Create tag extractor
Create a TagExtractor. A first TagExtractorVersion is created
automatically and marked as default.
Required field: name. The tagging_tree body is validated against
a schema by the backend — id, label, and children keys must be
present at every node (children may be empty).
Authorizations
Use Authorization: Bearer
Path Parameters
UUID of the project
Body
Applies hierarchical metadata tags to chunks (or documents) using an LLM.
"Department classifier"
"Classify each chunk into a department."
"gpt-4o"
Nested tree describing the tag taxonomy. Each node has shape
{id: string, label: string, children: [...]}.
"Choose the department this chunk most likely belongs to."
Granularity at which tags are applied.
chunk, document "chunk"
When true, only one leaf tag per chunk is allowed.
false
Response
Created
Applies hierarchical metadata tags to chunks (or documents) using an LLM.
"Department classifier"
"Classify each chunk into a department."
"gpt-4o"
Nested tree describing the tag taxonomy. Each node has shape
{id: string, label: string, children: [...]}.
"Choose the department this chunk most likely belongs to."
Granularity at which tags are applied.
chunk, document "chunk"
When true, only one leaf tag per chunk is allowed.
false
Immutable snapshot of a TagExtractor's version-bearing configuration.
Immutable snapshot of a TagExtractor's version-bearing configuration.