Loading packages/3gpp-ai/threegpp_ai/args.py +36 −3 Original line number Diff line number Diff line Loading @@ -22,7 +22,7 @@ CacheDirOption = Annotated[ # Summarize SummarizeDocumentArgument = Annotated[str, typer.Argument(help="Document ID to summarize")] SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target/Maximum word count (default: 200)")] SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target/Maximum word count")] SummarizeForceOption = Annotated[bool, typer.Option("--force", "-f", help="Force reconversion even if cached")] # Convert Loading @@ -38,7 +38,7 @@ WorkspaceNameArgument = Annotated[str, typer.Argument(help="Workspace name")] WorkspaceNameOption = Annotated[str | None, typer.Option("--workspace", "-w", help="Workspace name")] WorkspaceActivateOption = Annotated[ bool, typer.Option("--activate/--no-activate", help="Activate workspace after creation (default: activate)"), typer.Option("--activate/--no-activate", help="Activate workspace after creation"), ] WorkspaceAutoBuildOption = Annotated[ bool, Loading @@ -60,6 +60,13 @@ ConvertMdOption = Annotated[ envvar="TDC_AI_CONVERT_MD", ), ] WorkspaceEmbedOption = Annotated[ bool, typer.Option( "--embed", help="Insert extracted documents into LightRAG knowledge graph (implies --convert-md)", ), ] WorkspaceReleaseOption = Annotated[ str | None, typer.Option( Loading @@ -71,7 +78,7 @@ WorkspaceLimitOption = Annotated[int | None, typer.Option("--limit", help="Maxim WorkspaceIncludeInactiveOption = Annotated[bool, typer.Option("--include-inactive", help="Include inactive members")] WorkspaceProcessForceOption = Annotated[bool, typer.Option("--force", help="Force reprocessing of all members")] WorkspaceProcessVlmOption = Annotated[ bool | None, bool, typer.Option( "--vlm/--no-vlm", help="Enable VLM picture description and formula enrichment", Loading @@ -86,6 +93,32 @@ WorkspacePreserveArtifactsOption = Annotated[ ), ] # Accelerator options for Docling extraction AcceleratorDeviceOption = Annotated[ str, typer.Option( "--device", help="Compute device for document extraction: auto, cpu, cuda, mps, xpu, or cuda:N", envvar="TDC_AI_DEVICE", ), ] AcceleratorThreadsOption = Annotated[ int, typer.Option( "--threads", help="Number of threads for CPU-bound extraction operations", envvar="TDC_AI_NUM_THREADS", ), ] AcceleratorBatchSizeOption = Annotated[ int, typer.Option( "--batch-size", help="Batch size for OCR, layout, and table structure. Higher values benefit GPU", envvar="TDC_AI_BATCH_SIZE", ), ] # Filter options for workspace add-members StartDateOption = Annotated[ str | None, Loading src/tdoc_crawler/cli/args.py +6 −5 Original line number Diff line number Diff line Loading @@ -105,7 +105,7 @@ ReleaseOption = Annotated[ typer.Option( "--release", help=( "Spec release selector. Values: 'latest' (default), 'all', or explicit version. " "Spec release selector. Values: 'latest', 'all', or explicit version. " "Version formats: 18.0.0, 18.1 (=18.1.x), 18 (=18.x.y). " "Prefixes supported: v18, v18.1, v18.1.2, Rel-18, rel18 (case-insensitive)." ), Loading Loading @@ -152,7 +152,7 @@ NoProgressOption = Annotated[ # Options - AI SummarizeDocumentArgument = Annotated[str, typer.Argument(help="Document ID to summarize")] SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target/Maximum word count (default: 200)")] SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target/Maximum word count")] SummarizeForceOption = Annotated[ bool, typer.Option("--force", "-f", help="Force reconversion even if cached"), Loading @@ -172,7 +172,7 @@ ConvertForceOption = Annotated[ QueryArgument = Annotated[str | None, typer.Argument(help="Semantic search query")] WorkspaceNameOption = Annotated[str | None, typer.Option("--workspace", "-w", help="Workspace name")] EmbeddingTopKOption = Annotated[int, typer.Option("--top-k", "-k", help="Number of embedding results to return")] QueryMaxWordsOption = Annotated[int, typer.Option("--words", help="Maximum word count for LLM answer (default: 300)")] QueryMaxWordsOption = Annotated[int, typer.Option("--words", help="Maximum word count for LLM answer")] _ = Annotated[str | None, typer.Option("--tdoc-id", "-t", help="TDoc ID to process")] EmbeddingBackendOption = Annotated[ Loading Loading @@ -202,8 +202,9 @@ WorkspaceAutoBuildOption = Annotated[ WorkspaceActivateOption = Annotated[ bool, typer.Option( True, "--activate/--no-activate", help="Activate workspace after creation (default: activate)", help="Activate workspace after creation", envvar="TDC_AI_WORKSPACE_ACTIVATE", ), ] Loading @@ -226,5 +227,5 @@ WorkspaceProcessForceOption = Annotated[bool, typer.Option("--force", help="Forc WorkspacePreserveArtifactsOption = Annotated[ bool, typer.Option("--preserve-artifacts/--no-preserve-artifacts", help="Preserve artifacts (default: yes)"), typer.Option("--preserve-artifacts/--no-preserve-artifacts", help="Preserve artifacts"), ] Loading
packages/3gpp-ai/threegpp_ai/args.py +36 −3 Original line number Diff line number Diff line Loading @@ -22,7 +22,7 @@ CacheDirOption = Annotated[ # Summarize SummarizeDocumentArgument = Annotated[str, typer.Argument(help="Document ID to summarize")] SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target/Maximum word count (default: 200)")] SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target/Maximum word count")] SummarizeForceOption = Annotated[bool, typer.Option("--force", "-f", help="Force reconversion even if cached")] # Convert Loading @@ -38,7 +38,7 @@ WorkspaceNameArgument = Annotated[str, typer.Argument(help="Workspace name")] WorkspaceNameOption = Annotated[str | None, typer.Option("--workspace", "-w", help="Workspace name")] WorkspaceActivateOption = Annotated[ bool, typer.Option("--activate/--no-activate", help="Activate workspace after creation (default: activate)"), typer.Option("--activate/--no-activate", help="Activate workspace after creation"), ] WorkspaceAutoBuildOption = Annotated[ bool, Loading @@ -60,6 +60,13 @@ ConvertMdOption = Annotated[ envvar="TDC_AI_CONVERT_MD", ), ] WorkspaceEmbedOption = Annotated[ bool, typer.Option( "--embed", help="Insert extracted documents into LightRAG knowledge graph (implies --convert-md)", ), ] WorkspaceReleaseOption = Annotated[ str | None, typer.Option( Loading @@ -71,7 +78,7 @@ WorkspaceLimitOption = Annotated[int | None, typer.Option("--limit", help="Maxim WorkspaceIncludeInactiveOption = Annotated[bool, typer.Option("--include-inactive", help="Include inactive members")] WorkspaceProcessForceOption = Annotated[bool, typer.Option("--force", help="Force reprocessing of all members")] WorkspaceProcessVlmOption = Annotated[ bool | None, bool, typer.Option( "--vlm/--no-vlm", help="Enable VLM picture description and formula enrichment", Loading @@ -86,6 +93,32 @@ WorkspacePreserveArtifactsOption = Annotated[ ), ] # Accelerator options for Docling extraction AcceleratorDeviceOption = Annotated[ str, typer.Option( "--device", help="Compute device for document extraction: auto, cpu, cuda, mps, xpu, or cuda:N", envvar="TDC_AI_DEVICE", ), ] AcceleratorThreadsOption = Annotated[ int, typer.Option( "--threads", help="Number of threads for CPU-bound extraction operations", envvar="TDC_AI_NUM_THREADS", ), ] AcceleratorBatchSizeOption = Annotated[ int, typer.Option( "--batch-size", help="Batch size for OCR, layout, and table structure. Higher values benefit GPU", envvar="TDC_AI_BATCH_SIZE", ), ] # Filter options for workspace add-members StartDateOption = Annotated[ str | None, Loading
src/tdoc_crawler/cli/args.py +6 −5 Original line number Diff line number Diff line Loading @@ -105,7 +105,7 @@ ReleaseOption = Annotated[ typer.Option( "--release", help=( "Spec release selector. Values: 'latest' (default), 'all', or explicit version. " "Spec release selector. Values: 'latest', 'all', or explicit version. " "Version formats: 18.0.0, 18.1 (=18.1.x), 18 (=18.x.y). " "Prefixes supported: v18, v18.1, v18.1.2, Rel-18, rel18 (case-insensitive)." ), Loading Loading @@ -152,7 +152,7 @@ NoProgressOption = Annotated[ # Options - AI SummarizeDocumentArgument = Annotated[str, typer.Argument(help="Document ID to summarize")] SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target/Maximum word count (default: 200)")] SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target/Maximum word count")] SummarizeForceOption = Annotated[ bool, typer.Option("--force", "-f", help="Force reconversion even if cached"), Loading @@ -172,7 +172,7 @@ ConvertForceOption = Annotated[ QueryArgument = Annotated[str | None, typer.Argument(help="Semantic search query")] WorkspaceNameOption = Annotated[str | None, typer.Option("--workspace", "-w", help="Workspace name")] EmbeddingTopKOption = Annotated[int, typer.Option("--top-k", "-k", help="Number of embedding results to return")] QueryMaxWordsOption = Annotated[int, typer.Option("--words", help="Maximum word count for LLM answer (default: 300)")] QueryMaxWordsOption = Annotated[int, typer.Option("--words", help="Maximum word count for LLM answer")] _ = Annotated[str | None, typer.Option("--tdoc-id", "-t", help="TDoc ID to process")] EmbeddingBackendOption = Annotated[ Loading Loading @@ -202,8 +202,9 @@ WorkspaceAutoBuildOption = Annotated[ WorkspaceActivateOption = Annotated[ bool, typer.Option( True, "--activate/--no-activate", help="Activate workspace after creation (default: activate)", help="Activate workspace after creation", envvar="TDC_AI_WORKSPACE_ACTIVATE", ), ] Loading @@ -226,5 +227,5 @@ WorkspaceProcessForceOption = Annotated[bool, typer.Option("--force", help="Forc WorkspacePreserveArtifactsOption = Annotated[ bool, typer.Option("--preserve-artifacts/--no-preserve-artifacts", help="Preserve artifacts (default: yes)"), typer.Option("--preserve-artifacts/--no-preserve-artifacts", help="Preserve artifacts"), ]