graph-knowledge-doc-parser 0.2.2__tar.gz → 0.2.5__tar.gz

{graph_knowledge_doc_parser-0.2.2 → graph_knowledge_doc_parser-0.2.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: graph-knowledge-doc-parser
-Version: 0.2.2
+Version: 0.2.5
 Summary: doc parser using llm driven engine with graph knowledge awareness
 Author: humblemat810
 Author-email: 67593116+humblemat810@users.noreply.github.com
@@ -14,11 +14,18 @@ Classifier: Programming Language :: Python :: 3.14
 Classifier: Programming Language :: Python :: 3.15
 Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Text Processing :: General
+Provides-Extra: azure
+Provides-Extra: cloud
+Provides-Extra: gemini
+Provides-Extra: openai
+Provides-Extra: vertex
 Requires-Dist: diskcache (>=5.6,<6.0) ; platform_python_implementation == "PyPy"
 Requires-Dist: joblib (>=1.5.3,<2.0.0) ; platform_python_implementation == "CPython"
-Requires-Dist: kogwistar (==0.6.3)
+Requires-Dist: kogwistar (==0.6.4)
 Requires-Dist: langchain-core (>=1.2.5,<2.0.0)
-Requires-Dist: langchain-google-genai (>=4.1.2,<5.0.0)
+Requires-Dist: langchain-google-genai (>=4.1.2,<5.0.0) ; extra == "gemini" or extra == "cloud"
+Requires-Dist: langchain-google-vertexai (>=3.2.4,<4.0.0) ; extra == "vertex" or extra == "cloud"
+Requires-Dist: langchain-openai (>=1.6.7,<2.0.0) ; extra == "openai" or extra == "azure" or extra == "cloud"
 Requires-Dist: mcp (>=2.2.0,<3.0.0)
 Requires-Dist: pathspec (>=0.12.1,<0.13.0)
 Requires-Dist: pdf2image (>=1.17.0,<2.0.0)
@@ -65,6 +72,19 @@ The reusable helpers live under `src/workflow_ingest/` and are designed so the
 same core logic can be called from tests, scripts, and higher-level workflow
 code without duplicating orchestration.
 
+Layerwise parsing selects a strategy independently for each frontier layer.
+The default deterministic order is `layer_excerpt`, `layer_boundary`, then
+`page_index`; callers may provide another complete order, and optional triage
+may choose among the currently enabled strategies. Failed strategies are
+disabled for that layer and the workflow routes through the remaining methods
+before reaching explicit parse failure. PageIndex is a one-layer structural
+fallback that preserves exact source pointers and returns expandable children
+to normal strategy selection. See the
+[`0.2.5` release note](doc/release_0.2.5.md) and the
+[progressive refinement ADR](doc/adr_progressive_refinement_strategy_arbitration.md).
+The deterministic and text-only Bonsai fixture evaluation is recorded in the
+[`PageIndex adversarial fixture report`](doc/page_index_adversarial_fixture_report.md).
+
 For an adoption path that starts with parser-grounded source units and later
 adds LLM-Wiki cross-document maintenance, see
 [`doc/progressive_adoption_guide.md`](doc/progressive_adoption_guide.md). The
@@ -198,7 +218,7 @@ The project currently expects or optionally uses:
 - `split_raw_file_list`: optional allow-list file for PDF splitting runs
 - `answer_export_list`: optional export list path used by local workflows
 
-An example template is provided in [`.env.example`](/c:/Users/chanh/Documents/kg_doc_parser/.env.example).
+An example template is provided in [`.env.example`](.env.example).
 
 ## Provider Guide
 
@@ -242,6 +262,20 @@ and structured extraction.
   - `KG_DOC_PARSER_PROJECT=my-project`
   - `KG_DOC_PARSER_LOCATION=us-central1`
 
+Gemini, OpenAI/Azure, and Vertex adapters are optional so local-only
+installations do not pull their cloud SDK trees:
+
+```powershell
+poetry install -E openai -E gemini -E vertex
+# or, after building/installing the package:
+python -m pip install "graph-knowledge-doc-parser[openai,gemini,vertex]"
+```
+
+Installing an adapter does not create credentials, a cloud project, or a paid
+service. Use the no-charge offline provider contract tests for CI validation;
+only run a live provider smoke test when the account, endpoint, model, and
+zero-cost allowance are explicitly confirmed.
+
 ### Recipe Parsing Example
 
 If you are parsing a cooking recipe, one practical split is:
@@ -330,7 +364,7 @@ There is now a manual workflow-ingest demo harness that can run the end-to-end f
 - an already running external Kogwistar server
 
 The legacy semantic-smoke test in
-[`tests/test_semantic_layerwise_doc_parsing.py`](/c:/Users/chanh/Documents/kg_doc_parser/tests/test_semantic_layerwise_doc_parsing.py)
+[`tests/test_semantic_layerwise_doc_parsing.py`](tests/test_semantic_layerwise_doc_parsing.py)
 also expects a live Kogwistar server at `http://127.0.0.1:28110`. It does not
 start that server for you, so use the VS Code server launch config or start it
 manually before running the Ollama case.

{graph_knowledge_doc_parser-0.2.2 → graph_knowledge_doc_parser-0.2.5}/README.md

@@ -32,6 +32,19 @@ The reusable helpers live under `src/workflow_ingest/` and are designed so the
 same core logic can be called from tests, scripts, and higher-level workflow
 code without duplicating orchestration.
 
+Layerwise parsing selects a strategy independently for each frontier layer.
+The default deterministic order is `layer_excerpt`, `layer_boundary`, then
+`page_index`; callers may provide another complete order, and optional triage
+may choose among the currently enabled strategies. Failed strategies are
+disabled for that layer and the workflow routes through the remaining methods
+before reaching explicit parse failure. PageIndex is a one-layer structural
+fallback that preserves exact source pointers and returns expandable children
+to normal strategy selection. See the
+[`0.2.5` release note](doc/release_0.2.5.md) and the
+[progressive refinement ADR](doc/adr_progressive_refinement_strategy_arbitration.md).
+The deterministic and text-only Bonsai fixture evaluation is recorded in the
+[`PageIndex adversarial fixture report`](doc/page_index_adversarial_fixture_report.md).
+
 For an adoption path that starts with parser-grounded source units and later
 adds LLM-Wiki cross-document maintenance, see
 [`doc/progressive_adoption_guide.md`](doc/progressive_adoption_guide.md). The
@@ -165,7 +178,7 @@ The project currently expects or optionally uses:
 - `split_raw_file_list`: optional allow-list file for PDF splitting runs
 - `answer_export_list`: optional export list path used by local workflows
 
-An example template is provided in [`.env.example`](/c:/Users/chanh/Documents/kg_doc_parser/.env.example).
+An example template is provided in [`.env.example`](.env.example).
 
 ## Provider Guide
 
@@ -209,6 +222,20 @@ and structured extraction.
   - `KG_DOC_PARSER_PROJECT=my-project`
   - `KG_DOC_PARSER_LOCATION=us-central1`
 
+Gemini, OpenAI/Azure, and Vertex adapters are optional so local-only
+installations do not pull their cloud SDK trees:
+
+```powershell
+poetry install -E openai -E gemini -E vertex
+# or, after building/installing the package:
+python -m pip install "graph-knowledge-doc-parser[openai,gemini,vertex]"
+```
+
+Installing an adapter does not create credentials, a cloud project, or a paid
+service. Use the no-charge offline provider contract tests for CI validation;
+only run a live provider smoke test when the account, endpoint, model, and
+zero-cost allowance are explicitly confirmed.
+
 ### Recipe Parsing Example
 
 If you are parsing a cooking recipe, one practical split is:
@@ -297,7 +324,7 @@ There is now a manual workflow-ingest demo harness that can run the end-to-end f
 - an already running external Kogwistar server
 
 The legacy semantic-smoke test in
-[`tests/test_semantic_layerwise_doc_parsing.py`](/c:/Users/chanh/Documents/kg_doc_parser/tests/test_semantic_layerwise_doc_parsing.py)
+[`tests/test_semantic_layerwise_doc_parsing.py`](tests/test_semantic_layerwise_doc_parsing.py)
 also expects a live Kogwistar server at `http://127.0.0.1:28110`. It does not
 start that server for you, so use the VS Code server launch config or start it
 manually before running the Ollama case.

{graph_knowledge_doc_parser-0.2.2 → graph_knowledge_doc_parser-0.2.5}/kg_doc_parser/document_ingester_logger.py

@@ -82,7 +82,6 @@ NOTES
 
 from __future__ import annotations
 
-import json
 import os
 import queue
 import sqlite3
@@ -100,6 +99,8 @@ from langchain_core.outputs.llm_result import LLMResult
 from langchain_core.messages import BaseMessage
 from uuid import UUID
 
+from kg_doc_parser.workflow_ingest.serialization import safe_json_dumps
+
 # ---------------------------
 # Pricing / cost calculation
 # ---------------------------
@@ -537,7 +538,7 @@ class DocumentIngestSQLiteCallback(BaseCallbackHandler):
                 token_count=0,
                 cost_usd=0.0,
                 n_try=n_try,
-                metadata_json=json.dumps(payload, ensure_ascii=False),
+                metadata_json=safe_json_dumps(payload, ensure_ascii=False),
             )
         )
     def on_llm_start(
@@ -594,7 +595,7 @@ class DocumentIngestSQLiteCallback(BaseCallbackHandler):
                 token_count=0,
                 cost_usd=0.0,
                 n_try = payload.get('n_try', 0),
-                metadata_json=json.dumps(payload, ensure_ascii=False),
+                metadata_json=safe_json_dumps(payload, ensure_ascii=False),
             )
         )
 
@@ -710,7 +711,7 @@ class DocumentIngestSQLiteCallback(BaseCallbackHandler):
                 token_count=token_count,
                 cost_usd=float(cost_usd),
                 n_try=float(payload.get('n_try', 0)),
-                metadata_json=json.dumps(payload, ensure_ascii=False),
+                metadata_json=safe_json_dumps(payload, ensure_ascii=False),
             )
         )
 
@@ -777,6 +778,6 @@ class DocumentIngestSQLiteCallback(BaseCallbackHandler):
                 token_count=0,
                 cost_usd=0.0,
                 n_try=float(payload.get('n_try', 0)),
-                metadata_json=json.dumps(payload, ensure_ascii=False),
+                metadata_json=safe_json_dumps(payload, ensure_ascii=False),
             )
         )

{graph_knowledge_doc_parser-0.2.2 → graph_knowledge_doc_parser-0.2.5}/kg_doc_parser/workflow_ingest/__init__.py

@@ -4,71 +4,34 @@ from .adapters import (
     build_parser_source_map,
     normalize_ocr_pages,
 )
+from .cache import WorkflowLLMCallCache
 from .clients import (
     CanonicalGraphPersistenceClient,
-    DocumentTreeApiPersistenceClient,
     DirectRuntimeIngestClient,
+    DocumentTreeApiPersistenceClient,
     IngestExecutionClient,
     ServerCanonicalKgClient,
     UnsupportedClientOperation,
 )
-from .cache import WorkflowLLMCallCache
-from .design import DEFAULT_WORKFLOW_ID, build_ingest_workflow_design, ensure_ingest_workflow_design
 from .demo_harness import DemoHarnessArtifacts, DemoHarnessConfig, run_demo_harness
-from .handlers import build_ingest_step_resolver
-from .parsing import (
-    OCRParseRequest,
-    PageIndexParseRequest,
-    ParseMode,
-    TreeParseRequest,
-    parse_document,
-    parse_ocr_document,
-    parse_page_index_document,
-    parse_tree_document,
-)
-from .ocr_pipeline import (
-    OCRImagePayload,
-    OCRWorkflowArtifacts,
-    OCRWorkflowStateStore,
-    prepare_ocr_workflow_input,
-    run_ocr_ingest_workflow,
-)
-from .runners import (
-    LayerwiseWorkflowCommandResult,
-    OcrWorkflowCommandResult,
-    PageIndexWorkflowCommandResult,
-    WorkflowCommandResult,
-    discover_input_files,
-    run_demo_harness_workflow,
-    run_layerwise_batch_workflow,
-    run_layerwise_source_workflow,
-    run_ocr_batch_workflow,
-    run_ocr_source_workflow,
-    run_page_index_batch_workflow,
-    run_page_index_source_workflow,
-)
-from .smoke_assets import generate_ocr_smoke_assets
-from .page_index import (
-    BlockAssignment,
-    BlockAssignmentBatch,
-    CandidateBlock,
-    PageIndexBlockSpec,
-    PageIndexParseResult,
-    PageIndexValidationResult,
-    build_page_index_workflow_input,
+from .design import (
+    DEFAULT_WORKFLOW_ID,
+    build_ingest_workflow_design,
+    ensure_ingest_workflow_design,
 )
+from .handlers import build_ingest_step_resolver
 from .models import (
     BoundingBox,
     CanonicalGraphWriteResult,
     CurrentLayerContext,
-    CurrentLayerReview,
     CurrentLayerResult,
-    LayerCoverageGap,
-    LayerDuplicateChildNote,
+    CurrentLayerReview,
     GroundedSourceRecord,
     IngestRunHandle,
     IngestRunResult,
     LayerChildCandidate,
+    LayerCoverageGap,
+    LayerDuplicateChildNote,
     LayerFrontierItem,
     LayerSpanConflict,
     NormalizedPage,
@@ -79,16 +42,25 @@ from .models import (
     WorkflowExportBundle,
     WorkflowIngestInput,
 )
-from .providers import (
-    EmbeddingProviderConfig,
-    FakeChatModel,
-    ProviderEndpointConfig,
-    WorkflowProviderSettings,
-    build_chat_model,
-    build_chat_model_for_role,
-    build_embedding_function,
+from .ocr_pipeline import (
+    OCRImagePayload,
+    OCRWorkflowArtifacts,
+    OCRWorkflowStateStore,
+    prepare_ocr_workflow_input,
+    run_ocr_ingest_workflow,
+)
+from .page_index import (
+    BlockAssignment,
+    BlockAssignmentBatch,
+    CandidateBlock,
+    HierarchicalSummaryAssignment,
+    HierarchicalSummaryBatch,
+    PageIndexBlockSpec,
+    PageIndexParseResult,
+    PageIndexValidationResult,
+    build_page_index_workflow_input,
+    parse_page_index_layer,
 )
-from .probe import WorkflowProbe, emit_probe_event
 from .parser_core import (
     apply_cud_update,
     check_layer_coverage,
@@ -99,101 +71,161 @@ from .parser_core import (
     propose_layer_breakdown,
     review_layer,
 )
-from .service import build_default_engines, build_runtime, run_ingest_workflow
+from .parsing import (
+    OCRParseRequest,
+    PageIndexParseRequest,
+    ParseMode,
+    TreeParseRequest,
+    parse_document,
+    parse_ocr_document,
+    parse_page_index_document,
+    parse_tree_document,
+)
+from .probe import WorkflowProbe, emit_probe_event
+from .providers import (
+    EmbeddingProviderConfig,
+    FakeChatModel,
+    ProviderEndpointConfig,
+    WorkflowProviderSettings,
+    build_chat_model,
+    build_chat_model_for_role,
+    build_embedding_function,
+    provider_call_metrics_snapshot,
+)
+from .runners import (
+    LayerwiseWorkflowCommandResult,
+    OcrWorkflowCommandResult,
+    PageIndexWorkflowCommandResult,
+    WorkflowCommandResult,
+    discover_input_files,
+    run_demo_harness_workflow,
+    run_layerwise_batch_workflow,
+    run_layerwise_source_workflow,
+    run_ocr_batch_workflow,
+    run_ocr_source_workflow,
+    run_page_index_batch_workflow,
+    run_page_index_source_workflow,
+)
 from .semantics import HydratedTextPointer, SemanticNode
+from .service import build_default_engines, build_runtime, run_ingest_workflow
+from .smoke_assets import generate_ocr_smoke_assets
+from .strategy import (
+    HARD_CODED_STRATEGY_PRIORITY,
+    ParseStrategy,
+    ParseStrategyAssessment,
+    ParseStrategyDecision,
+    ParseStrategyRequest,
+    ParseStrategyTriage,
+    build_llm_strategy_triage,
+    hardcoded_strategy,
+    select_parse_strategy,
+)
 
 __all__ = [
+    "DEFAULT_WORKFLOW_ID",
+    "HARD_CODED_STRATEGY_PRIORITY",
+    "BlockAssignment",
+    "BlockAssignmentBatch",
     "BoundingBox",
+    "CandidateBlock",
     "CanonicalGraphPersistenceClient",
     "CanonicalGraphWriteResult",
     "CurrentLayerContext",
-    "CurrentLayerReview",
     "CurrentLayerResult",
-    "LayerCoverageGap",
-    "LayerDuplicateChildNote",
+    "CurrentLayerReview",
     "DemoHarnessArtifacts",
     "DemoHarnessConfig",
-    "DocumentTreeApiPersistenceClient",
     "DirectRuntimeIngestClient",
+    "DocumentTreeApiPersistenceClient",
     "EmbeddingProviderConfig",
+    "FakeChatModel",
     "GroundedSourceRecord",
+    "HierarchicalSummaryAssignment",
+    "HierarchicalSummaryBatch",
     "HydratedTextPointer",
-    "FakeChatModel",
     "IngestExecutionClient",
     "IngestRunHandle",
     "IngestRunResult",
     "LayerChildCandidate",
+    "LayerCoverageGap",
+    "LayerDuplicateChildNote",
     "LayerFrontierItem",
     "LayerSpanConflict",
+    "LayerwiseWorkflowCommandResult",
     "NormalizedPage",
     "NormalizedSourceCollection",
     "OCRImagePayload",
+    "OCRParseRequest",
     "OCRWorkflowArtifacts",
     "OCRWorkflowStateStore",
-    "OCRParseRequest",
-    "ParseSessionState",
-    "ProviderEndpointConfig",
-    "PageIndexParseRequest",
+    "OcrWorkflowCommandResult",
     "PageIndexBlockSpec",
+    "PageIndexParseRequest",
     "PageIndexParseResult",
     "PageIndexValidationResult",
+    "PageIndexWorkflowCommandResult",
     "ParseMode",
-    "TreeParseRequest",
+    "ParseSessionState",
+    "ParseStrategy",
+    "ParseStrategyAssessment",
+    "ParseStrategyDecision",
+    "ParseStrategyRequest",
+    "ParseStrategyTriage",
+    "ProviderEndpointConfig",
     "SemanticNode",
     "ServerCanonicalKgClient",
     "SourceUnit",
+    "TreeParseRequest",
     "UnsupportedClientOperation",
     "ValidationReport",
+    "WorkflowCommandResult",
+    "WorkflowExportBundle",
+    "WorkflowIngestInput",
     "WorkflowLLMCallCache",
     "WorkflowProbe",
     "WorkflowProviderSettings",
-    "WorkflowExportBundle",
-    "WorkflowIngestInput",
-    "WorkflowCommandResult",
-    "OcrWorkflowCommandResult",
-    "PageIndexWorkflowCommandResult",
-    "LayerwiseWorkflowCommandResult",
-    "CandidateBlock",
-    "BlockAssignment",
-    "BlockAssignmentBatch",
-    "DEFAULT_WORKFLOW_ID",
-    "build_chat_model",
-    "build_chat_model_for_role",
-    "build_embedding_function",
     "apply_cud_update",
-    "check_layer_coverage",
-    "default_parse_semantic_fn",
-    "finalize_semantic_tree",
-    "initialize_parse_session",
-    "prepare_layer_frontier",
-    "propose_layer_breakdown",
-    "review_layer",
     "build_authoritative_source_map",
+    "build_chat_model",
+    "build_chat_model_for_role",
     "build_default_engines",
-    "build_ingest_workflow_design",
+    "build_embedding_function",
     "build_ingest_step_resolver",
-    "build_parser_input_dict",
+    "build_ingest_workflow_design",
+    "build_llm_strategy_triage",
     "build_page_index_workflow_input",
+    "build_parser_input_dict",
     "build_parser_source_map",
     "build_runtime",
-    "ensure_ingest_workflow_design",
+    "check_layer_coverage",
+    "default_parse_semantic_fn",
+    "discover_input_files",
     "emit_probe_event",
+    "ensure_ingest_workflow_design",
+    "finalize_semantic_tree",
+    "generate_ocr_smoke_assets",
+    "hardcoded_strategy",
+    "initialize_parse_session",
     "normalize_ocr_pages",
     "parse_document",
     "parse_ocr_document",
     "parse_page_index_document",
+    "parse_page_index_layer",
     "parse_tree_document",
+    "prepare_layer_frontier",
     "prepare_ocr_workflow_input",
+    "propose_layer_breakdown",
+    "provider_call_metrics_snapshot",
+    "review_layer",
     "run_demo_harness",
     "run_demo_harness_workflow",
     "run_ingest_workflow",
-    "discover_input_files",
     "run_layerwise_batch_workflow",
     "run_layerwise_source_workflow",
     "run_ocr_batch_workflow",
+    "run_ocr_ingest_workflow",
     "run_ocr_source_workflow",
     "run_page_index_batch_workflow",
     "run_page_index_source_workflow",
-    "generate_ocr_smoke_assets",
-    "run_ocr_ingest_workflow",
+    "select_parse_strategy",
 ]

{graph_knowledge_doc_parser-0.2.2 → graph_knowledge_doc_parser-0.2.5}/kg_doc_parser/workflow_ingest/cli.py

@@ -46,14 +46,51 @@ def _provider_settings_from_args(args: argparse.Namespace) -> WorkflowProviderSe
         "api_key_env": args.parser_api_key_env,
     }
     proposal_mode = getattr(args, "proposal_mode", None)
+    parse_strategy = getattr(args, "parse_strategy", None)
+    parse_strategy_order = getattr(args, "parse_strategy_order", None)
+    triage_enabled = getattr(args, "triage_enabled", None)
+    page_index_summary_enabled = getattr(args, "page_index_summary_enabled", None)
+    page_index_hierarchical_summary_enabled = getattr(
+        args, "page_index_hierarchical_summary_enabled", None
+    )
     ocr_override = any(value is not None for value in ocr_values.values())
     parser_override = any(value is not None for value in parser_values.values())
     proposal_override = proposal_mode is not None
-    if not ocr_override and not parser_override and not proposal_override:
+    strategy_override = parse_strategy is not None
+    strategy_order_override = parse_strategy_order is not None
+    triage_override = triage_enabled is not None
+    summary_override = page_index_summary_enabled is not None
+    hierarchical_summary_override = page_index_hierarchical_summary_enabled is not None
+    if (
+        not ocr_override
+        and not parser_override
+        and not proposal_override
+        and not strategy_override
+        and not strategy_order_override
+        and not triage_override
+        and not summary_override
+        and not hierarchical_summary_override
+    ):
         return None
     settings = WorkflowProviderSettings.from_env()
     if proposal_override:
         settings = settings.model_copy(update={"proposal_mode": proposal_mode})
+    if strategy_override:
+        settings = settings.model_copy(update={"parse_strategy": parse_strategy})
+    if strategy_order_override:
+        settings = settings.model_copy(
+            update={"parse_strategy_order": tuple(parse_strategy_order.split(","))}
+        )
+    if triage_override:
+        settings = settings.model_copy(update={"triage_enabled": triage_enabled})
+    if summary_override:
+        settings = settings.model_copy(update={"page_index_summary_enabled": page_index_summary_enabled})
+    if hierarchical_summary_override:
+        settings = settings.model_copy(
+            update={
+                "page_index_hierarchical_summary_enabled": page_index_hierarchical_summary_enabled
+            }
+        )
     if ocr_override:
         settings = settings.model_copy(
             update={
@@ -76,6 +113,35 @@ def _provider_settings_from_args(args: argparse.Namespace) -> WorkflowProviderSe
 def _add_provider_args(parser: argparse.ArgumentParser) -> None:
     group = parser.add_argument_group("provider overrides")
     group.add_argument("--proposal-mode", choices=["children", "boundaries"], default=None)
+    group.add_argument(
+        "--parse-strategy",
+        choices=["auto", "layer_excerpt", "layer_boundary", "page_index"],
+        default=None,
+        help="Select the parser strategy for every frontier layer in this parse call",
+    )
+    group.add_argument(
+        "--parse-strategy-order",
+        default=None,
+        help="comma-separated parser order, e.g. layer_boundary,layer_excerpt,page_index",
+    )
+    group.add_argument(
+        "--triage-enabled",
+        action=argparse.BooleanOptionalAction,
+        default=None,
+        help="Enable or disable provider-backed per-layer strategy triage",
+    )
+    group.add_argument(
+        "--page-index-summary-enabled",
+        action=argparse.BooleanOptionalAction,
+        default=None,
+        help="Enable or disable summaries on PageIndex nodes for this parse call",
+    )
+    group.add_argument(
+        "--page-index-hierarchical-summary-enabled",
+        action=argparse.BooleanOptionalAction,
+        default=None,
+        help="Enable or disable the bounded parent-summary context pass",
+    )
     group.add_argument("--ocr-provider", default=None)
     group.add_argument("--ocr-model", default=None)
     group.add_argument("--ocr-base-url", default=None)