Construct universal modules with decoded options

This commit is contained in:
2026-07-17 06:30:56 +00:00
parent ce3a07512f
commit b949e9bbc0
22 changed files with 290 additions and 158 deletions

View File

@@ -33,10 +33,17 @@ var referenceSlotDescriptions = shared.ReferenceSlotDescriptions{
var _ contracts.Chunker = (*Chunker)(nil)
var _ contracts.ManifestMetadataProvider = (*Chunker)(nil)
type Chunker struct{}
type Options struct{}
func New() *Chunker {
return &Chunker{}
type Chunker struct {
llm contracts.StructuredLLMClient
}
func New(llmClient contracts.StructuredLLMClient, _ Options) (*Chunker, error) {
if llmClient == nil {
return nil, chunkerErrorf("LLM client must not be nil")
}
return &Chunker{llm: llmClient}, nil
}
func (c *Chunker) Key() string {
@@ -71,6 +78,9 @@ func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contra
if c == nil {
return contracts.ChunkResult{}, chunkerErrorf("chunker must not be nil")
}
if c.llm == nil {
return contracts.ChunkResult{}, chunkerErrorf("LLM client must not be nil")
}
if ctx == nil {
return contracts.ChunkResult{}, chunkerErrorf("context must not be nil")
}
@@ -86,15 +96,8 @@ func (c *Chunker) Chunk(ctx context.Context, req contracts.ChunkRequest) (contra
if err := source.ValidateDocument(req.Source); err != nil {
return contracts.ChunkResult{}, chunkerErrorf("validate source document: %w", err)
}
if req.LLMClient == nil {
return contracts.ChunkResult{}, chunkerErrorf("LLM client must not be nil")
}
if len(req.Options) > 0 {
return contracts.ChunkResult{}, chunkerErrorf("options are not supported")
}
var response chunkResponse
if _, err := req.LLMClient.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
if _, err := c.llm.CompleteStructured(ctx, contracts.StructuredCompletionRequest{
StageName: Key,
PromptID: PromptID,
PromptVersion: ResponseSchemaVersion,
@@ -130,11 +133,27 @@ func ModuleSpec() pipeline.ModuleSpec {
}
func Register(registry *pipeline.ChunkerRegistry) error {
return registry.RegisterWithSpec(ModuleSpec(), func() (contracts.Chunker, error) {
return New(), nil
return registry.RegisterBuilderWithSpec(ModuleSpec(), validateOptions, func(request pipeline.BuildRequest) (contracts.Chunker, error) {
options, err := DecodeOptions(request.Options)
if err != nil {
return nil, err
}
return New(request.Dependencies.LLM, options)
})
}
func validateOptions(options map[string]any) error {
_, err := DecodeOptions(options)
return err
}
func DecodeOptions(options map[string]any) (Options, error) {
if err := pipeline.RejectUnknownOptions(options); err != nil {
return Options{}, chunkerErrorf("%w", err)
}
return Options{}, nil
}
func chunksFromResponse(doc *source.SourceDocument, response chunkResponse) ([]source.Chunk, error) {
if response.Scenes == nil {
return nil, fmt.Errorf("scenes must be present")