: - Victor's projects (see files in data/projects/) - His experience and technical skills - His work approach Respond in English, with professional but accessible tone. If you're asked something not in your context, say it honestly. Recommended format: - Use markdown for lists, code, and emphasis - Be concise (max 2-3 paragraphs per response) - Include links to repos when relevant # Logging logging: level: info # debug | info | warn | error format: json # json | text output: stderr