Ingestion Rule

This page is auto-generated from the formations OpenAPI spec. Do not edit manually — run pnpm generate-formations-resource-docs to regenerate.

Routes a file content_type to a converter (tool or agent) so ingestion can turn non-native files (images, audio, scanned PDFs) into Documents. See the Ingestion Rules module docs for the matching and converter-invocation model.

Syntax

type: ingestion_rule
properties:
  content_type_glob: String
  tool_id: String
  agent_id: String
  action: String
  preset_parameters: Object
  native_extraction: String
  file_delivery: String
  chunk_strategy: String
  chunk_size: Integer
  chunk_overlap: Integer
  metadata: Object

Output

The physical resource ID is the public ID of the created resource. Reference it from other resources with a ref expression:

      some_field:
        ref: MyIngestionRule

Properties

content_type_glob

MIME type glob matched against a file's content_type (e.g. image/*, audio/mpeg, application/pdf)

Required: Yes Type: String

---

tool_id

Converter tool ID (mutually exclusive with agent_id)

Required: No Type: String Nullable: Yes

---

agent_id

Converter agent ID (mutually exclusive with tool_id)

Required: No Type: String Nullable: Yes

---

action

Operation id, required for soat/mcp tool converters

Required: No Type: String Nullable: Yes

---

preset_parameters

Merged into the tool input before invocation (tool converters only)

Required: No Type: Object Nullable: Yes

---

native_extraction

For native types (PDF/text): first (default) converts only when native extraction yields no text; skip always converts.

Required: No Type: String Nullable: Yes

---

file_delivery

How the file reaches a tool converter — base64 (default) or download_url

Required: No Type: String Nullable: Yes

---

chunk_strategy

Default chunk strategy (page/whole/size), overridable per ingest request

Required: No Type: String Nullable: Yes

---

chunk_size

Default window size in characters for the size strategy

Required: No Type: Integer Nullable: Yes

---

chunk_overlap

Default overlap in characters for the size strategy

Required: No Type: Integer Nullable: Yes

---

metadata

Arbitrary JSON metadata

Required: No Type: Object Nullable: Yes

---