Move chunks into the canonical source model

This commit is contained in:
2026-07-17 05:32:11 +00:00
parent 40709e4ad8
commit 075888c97f
33 changed files with 548 additions and 325 deletions

View File

@@ -138,18 +138,6 @@ type InputAdapter interface {
Parse(ctx context.Context, req ParseRequest) (*source.SourceDocument, error)
}
type SourceChunk struct {
ID string `json:"id"`
SourceID string `json:"source_id"`
Index int `json:"index"`
StartUnitID int `json:"start_unit_id"`
EndUnitID int `json:"end_unit_id"`
Content []byte `json:"-"`
MediaType string `json:"media_type"`
Units []source.SourceUnit `json:"units"`
Metadata map[string]any `json:"metadata,omitempty"`
}
type ChunkRequest struct {
Source *source.SourceDocument `json:"-"`
SourceInput LLMInputMaterial `json:"source_input,omitempty"`
@@ -162,8 +150,8 @@ type ChunkRequest struct {
}
type ChunkResult struct {
Chunks []SourceChunk `json:"chunks"`
Warnings []Warning `json:"warnings,omitempty"`
Chunks []source.Chunk `json:"chunks"`
Warnings []Warning `json:"warnings,omitempty"`
}
type Chunker interface {
@@ -224,7 +212,7 @@ type ReferenceSet struct {
type ExtractionRequest struct {
Source *source.SourceDocument `json:"-"`
Chunk *SourceChunk `json:"chunk,omitempty"`
Chunk *source.Chunk `json:"chunk,omitempty"`
AmbientContext map[string]any `json:"ambient_context,omitempty"`
SourceInput LLMInputMaterial `json:"source_input,omitempty"`
SessionID string `json:"session_id,omitempty"`
@@ -277,8 +265,8 @@ type ValidationRequest struct {
Payload RawPayload `json:"payload"`
ChunkID string `json:"chunk_id,omitempty"`
ChunkIndex int `json:"chunk_index,omitempty"`
Chunk *SourceChunk `json:"chunk,omitempty"`
Chunks []SourceChunk `json:"chunks,omitempty"`
Chunk *source.Chunk `json:"chunk,omitempty"`
Chunks []source.Chunk `json:"chunks,omitempty"`
ExtractOutputs []ExtractOutput `json:"extract_outputs,omitempty"`
MergeOutput MergeOutput `json:"merge_output,omitempty"`
}