Files
David Gageot cab21861d1 Refactor RAG from agent-level config to standard toolset type
Replace the special-cased RAG configuration (AgentConfig.RAG []string referencing
top-level Config.RAG map) with a standard toolset type (type: rag) that follows
the same patterns as MCP and other toolsets.

Key changes:
- Add 'type: rag' to toolset registry with ref support for shared definitions
- Introduce RAGToolset wrapper (mirrors MCPToolset) for top-level rag section
- Add RAGConfig field to Toolset for inline/resolved RAG configuration
- Add resolveRAGDefinitions() mirroring resolveMCPDefinitions()
- Extract rag.NewManager() for per-toolset manager creation
- Implement tools.Startable on RAGTool for lazy init and file watching
- Remove RAG special-casing from Team, LocalRuntime, and teamloader
- Add v6→v7 migration for old rag agent field to toolset entries
- Update schema, docs, and all example YAML files

Assisted-By: docker-agent
2026-03-23 22:17:06 +01:00

31 lines
701 B
YAML

agents:
root:
model: openai/gpt-5-mini
description: a helpful assistant with keyword search
instruction: |
You are a helpful assistant that uses BM25 keyword-based search
to find relevant information in documents.
toolsets:
- type: rag
ref: blork_knowledge_base
rag:
blork_knowledge_base:
tool:
description: keyword-based search for blork documents
docs:
- ./docs
- ./blork_field_guide.txt
strategies:
- type: bm25
database: ./bm25.db
k1: 1.5
b: 0.75
threshold: 0.3
chunking:
size: 1000
overlap: 100
respect_word_boundaries: true
limit: 5