Files
notarius/internal/cli/catalog.go

150 lines
5.3 KiB
Go

package cli
import (
"context"
"fmt"
"strings"
"gitea.maximumdirect.net/eric/notarius/internal/core/artifacts"
"gitea.maximumdirect.net/eric/notarius/internal/core/config"
"gitea.maximumdirect.net/eric/notarius/internal/framework/contracts"
"gitea.maximumdirect.net/eric/notarius/internal/framework/llm"
"gitea.maximumdirect.net/eric/notarius/internal/framework/pipeline"
"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/dnd/scenes"
"gitea.maximumdirect.net/eric/notarius/internal/modules/chunk/generic"
"gitea.maximumdirect.net/eric/notarius/internal/modules/dnd/promptassets"
"gitea.maximumdirect.net/eric/notarius/internal/modules/extract/dnd/spells"
"gitea.maximumdirect.net/eric/notarius/internal/modules/input/seriatim"
"gitea.maximumdirect.net/eric/notarius/internal/modules/merge/appendorder"
"gitea.maximumdirect.net/eric/notarius/internal/modules/normalize/noop"
jsonoutput "gitea.maximumdirect.net/eric/notarius/internal/modules/output/json"
)
func productionRegistries() (pipeline.Registries, error) {
registries := pipeline.Registries{
Inputs: pipeline.NewInputAdapterRegistry(),
Chunkers: pipeline.NewChunkerRegistry(),
Extractors: pipeline.NewExtractorRegistry(),
Mergers: pipeline.NewMergerRegistry(),
Normalizers: pipeline.NewNormalizerRegistry(),
Validators: pipeline.NewValidatorRegistry(),
Outputs: pipeline.NewOutputEncoderRegistry(),
}
if err := seriatim.Register(registries.Inputs); err != nil {
return pipeline.Registries{}, fmt.Errorf("register seriatim input: %w", err)
}
if err := generic.Register(registries.Chunkers); err != nil {
return pipeline.Registries{}, fmt.Errorf("register generic chunker: %w", err)
}
if err := scenes.Register(registries.Chunkers); err != nil {
return pipeline.Registries{}, fmt.Errorf("register dnd scenes chunker: %w", err)
}
if err := spells.Register(registries.Extractors); err != nil {
return pipeline.Registries{}, fmt.Errorf("register dnd spells extractor: %w", err)
}
if err := appendorder.Register(registries.Mergers); err != nil {
return pipeline.Registries{}, fmt.Errorf("register appendorder merger: %w", err)
}
if err := noop.Register(registries.Normalizers); err != nil {
return pipeline.Registries{}, fmt.Errorf("register noop normalizer: %w", err)
}
if err := jsonoutput.Register(registries.Outputs); err != nil {
return pipeline.Registries{}, fmt.Errorf("register json output encoder: %w", err)
}
return registries, nil
}
func productionCatalog() (pipeline.ModuleCatalog, error) {
registries, err := productionRegistries()
if err != nil {
return pipeline.ModuleCatalog{}, err
}
return catalogFromRegistries(registries), nil
}
func productionPromptAssets() (*llm.AssetRegistry, error) {
registry := llm.NewAssetRegistry()
if err := promptassets.Register(registry); err != nil {
return nil, fmt.Errorf("register shared dnd prompt assets: %w", err)
}
if err := scenes.RegisterPromptAssets(registry); err != nil {
return nil, fmt.Errorf("register dnd scenes prompt assets: %w", err)
}
if err := spells.RegisterPromptAssets(registry); err != nil {
return nil, fmt.Errorf("register dnd spells prompt assets: %w", err)
}
return registry, nil
}
func effectiveCatalog(opts Options) (pipeline.ModuleCatalog, error) {
if !isEmptyCatalog(opts.Catalog) {
return opts.Catalog, nil
}
if !isEmptyRegistries(opts.Registries) {
return catalogFromRegistries(opts.Registries), nil
}
return productionCatalog()
}
func effectiveRegistries(opts Options) (pipeline.Registries, error) {
if !isEmptyRegistries(opts.Registries) {
return opts.Registries, nil
}
if !isEmptyCatalog(opts.Catalog) {
return registriesFromCatalog(opts.Catalog), nil
}
return productionRegistries()
}
func catalogFromRegistries(registries pipeline.Registries) pipeline.ModuleCatalog {
return pipeline.ModuleCatalog{
Inputs: registries.Inputs,
Chunkers: registries.Chunkers,
Extractors: registries.Extractors,
Mergers: registries.Mergers,
Normalizers: registries.Normalizers,
Validators: registries.Validators,
Outputs: registries.Outputs,
}
}
func registriesFromCatalog(catalog pipeline.ModuleCatalog) pipeline.Registries {
return pipeline.Registries{
Inputs: catalog.Inputs,
Chunkers: catalog.Chunkers,
Extractors: catalog.Extractors,
Mergers: catalog.Mergers,
Normalizers: catalog.Normalizers,
Validators: catalog.Validators,
Outputs: catalog.Outputs,
}
}
func isEmptyCatalog(catalog pipeline.ModuleCatalog) bool {
return catalog.Inputs == nil &&
catalog.Chunkers == nil &&
catalog.Extractors == nil &&
catalog.Mergers == nil &&
catalog.Normalizers == nil &&
catalog.Validators == nil &&
catalog.Outputs == nil
}
func isEmptyRegistries(registries pipeline.Registries) bool {
return registries.Inputs == nil &&
registries.Chunkers == nil &&
registries.Extractors == nil &&
registries.Mergers == nil &&
registries.Normalizers == nil &&
registries.Validators == nil &&
registries.Outputs == nil
}
func productionLLMClientFactory(ctx context.Context, cfg config.Config, profileID string) (contracts.StructuredLLMClient, []artifacts.LLMProfileManifest, error) {
if err := ctx.Err(); err != nil {
return nil, nil, err
}
trimmedID := strings.TrimSpace(profileID)
return nil, nil, fmt.Errorf("create Scriptorium-backed LLM client for profile %q: not implemented yet", trimmedID)
}