本地GenAI实验室

Prerequisites

• Java 21+
• Maven 3.9+
• Node 20+
• Ollama installed locally for the default provider
• Docker + Docker Compose, optional
• AWS CLI v2 + jq + valid AWS credentials, only for AWS shell tools and local MCP-backed report flows

5. Optional: build the local MCP server

cd mcp
npm install
npm run build

MCP is enabled by default in the backend. To run without it, set MCP_ENABLED=false.

Docker

Keep Ollama running on the host first, then:

docker compose up --build

• frontend: http://localhost:3000
• backend: http://localhost:8080

Qdrant is available as an optional local service for the phase-2 RAG vector database path. It is not required for default startup, lexical RAG, or current in-memory vector retrieval. If you want Qdrant as the backend startup default, start.sh and restart.sh start the qdrant Docker Compose service automatically when Qdrant mode is configured:

RAG_RETRIEVAL_MODE=vector RAG_VECTOR_STORE=qdrant ./restart.sh
./status.sh

Qdrant readiness and collection point count are visible in status output and the RAG UI. For normal use, start with ./restart.sh, open the RAG workspace, select Vector - Qdrant, and click Rebuild Index to populate the configured Qdrant collection. If Qdrant is unavailable or the collection is missing, the UI shows the target as unavailable instead of letting the failure look like a generic backend error.

Quick Start

2. Optional: create a local environment file

cp .env.example .env

Fill in only the providers you want available in the running backend process. The backend helper script will auto-load .env if it exists.

Configuration Overview

The most important backend settings are:

• APP_MODEL_PROVIDER default: ollama
• OLLAMA_DEFAULT_MODEL default: llama3:8b
• BEDROCK_REGION default: us-east-2
• BEDROCK_MODEL_ID default: empty
• HUGGINGFACE_BASE_URL default: https://router.huggingface.co/v1/chat/completions
• HUGGINGFACE_DEFAULT_MODEL default: empty
• HUGGINGFACE_MODELS default: empty
• MCP_ENABLED default: true
• RAG_ENABLED default: true
• RAG_CORPUS_ROOT default: docs
• RAG_TOP_K default: 4
• RAG_RETRIEVAL_MODE default: lexical
• RAG_VECTOR_STORE default: in-memory
• RAG_QDRANT_URL default: http://localhost:6333
• RAG_QDRANT_COLLECTION default: local_genai_lab_docs
• RAG_EMBEDDING_PROVIDER default: ollama
• RAG_EMBEDDING_MODEL default: nomic-embed-text
• RAG_EXCLUDED_SOURCE_PATHS default: rag-evaluation-guide.md,rag-retrieval-evaluation-template.md
• APP_TOOLS_ROUTING_MODE default: hybrid
• APP_STORAGE_SESSIONS_DIRECTORY default: data/sessions
• APP_STORAGE_REPORTS_DIRECTORY default: scripts/reports

The storage defaults are resolved from the project root so they stay stable whether the backend starts from backend/ or the repository root. You can also point APP_STORAGE_REPORTS_DIRECTORY to an absolute path outside the repository if you want report artifacts stored elsewhere. Provider switching details and helper startup scripts live in docs/providers.md.