Add reference contracts to extractor metadata

This commit is contained in:
2026-07-05 14:13:48 +00:00
parent f9999a73df
commit 1c31f56af1
15 changed files with 347 additions and 12 deletions

View File

@@ -74,10 +74,49 @@ type Chunker interface {
Chunk(ctx context.Context, req ChunkRequest) (ChunkResult, error)
}
const (
ReferenceBindingSourceConfig = "config"
ReferenceBindingSourceCLI = "cli"
)
type ReferenceSlot struct {
Name string `json:"name"`
Description string `json:"description,omitempty"`
Required bool `json:"required,omitempty"`
AcceptedMediaTypes []string `json:"accepted_media_types,omitempty"`
Multiple bool `json:"multiple,omitempty"`
MaxBytes int64 `json:"max_bytes,omitempty"`
}
type ReferenceOrigin struct {
Type string `json:"type"`
URI string `json:"uri,omitempty"`
}
type ReferenceItem struct {
SlotName string `json:"slot_name"`
MediaType string `json:"media_type,omitempty"`
Content []byte `json:"-"`
Digest string `json:"digest,omitempty"`
Origin ReferenceOrigin `json:"origin"`
SizeBytes int64 `json:"size_bytes,omitempty"`
BindingSource string `json:"binding_source,omitempty"`
}
type ResolvedReferenceSlot struct {
Slot ReferenceSlot `json:"slot"`
Items []ReferenceItem `json:"items,omitempty"`
}
type ReferenceSet struct {
Slots map[string]ResolvedReferenceSlot `json:"slots,omitempty"`
}
type ExtractionRequest struct {
Source *source.SourceDocument `json:"-"`
Chunk *SourceChunk `json:"chunk,omitempty"`
AmbientContext map[string]any `json:"ambient_context,omitempty"`
References ReferenceSet `json:"references,omitempty"`
LLMClient StructuredLLMClient `json:"-"`
LLMProfile string `json:"llm_profile,omitempty"`
Options map[string]any `json:"options,omitempty"`
@@ -93,6 +132,7 @@ type Extractor interface {
Key() string
ArtifactType() string
SchemaVersion() string
ReferenceSlots() []ReferenceSlot
Validators() []Validator
Extract(ctx context.Context, req ExtractionRequest) (ExtractionResult, error)
}