RAG Module

The rag module indexes sources into knowledge bases and retrieves for agents.

On digitorn.ai (managed)? Use Studio Knowledge, not this module.

On the hosted platform, give an agent a knowledge base from the Knowledge manager in Studio (upload files or add a website, attach it to the agent) — the agent then searches it with the built-in knowledge.search tool, no YAML and no vector store to run. This page is the self-hosted rag module, for when you run your own daemon and vector backend.

Authoritative tool table: reference/modules/rag.

Agent tools (11)

create_knowledge_base, delete_knowledge_base, list_knowledge_bases, knowledge_base_stats, index_stats, ingest, ingest_file, ingest_directory, query, reindex, migrate_embeddings.

Zero-config

yaml

tools:
  modules:
    rag: {}

Configuration (high level)

Config is bound from YAML under tools.modules.rag (and related module config). Important groups from Config in Go:

Area	Notes
embedding_model	String shortcut or {id, dimensions, pooling}
backend	Vector store settings (Qdrant / pgvector / Elasticsearch appear in code)
pipeline / chunking / citations / cache / acl	Retrieval and safety knobs
sources	File, DB, web, kafka-style source entries for the indexer
auto_index	on_start, schedule (cron string for indexer triggers)
default_knowledge_base	Default KB name
max_knowledge_bases / max_documents	Caps

Source entries can carry their own triggers (type, every, cron).

Example

yaml

tools:
  modules:
    rag:
      config:
        embedding_model: minilm-l12
        default_knowledge_base: docs
        auto_index:
          on_start: true
          schedule: ""   # optional cron for the indexer
        sources:
          - name: handbook
            type: file
            path: "{{workdir}}/docs"
            extensions: [.md, .txt]
            recursive: true
  capabilities:
    grant:
      - module: rag

Related

• rag module reference
• Built-in tools
• scheduler for session wake-ups (unrelated to RAG auto_index)