HKUDS/LightRAG

Pattern Findings

The scanner identified 12483 distinct pattern matches across 24 syntactic categories. Each entry below represents a discrete location in the source code where the engine recorded a detector match to inspect in context. Expand any category row to inspect the individual file paths, line numbers, code snippets, and the lexical context (CODE, COMMENT, or STRING) in which each match was detected.

Reading the findings table: The Severity column indicates the configured finding weight (CRITICAL / HIGH / MEDIUM / LOW). The Context column identifies whether the match occurred inside executable code, an inline comment, or a string literal — legacy comment-context matches receive a ×1.5 score weight. The ⚡ bolt icon marks clustered matches: three or more patterns within a 10-line window, each receiving an additional ×1.5 density multiplier under the legacy scoring model.

Hyper-Verbose Identifiers7927 hits · 6932 pts

Severity	File	Line	Snippet	Context
LOW	reproduce/Step_3_openai_compatible.py	57	def run_queries_and_save_to_json(	CODE
LOW	reproduce/Step_3.py	26	def run_queries_and_save_to_json(	CODE
LOW	lightrag/rerank.py	36	def chunk_documents_for_rerank(	CODE
LOW	lightrag/rerank.py	142	async def achunk_documents_for_rerank(	CODE
LOW	lightrag/addon_params.py	30	def _emit_deprecated_addon_warnings(params: Mapping[str, Any]) -> None:	CODE
LOW	lightrag/table_markup.py	83	def header_grid_to_thead_html(grid: list[list[str]]) -> str:	CODE
LOW	lightrag/llm_roles.py	130	def register_role_llm_builder(	CODE
LOW⚡	lightrag/llm_roles.py	162	def _get_effective_role_llm_kwargs(self, role: str) -> dict[str, Any]:	CODE
LOW⚡	lightrag/llm_roles.py	170	def _get_effective_role_llm_timeout(self, role: str) -> int:	CODE
LOW⚡	lightrag/llm_roles.py	174	def _get_effective_role_llm_max_async(self, role: str) -> int:	CODE
LOW	lightrag/llm_roles.py	212	def _rebuild_single_role_llm_func(self, role: str) -> None:	CODE
LOW	lightrag/llm_roles.py	228	def _schedule_retired_llm_queue_cleanup(	CODE
LOW⚡	lightrag/llm_roles.py	256	def _finalize_retired_llm_queue_cleanup(self, task: asyncio.Task) -> None:	CODE
LOW⚡	lightrag/llm_roles.py	265	async def wait_for_retired_llm_queues(self) -> None:	CODE
LOW	lightrag/llm_roles.py	309	def _apply_llm_role_config_update(	CODE
LOW	lightrag/llm_roles.py	611	async def get_embedding_queue_status(self) -> dict[str, Any]:	CODE
LOW⚡	lightrag/lightrag.py	1426	def _set_runtime_addon_params(self, addon_params: Mapping[str, Any] \| None) -> None:	CODE
LOW⚡	lightrag/lightrag.py	1430	def _apply_chunk_size_overlay(self) -> None:	CODE
LOW⚡	lightrag/lightrag.py	7475	def _admin_write_gate_required(self) -> bool:	CODE
LOW	lightrag/lightrag.py	286	def _default_admin_write_hold_seconds(embedding_timeout: float) -> float:	CODE
LOW	lightrag/lightrag.py	1549	def _refresh_addon_params_cache(self) -> None:	CODE
LOW	lightrag/lightrag.py	1569	def _ensure_addon_params_cache(self) -> None:	CODE
LOW	lightrag/lightrag.py	1623	def _build_role_llm_cache_identity(	CODE
LOW	lightrag/lightrag.py	2039	def _get_parse_native_executor(self) -> ThreadPoolExecutor:	CODE
LOW	lightrag/lightrag.py	2056	def _shutdown_parser_executor(self) -> None:	CODE
LOW	lightrag/lightrag.py	2074	async def _commit_cache_pair_before_finalize(self) -> None:	CODE
LOW	lightrag/lightrag.py	2102	async def _quarantine_cache_before_finalize(	CODE
LOW	lightrag/lightrag.py	2691	def _operation_truncation_record() -> dict[str, Any] \| None:	CODE
LOW	lightrag/lightrag.py	2705	def _terminal_truncation_kwargs() -> dict[str, Any]:	CODE
LOW	lightrag/lightrag.py	2728	async def _journal_truncation_write_ahead(	CODE
LOW	lightrag/lightrag.py	3139	async def _upsert_custom_chunk_status(	CODE
LOW	lightrag/lightrag.py	3229	async def _union_doc_recovery_anchors(	CODE
LOW	lightrag/lightrag.py	3269	async def arollback_failed_custom_chunk_patches(	CODE
LOW	lightrag/lightrag.py	3436	async def _rollback_one_custom_chunk_patch(	CODE
LOW	lightrag/lightrag.py	3568	async def _persist_custom_chunk_recovery_warning(	CODE
LOW	lightrag/lightrag.py	3692	async def _prune_doc_recovery_anchors(	CODE
LOW	lightrag/lightrag.py	3762	async def _process_extract_entities(	CODE
LOW	lightrag/lightrag.py	3814	async def _discard_pending_index_ops(	CODE
LOW	lightrag/lightrag.py	3995	async def _record_chunk_reference_commit_failure(self, reason: str) -> None:	CODE
LOW	lightrag/lightrag.py	4184	async def _flush_cache_after_references() -> None:	CODE
LOW	lightrag/lightrag.py	4299	async def _insert_done_with_cleanup(self) -> None:	CODE
LOW	lightrag/lightrag.py	4387	def _normalize_custom_kg_entity_name(value: Any, *, field: str) -> str:	CODE
LOW	lightrag/lightrag.py	5367	async def _update_delete_retry_state(	CODE
LOW	lightrag/lightrag.py	5448	async def _get_existing_llm_cache_ids(self, cache_ids: list[str]) -> list[str]:	CODE
LOW	lightrag/lightrag.py	5644	def _patch_journal_candidates(	CODE
LOW	lightrag/lightrag.py	5674	async def _resolve_purge_recovery_proof(	CODE
LOW	lightrag/lightrag.py	5882	def _raise_missing_recovery_proof(	CODE
LOW	lightrag/lightrag.py	6265	async def _purge_derived_kg_contributions(	CODE
LOW	lightrag/lightrag.py	7495	def _admin_write_hold_ceiling(self) -> float:	CODE
LOW	lightrag/lightrag.py	7513	def _validate_admin_write_bounds(self) -> None:	CODE
LOW	lightrag/lightrag.py	7557	def _admin_write_lock_namespace(self) -> str:	CODE
LOW	lightrag/lightrag.py	7760	def _discard_uncommitted_graph_mutations(self, operation: str) -> None:	CODE
LOW	lightrag/lightrag.py	7791	async def _drive_pipeline_if_deferred(self, workspace: str) -> None:	CODE
LOW	lightrag/lightrag.py	7848	def _schedule_deferred_pipeline_drive(self, workspace: str) -> asyncio.Task \| None:	CODE
LOW	lightrag/lightrag.py	7910	async def _cancel_admin_release_drives(self) -> None:	CODE
LOW	lightrag/lightrag.py	7925	async def _raise_if_recovery_required(self) -> None:	CODE
LOW	lightrag/query_validation.py	101	def meets_min_rag_query_weight(query: str) -> bool:	CODE
LOW	lightrag/operate.py	184	def _get_relationship_vdb_timeout_seconds(global_config: dict[str, Any]) -> float:	CODE
LOW	lightrag/operate.py	201	def _format_relation_edge_label(edge_key: tuple[str, str] \| list[str]) -> str:	CODE
LOW	lightrag/operate.py	209	def _truncate_entity_identifier(	CODE
7867 more matches not shown…

Decorative Section Separators1575 hits · 5901 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	lightrag/lightrag.py	7471	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/lightrag.py	7473	# ------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/lightrag.py	233	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/lightrag.py	235	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/constants.py	790	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/constants.py	794	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/utils.py	4006	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/utils.py	4008	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	2880	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	2882	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	3270	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	3272	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	3325	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	3327	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	3577	# -----------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	3579	# -----------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	3812	# -----------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils.py	3814	# -----------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/pipeline.py	736	# ============================================================	COMMENT
MEDIUM⚡	lightrag/pipeline.py	738	# ============================================================	COMMENT
MEDIUM⚡	lightrag/pipeline.py	2274	# ============================================================	COMMENT
MEDIUM⚡	lightrag/pipeline.py	2276	# ============================================================	COMMENT
MEDIUM⚡	lightrag/pipeline.py	6095	# ============================================================	COMMENT
MEDIUM⚡	lightrag/pipeline.py	6097	# ============================================================	COMMENT
MEDIUM⚡	lightrag/pipeline.py	6502	# ============================================================	COMMENT
MEDIUM⚡	lightrag/pipeline.py	6504	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	634	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	636	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	3150	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	3156	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	4405	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	4407	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	4987	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	4989	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	6837	# ============================================================	COMMENT
MEDIUM	lightrag/pipeline.py	6839	# ============================================================	COMMENT
MEDIUM⚡	lightrag/multimodal_context.py	86	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/multimodal_context.py	90	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/multimodal_context.py	265	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/multimodal_context.py	267	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/multimodal_context.py	724	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/multimodal_context.py	726	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/multimodal_context.py	130	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/multimodal_context.py	133	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/multimodal_context.py	186	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/multimodal_context.py	188	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/multimodal_context.py	500	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/multimodal_context.py	502	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/utils_pipeline.py	1303	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/utils_pipeline.py	1305	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/utils_pipeline.py	1330	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/utils_pipeline.py	1332	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils_pipeline.py	1178	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils_pipeline.py	1180	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils_pipeline.py	1228	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils_pipeline.py	1230	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils_pipeline.py	1368	# ---------------------------------------------------------------------------	COMMENT
MEDIUM	lightrag/utils_pipeline.py	1370	# ---------------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/base.py	1763	# ------------------------------------------------------------------	COMMENT
MEDIUM⚡	lightrag/base.py	1769	# ------------------------------------------------------------------	COMMENT
1515 more matches not shown…

Excessive Try-Catch Wrapping844 hits · 641 pts

Severity	File	Line	Snippet	Context
LOW	reproduce/Step_1_openai_compatible.py	50	except Exception as e:	CODE
LOW	reproduce/Step_0.py	41	except Exception as e:	CODE
MEDIUM	reproduce/Step_0.py	42	print(f"An error occurred while processing file {filename}: {e}")	CODE
LOW	reproduce/Step_0.py	54	except Exception as e:	CODE
MEDIUM	reproduce/Step_0.py	55	print(f"An error occurred while saving to the file {output_filename}: {e}")	CODE
LOW	reproduce/Step_1.py	19	except Exception as e:	CODE
LOW	reproduce/Step_3_openai_compatible.py	53	except Exception as e:	CODE
MEDIUM	reproduce/Step_3_openai_compatible.py	49	def process_query(query_text, rag_instance, query_param):	CODE
LOW	reproduce/Step_3.py	22	except Exception as e:	CODE
MEDIUM	reproduce/Step_3.py	18	def process_query(query_text, rag_instance, query_param):	CODE
LOW	lightrag/pipeline_metrics.py	97	except Exception as metric_error: # pragma: no cover - defensive	CODE
LOW	lightrag/pipeline_metrics.py	115	except Exception as metric_error: # pragma: no cover - defensive	CODE
LOW	lightrag/rerank.py	84	except Exception as e:	CODE
LOW	lightrag/rerank.py	624	except Exception as e:	CODE
LOW	lightrag/rerank.py	639	except Exception as e:	CODE
LOW	lightrag/rerank.py	654	except Exception as e:	CODE
LOW⚡	lightrag/llm_roles.py	262	except Exception as e:	CODE
LOW	lightrag/llm_roles.py	306	except Exception as e:	CODE
LOW	lightrag/llm_roles.py	381	except Exception:	CODE
LOW	lightrag/lightrag.py	16	except Exception: # pragma: no cover - optional dependency	CODE
LOW	lightrag/lightrag.py	2099	except Exception as e:	CODE
LOW	lightrag/lightrag.py	2134	except Exception as e:	CODE
LOW	lightrag/lightrag.py	2142	except Exception as e:	CODE
LOW	lightrag/lightrag.py	2221	except Exception as e:	CODE
LOW	lightrag/lightrag.py	2987	except Exception as bookkeeping_error:	CODE
LOW	lightrag/lightrag.py	3019	except Exception as ingress_error:	CODE
LOW	lightrag/lightrag.py	3049	except Exception as probe_error:	CODE
LOW	lightrag/lightrag.py	3120	except Exception as drain_error:	CODE
LOW	lightrag/lightrag.py	3360	except Exception as rollback_error:	CODE
LOW	lightrag/lightrag.py	3780	except Exception as e:	CODE
LOW	lightrag/lightrag.py	3928	except Exception as e:	CODE
LOW	lightrag/lightrag.py	3956	except Exception as e:	CODE
LOW	lightrag/lightrag.py	3989	except Exception as e:	CODE
LOW	lightrag/lightrag.py	4045	except Exception as e:	CODE
LOW	lightrag/lightrag.py	4138	except Exception as e:	CODE
LOW	lightrag/lightrag.py	4789	except Exception as e:	CODE
LOW	lightrag/lightrag.py	5257	except Exception as e:	CODE
LOW	lightrag/lightrag.py	5326	except Exception as e:	CODE
LOW	lightrag/lightrag.py	5463	except Exception as verification_error:	CODE
LOW	lightrag/lightrag.py	6209	except Exception as e:	CODE
LOW	lightrag/lightrag.py	6241	except Exception as e:	CODE
LOW	lightrag/lightrag.py	6378	except Exception as e:	CODE
LOW	lightrag/lightrag.py	6563	except Exception as e:	CODE
LOW	lightrag/lightrag.py	6601	except Exception as e:	CODE
LOW	lightrag/lightrag.py	6667	except Exception as e:	CODE
LOW	lightrag/lightrag.py	6680	except Exception as e:	CODE
LOW	lightrag/lightrag.py	6705	except Exception as e:	CODE
LOW	lightrag/lightrag.py	6718	except Exception as e:	CODE
LOW	lightrag/lightrag.py	7023	except Exception as cache_err:	CODE
LOW	lightrag/lightrag.py	7036	except Exception as e:	CODE
LOW	lightrag/lightrag.py	7093	except Exception as cache_collect_error:	CODE
LOW	lightrag/lightrag.py	7112	except Exception as status_write_error:	CODE
LOW	lightrag/lightrag.py	7206	except Exception as cache_delete_error:	CODE
LOW	lightrag/lightrag.py	7234	except Exception as e:	CODE
LOW	lightrag/lightrag.py	7267	except Exception as status_update_error:	CODE
LOW	lightrag/lightrag.py	7281	except Exception as e:	CODE
LOW	lightrag/lightrag.py	7300	except Exception as status_update_error:	CODE
LOW	lightrag/lightrag.py	7339	except Exception as ingress_error:	CODE
LOW	lightrag/lightrag.py	7362	except Exception as probe_error:	CODE
LOW	lightrag/lightrag.py	7401	except Exception as persistence_error:	CODE
784 more matches not shown…

Cross-File Repetition120 hits · 600 pts

Severity	File	Line	Snippet	Context
HIGH	lightrag/base.py	0	get multiple vector data by their ids (read-your-writes), preserving order. args: ids: list of unique identifiers return	STRING
HIGH	lightrag/kg/deprecated/chroma_impl.py	0	get multiple vector data by their ids (read-your-writes), preserving order. args: ids: list of unique identifiers return	STRING
HIGH	lightrag/kg/nano_vector_db_impl.py	0	get multiple vector data by their ids (read-your-writes), preserving order. args: ids: list of unique identifiers return	STRING
HIGH	lightrag/base.py	0	get all edges in the graph. returns: a list of all edges, where each edge is a dictionary of its properties	STRING
HIGH	lightrag/kg/networkx_impl.py	0	get all edges in the graph. returns: a list of all edges, where each edge is a dictionary of its properties	STRING
HIGH	lightrag/kg/mongo_impl.py	0	get all edges in the graph. returns: a list of all edges, where each edge is a dictionary of its properties	STRING
HIGH	lightrag/kg/memgraph_impl.py	0	get all edges in the graph. returns: a list of all edges, where each edge is a dictionary of its properties	STRING
HIGH	lightrag/kg/neo4j_impl.py	0	get all edges in the graph. returns: a list of all edges, where each edge is a dictionary of its properties	STRING
HIGH	lightrag/kg/qdrant_impl.py	0	buffered vector upsert waiting for embedding and/or bulk flush.	STRING
HIGH	lightrag/kg/mongo_impl.py	0	buffered vector upsert waiting for embedding and/or bulk flush.	STRING
HIGH	lightrag/kg/opensearch_impl.py	0	buffered vector upsert waiting for embedding and/or bulk flush.	STRING
HIGH	lightrag/kg/milvus_impl.py	0	buffered vector upsert waiting for embedding and/or bulk flush.	STRING
HIGH	lightrag/kg/qdrant_impl.py	0	discard buffered upserts/deletes (pipeline aborting on error).	STRING
HIGH	lightrag/kg/mongo_impl.py	0	discard buffered upserts/deletes (pipeline aborting on error).	STRING
HIGH	lightrag/kg/postgres_impl.py	0	discard buffered upserts/deletes (pipeline aborting on error).	STRING
HIGH	lightrag/kg/opensearch_impl.py	0	discard buffered upserts/deletes (pipeline aborting on error).	STRING
HIGH	lightrag/kg/milvus_impl.py	0	discard buffered upserts/deletes (pipeline aborting on error).	STRING
HIGH	lightrag/kg/qdrant_impl.py	0	buffer an entity vector delete by computing its hash id.	STRING
HIGH	lightrag/kg/mongo_impl.py	0	buffer an entity vector delete by computing its hash id.	STRING
HIGH	lightrag/kg/opensearch_impl.py	0	buffer an entity vector delete by computing its hash id.	STRING
HIGH	lightrag/kg/milvus_impl.py	0	buffer an entity vector delete by computing its hash id.	STRING
HIGH	lightrag/kg/qdrant_impl.py	0	get multiple vector data by their ids (read-your-writes), preserving order.	STRING
HIGH	lightrag/kg/mongo_impl.py	0	get multiple vector data by their ids (read-your-writes), preserving order.	STRING
HIGH	lightrag/kg/milvus_impl.py	0	get multiple vector data by their ids (read-your-writes), preserving order.	STRING
HIGH	lightrag/kg/networkx_impl.py	0	record ``fingerprint`` as the file pair this process now holds.	STRING
HIGH	lightrag/kg/nano_vector_db_impl.py	0	record ``fingerprint`` as the file pair this process now holds.	STRING
HIGH	lightrag/kg/faiss_impl.py	0	record ``fingerprint`` as the file pair this process now holds.	STRING
HIGH	lightrag/kg/networkx_impl.py	0	retrieve a connected subgraph of nodes where the label includes the specified `node_label`. args: node_label: label of t	STRING
HIGH	lightrag/kg/postgres_impl.py	0	retrieve a connected subgraph of nodes where the label includes the specified `node_label`. args: node_label: label of t	STRING
HIGH	lightrag/kg/memgraph_impl.py	0	retrieve a connected subgraph of nodes where the label includes the specified `node_label`. args: node_label: label of t	STRING
HIGH	lightrag/kg/neo4j_impl.py	0	retrieve a connected subgraph of nodes where the label includes the specified `node_label`. args: node_label: label of t	STRING
HIGH	lightrag/kg/networkx_impl.py	0	get all nodes in the graph. returns: a list of all nodes, where each node is a dictionary of its properties	STRING
HIGH	lightrag/kg/mongo_impl.py	0	get all nodes in the graph. returns: a list of all nodes, where each node is a dictionary of its properties	STRING
HIGH	lightrag/kg/postgres_impl.py	0	get all nodes in the graph. returns: a list of all nodes, where each node is a dictionary of its properties	STRING
HIGH	lightrag/kg/memgraph_impl.py	0	get all nodes in the graph. returns: a list of all nodes, where each node is a dictionary of its properties	STRING
HIGH	lightrag/kg/neo4j_impl.py	0	get all nodes in the graph. returns: a list of all nodes, where each node is a dictionary of its properties	STRING
HIGH	lightrag/kg/mongo_impl.py	0	check if the storage is empty for the current workspace and namespace returns: bool: true if storage is empty, false oth	STRING
HIGH	lightrag/kg/postgres_impl.py	0	check if the storage is empty for the current workspace and namespace returns: bool: true if storage is empty, false oth	STRING
HIGH	lightrag/kg/redis_impl.py	0	check if the storage is empty for the current workspace and namespace returns: bool: true if storage is empty, false oth	STRING
HIGH	lightrag/kg/mongo_impl.py	0	get counts of documents in each status for all documents returns: dictionary mapping status names to counts, including '	STRING
HIGH	lightrag/kg/postgres_impl.py	0	get counts of documents in each status for all documents returns: dictionary mapping status names to counts, including '	STRING
HIGH	lightrag/kg/json_doc_status_impl.py	0	get counts of documents in each status for all documents returns: dictionary mapping status names to counts, including '	STRING
HIGH	lightrag/kg/redis_impl.py	0	get counts of documents in each status for all documents returns: dictionary mapping status names to counts, including '	STRING
HIGH	lightrag/kg/mongo_impl.py	0	get document by file path args: file_path: the file path to search for returns: union[dict[str, any], none]: document da	STRING
HIGH	lightrag/kg/postgres_impl.py	0	get document by file path args: file_path: the file path to search for returns: union[dict[str, any], none]: document da	STRING
HIGH	lightrag/kg/redis_impl.py	0	get document by file path args: file_path: the file path to search for returns: union[dict[str, any], none]: document da	STRING
HIGH	lightrag/kg/json_doc_status_impl.py	0	get document by file path args: file_path: the file path to search for returns: union[dict[str, any], none]: document da	STRING
HIGH	lightrag/kg/mongo_impl.py	0	deterministic digest over candidate doc ids in stable sort order.	STRING
HIGH	lightrag/kg/postgres_impl.py	0	deterministic digest over candidate doc ids in stable sort order.	STRING
HIGH	lightrag/kg/opensearch_impl.py	0	deterministic digest over candidate doc ids in stable sort order.	STRING
HIGH	lightrag/kg/json_doc_status_impl.py	0	deterministic digest over candidate doc ids in stable sort order.	STRING
HIGH	lightrag/kg/redis_impl.py	0	deterministic digest over candidate doc ids in stable sort order.	STRING
HIGH	lightrag/kg/mongo_impl.py	0	get the total degree (sum of relationships) of two nodes. args: src_id: label of the source node tgt_id: label of the ta	STRING
HIGH	lightrag/kg/memgraph_impl.py	0	get the total degree (sum of relationships) of two nodes. args: src_id: label of the source node tgt_id: label of the ta	STRING
HIGH	lightrag/kg/neo4j_impl.py	0	get the total degree (sum of relationships) of two nodes. args: src_id: label of the source node tgt_id: label of the ta	STRING
HIGH	lightrag/kg/mongo_impl.py	0	check existence of multiple nodes in a single unwind query. args: node_ids: list of node ids to check. returns: set of n	STRING
HIGH	lightrag/kg/postgres_impl.py	0	check existence of multiple nodes in a single unwind query. args: node_ids: list of node ids to check. returns: set of n	STRING
HIGH	lightrag/kg/memgraph_impl.py	0	check existence of multiple nodes in a single unwind query. args: node_ids: list of node ids to check. returns: set of n	STRING
HIGH	lightrag/kg/neo4j_impl.py	0	check existence of multiple nodes in a single unwind query. args: node_ids: list of node ids to check. returns: set of n	STRING
HIGH	lightrag/kg/postgres_impl.py	0	get documents with pagination support args: status_filter: filter by document status, none for all statuses page: page n	STRING
60 more matches not shown…

Empty Error Handlers94 hits · 462 pts

Severity	File	Line	Snippet	Context
HIGH	lightrag/llm_roles.py	260	except asyncio.CancelledError:	CODE
HIGH	lightrag/lightrag.py	633	except RuntimeError:	CODE
HIGH	lightrag/lightrag.py	7922	except (asyncio.CancelledError, Exception):	CODE
HIGH	lightrag/utils.py	3424	except Exception:	CODE
HIGH	lightrag/utils.py	4683	except RuntimeError:	CODE
HIGH	lightrag/utils.py	6599	except Exception:	CODE
HIGH	lightrag/utils.py	6616	except Exception:	CODE
HIGH	lightrag/utils.py	86	except (ValueError, OSError):	CODE
HIGH	lightrag/utils.py	94	except (ValueError, OSError):	CODE
HIGH	lightrag/utils.py	3108	except RuntimeError:	CODE
HIGH	lightrag/utils.py	4697	except (RuntimeError, DeprecationWarning):	CODE
HIGH	lightrag/utils.py	2214	except asyncio.CancelledError:	CODE
HIGH	lightrag/utils.py	2253	except asyncio.CancelledError:	CODE
HIGH	lightrag/utils.py	2274	except Exception:	CODE
HIGH	lightrag/utils.py	2279	except Exception:	CODE
HIGH	lightrag/utils.py	2267	except Exception:	CODE
HIGH	lightrag/utils.py	1689	except asyncio.TimeoutError:	CODE
HIGH	lightrag/utils.py	1703	except asyncio.TimeoutError:	CODE
HIGH	lightrag/tools/clean_llm_query_cache.py	1235	except Exception:	CODE
HIGH	lightrag/tools/clean_llm_query_cache.py	1227	except Exception:	CODE
HIGH	lightrag/tools/chunk_tracking_repair.py	157	except (AttributeError, sqlite3.Error):	CODE
HIGH	lightrag/tools/rebuild_vdb.py	1196	except Exception:	CODE
HIGH	lightrag/tools/rebuild_vdb.py	1190	except Exception:	CODE
HIGH	lightrag/tools/migrate_llm_cache.py	1558	except Exception:	CODE
HIGH	lightrag/tools/migrate_llm_cache.py	1545	except Exception:	CODE
HIGH	lightrag/tools/migrate_llm_cache.py	1550	except Exception:	CODE
HIGH	lightrag/tools/migrate_graph_storage.py	1105	except Exception:	CODE
HIGH	lightrag/llm/gemini.py	533	except Exception:	CODE
HIGH	lightrag/parser/llm_bridge.py	100	except Exception:	CODE
HIGH	lightrag/parser/markdown/parser.py	587	except OSError:	CODE
HIGH	lightrag/parser/markdown/raw_cache.py	201	except OSError:	CODE
HIGH	lightrag/parser/external/mineru/ir_builder.py	533	except json.JSONDecodeError:	CODE
HIGH	lightrag/parser/external/mineru/client.py	516	except OSError:	CODE
HIGH	lightrag/parser/docx/numbering_resolver.py	269	except Exception:	CODE
HIGH	lightrag/parser/docx/numbering_resolver.py	318	except Exception:	CODE
HIGH	lightrag/parser/docx/parse_document.py	374	except Exception:	CODE
HIGH	lightrag/parser/docx/omml/ommlparser.py	216	except TypeError:	CODE
HIGH	lightrag/parser/docx/omml/ommlparser.py	556	except TypeError:	CODE
HIGH	lightrag/kg/shared_storage.py	1906	except Exception:	CODE
HIGH	lightrag/kg/shared_storage.py	4053	except Exception:	CODE
HIGH	lightrag/kg/shared_storage.py	4071	except Exception:	CODE
HIGH	lightrag/kg/shared_storage.py	290	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	4716	except ConflictError:	CODE
HIGH	lightrag/kg/opensearch_impl.py	7027	except OpenSearchException:	CODE
HIGH	lightrag/kg/opensearch_impl.py	7079	except OpenSearchException:	CODE
HIGH	lightrag/kg/opensearch_impl.py	7135	except OpenSearchException:	CODE
HIGH	lightrag/kg/opensearch_impl.py	4237	except NotFoundError:	CODE
HIGH	lightrag/kg/opensearch_impl.py	4990	except NotFoundError:	CODE
HIGH	lightrag/kg/opensearch_impl.py	5257	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	5372	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	6058	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	1222	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	2524	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	2639	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	4131	except OpenSearchException:	CODE
HIGH	lightrag/kg/opensearch_impl.py	4452	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	4663	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	5129	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	5174	except Exception:	CODE
HIGH	lightrag/kg/opensearch_impl.py	5893	except Exception:	CODE
34 more matches not shown…

Unused Imports410 hits · 375 pts

Severity	File	Line	Context
LOW	lightrag/pipeline_metrics.py	34	CODE
LOW	lightrag/rerank.py	1	CODE
LOW	lightrag/file_atomic.py	29	CODE
LOW	lightrag/addon_params.py	15	CODE
LOW	lightrag/table_markup.py	17	CODE
LOW	lightrag/llm_roles.py	11	CODE
LOW	lightrag/lightrag.py	1	CODE
LOW	lightrag/lightrag.py	215	CODE
LOW	lightrag/query_validation.py	3	CODE
LOW	lightrag/__init__.py	3	CODE
LOW	lightrag/types.py	1	CODE
LOW	lightrag/operate.py	1	CODE
LOW	lightrag/utils.py	1	CODE
LOW	lightrag/utils.py	431	CODE
LOW	lightrag/utils.py	431	CODE
LOW	lightrag/utils.py	431	CODE
LOW	lightrag/pipeline.py	12	CODE
LOW	lightrag/pipeline.py	133	CODE
LOW	lightrag/pipeline.py	133	CODE
LOW	lightrag/storage_migrations.py	14	CODE
LOW	lightrag/exceptions.py	1	CODE
LOW	lightrag/multimodal_context.py	62	CODE
LOW	lightrag/utils_graph.py	1	CODE
LOW	lightrag/prompt.py	1	CODE
LOW	lightrag/utils_pipeline.py	10	CODE
LOW	lightrag/namespace.py	1	CODE
LOW	lightrag/chunk_schema.py	24	CODE
LOW	lightrag/base.py	1	CODE
LOW	lightrag/prompt_multimodal.py	31	CODE
LOW	lightrag/tools/kg_integrity_repair.py	38	CODE
LOW	lightrag/tools/source_conflict_repair.py	92	CODE
LOW	lightrag/tools/source_conflict_repair.py	738	CODE
LOW	lightrag/tools/chunk_tracking_repair.py	19	CODE
LOW	lightrag/tools/migrate_graph_storage.py	67	CODE
LOW	lightrag/llm/_error_utils.py	14	CODE
LOW	lightrag/llm/gemini.py	10	CODE
LOW	lightrag/llm/_vision_utils.py	20	CODE
LOW	lightrag/llm/azure_openai.py	12	CODE
LOW	lightrag/llm/azure_openai.py	12	CODE
LOW	lightrag/llm/azure_openai.py	12	CODE
LOW	lightrag/parser/plugins.py	25	CODE
LOW	lightrag/parser/param_schema.py	30	CODE
LOW	lightrag/parser/native_dispatch.py	16	CODE
LOW	lightrag/parser/registry.py	16	CODE
LOW	lightrag/parser/registry.py	32	CODE
LOW	lightrag/parser/_html_table.py	13	CODE
LOW	lightrag/parser/llm_bridge.py	17	CODE
LOW	lightrag/parser/cli.py	20	CODE
LOW	lightrag/parser/_markdown.py	10	CODE
LOW	lightrag/parser/routing.py	1	CODE
LOW	lightrag/parser/debug.py	17	CODE
LOW	lightrag/parser/noop.py	18	CODE
LOW	lightrag/parser/native_base.py	15	CODE
LOW	lightrag/parser/native_base.py	33	CODE
LOW	lightrag/parser/exceptions.py	10	CODE
LOW	lightrag/parser/base.py	22	CODE
LOW	lightrag/parser/base.py	31	CODE
LOW	lightrag/parser/markdown/ir_builder.py	20	CODE
LOW	lightrag/parser/markdown/ir_builder.py	23	CODE
LOW	lightrag/parser/markdown/parser.py	41	CODE
350 more matches not shown…

Over-Commented Block482 hits · 323 pts

Severity	File	Line	Snippet	Context
LOW	docker-compose.podman.yml	1	# Podman-compatible compose file for LightRAG	COMMENT
LOW	docker-compose.podman.yml	21	tags:	COMMENT
LOW	README-id.md	161	# make dev installs the test toolchain plus the full offline stack	COMMENT
LOW	README-ja.md	161	# make dev はテストツールチェーンに加えて、完全なオフラインスタック	COMMENT
LOW	README.md	161		COMMENT
LOW	docker-entrypoint.sh	1	#!/bin/sh	COMMENT
LOW	docker-entrypoint.sh	21	# process can read/write them, covering bind-mounts/PVCs whose host content	COMMENT
LOW	requirements-offline-smart-heading.txt	1	# LightRAG Offline Dependencies - Native docx smart_heading (optional)	COMMENT
LOW	docker-compose.yml	41	# .env holds host paths so one file can serve both a source run and this	COMMENT
LOW	README-zh.md	161	# make dev 会安装测试工具链以及完整的离线依赖栈	COMMENT
LOW	lightrag/file_atomic.py	41		COMMENT
LOW	lightrag/lightrag.py	221	_RoleLLMMixin,	COMMENT
LOW	lightrag/lightrag.py	241	# On a graph storage that declares ``requires_single_writer`` (only	COMMENT
LOW	lightrag/lightrag.py	261	# manual operations, so queueing them is the point; the bound only keeps a	COMMENT
LOW	lightrag/lightrag.py	341	# ``_schedule_deferred_pipeline_drive``); a task held only by the loop's weak	COMMENT
LOW	lightrag/lightrag.py	661	# stranded mid-operation. The token is reset in a finally, so a nested or	COMMENT
LOW	lightrag/lightrag.py	1501	# when the caller hands us a partial ``addon_params['chunker']``	COMMENT
LOW	lightrag/lightrag.py	1581	# Restore the tokenizer object itself, the same way __post_init__ restores	COMMENT
LOW	lightrag/lightrag.py	2481	)	COMMENT
LOW	lightrag/lightrag.py	2641	)	COMMENT
LOW	lightrag/lightrag.py	2761	},	COMMENT
LOW	lightrag/lightrag.py	2921	# Patch mode AND resumed creates, not patch alone. Patch	COMMENT
LOW	lightrag/lightrag.py	3001	# The handoff decision consults the ingress mailbox: work that	COMMENT
LOW	lightrag/lightrag.py	3081	# cannot skip them: _exit_action keeps busy=True for a	COMMENT
LOW	lightrag/lightrag.py	3381	# every id first would have kept the sweep O(N) on the assumption that	COMMENT
LOW	lightrag/lightrag.py	3881	# placed beside the cache flush below would find nothing left. Commit	COMMENT
LOW	lightrag/lightrag.py	3961	# that takes the buffered DELETES with the upserts, and	COMMENT
LOW	lightrag/lightrag.py	4021	reachability* in the contract doc,	COMMENT
LOW	lightrag/lightrag.py	4121	# (``NetworkXStorage.index_done_callback``'s first block).	COMMENT
LOW	lightrag/lightrag.py	4141	):	COMMENT
LOW	lightrag/lightrag.py	4181	# the abort decision, and a second failing sibling would surface as a	COMMENT
LOW	lightrag/lightrag.py	4201	# ``use_llm_func_with_cache``; the lock and why an in-process one	COMMENT
LOW	lightrag/lightrag.py	4361	offline ``lightrag.tools.kg_integrity_repair`` audit can	COMMENT
LOW	lightrag/lightrag.py	4801	# (the hold ceiling's, a disconnected client's). The flush	COMMENT
LOW	lightrag/lightrag.py	5341	# are not on disk either -- recorded like every other failed	COMMENT
LOW	lightrag/lightrag.py	5501	return	COMMENT
LOW	lightrag/lightrag.py	6961	)	COMMENT
LOW	lightrag/lightrag.py	7141	#	COMMENT
LOW	lightrag/lightrag.py	7321	# so concurrent enqueues are permitted the whole time: an	COMMENT
LOW	lightrag/lightrag.py	7701	raise AdminWriteGateRefusedError(	COMMENT
LOW	lightrag/lightrag.py	7721	# the pipeline, and the "no other writer" clause above is exactly	COMMENT
LOW	lightrag/query_validation.py	1	"""Shared validation for query text entering the server and the core API."""	COMMENT
LOW	lightrag/query_validation.py	21	# minimum they should not. The cost of that is one retrieval that finds	COMMENT
LOW	lightrag/constants.py	121	# Bounds on any separator cascade, wherever it comes from. The recursive splitter	COMMENT
LOW	lightrag/constants.py	141	# CHUNK_SIZE default — heading-aligned paragraph merging needs more	COMMENT
LOW	lightrag/constants.py	161	# the ingestion path bounds: MAX_UPLOAD_SIZE bounds the compressed artifact on	COMMENT
LOW	lightrag/constants.py	181	# class — so the DOCX_* knobs below bound all three, enforced in the legacy	COMMENT
LOW	lightrag/constants.py	201	# above, these cap the bytes materialized into ``*.blocks.assets``: one image	COMMENT
LOW	lightrag/constants.py	221	# Overall wall-clock budget for downloading the result bundle from docling	COMMENT
LOW	lightrag/constants.py	241	# Native docx smart_heading (opt-in engine param) tunables. Each DEFAULT_*	COMMENT
LOW	lightrag/constants.py	261	"年,月,日,时,分,秒,个,人,只,条,次,项,天,号,元,角,件,名,台,种,倍,"	COMMENT
LOW	lightrag/constants.py	281	# anchor, which is why there is no longer an IMPRINT_SPACE_PREFIXES knob);	COMMENT
LOW	lightrag/constants.py	301	# rich physical outline naturally admits more candidates, so the effective	COMMENT
LOW	lightrag/constants.py	321	# CB4 per-sub-document gate: once the whole document clears the gate above,	COMMENT
LOW	lightrag/constants.py	341	# paragraphs (0 disables the auxiliary body-run break; the primary close	COMMENT
LOW	lightrag/constants.py	361	# Marker prefix for full_docs.content when format=lightrag.	COMMENT
LOW	lightrag/constants.py	381	# Reserved doc_status.metadata key recording how far this document's KG write	COMMENT
LOW	lightrag/constants.py	421	)	COMMENT
LOW	lightrag/constants.py	521	# Whether a doc_status backend missing a strict capability is a startup failure	COMMENT
LOW	lightrag/constants.py	541	# retries and ``/documents/scan`` bulk enqueues deliberately break through the	COMMENT
422 more matches not shown…

Modern AI Meta-Vocabulary102 hits · 313 pts

Severity	File	Line	Snippet	Context
MEDIUM	README-id.md	260	### Framework RAG Berbasis Graph yang Ringan	COMMENT
MEDIUM	README-ja.md	7	# 🚀 LightRAG: シンプルかつ高速な検索拡張生成（RAG）	COMMENT
MEDIUM	README-ja.md	260	### 軽量なグラフベース RAG フレームワーク	COMMENT
MEDIUM	README.md	261	### A Lightweight, Graph-Based RAG Framework	COMMENT
MEDIUM	README-zh.md	7	# 🚀 LightRAG: 简单且快速的检索增强生成（RAG）框架	COMMENT
MEDIUM	reproduce/Step_1_openai_compatible.py	77	# Initialize RAG instance	COMMENT
MEDIUM	reproduce/Step_1.py	42	# Initialize RAG instance	COMMENT
MEDIUM	lightrag/lightrag.py	5012	# `bypass` skips retrieval, so the RAG minimum does not apply to it —	COMMENT
MEDIUM	lightrag/lightrag.py	5135	# `bypass` skips retrieval, so the RAG minimum does not apply to it —	COMMENT
MEDIUM	lightrag/constants.py	41	# pushing an otherwise-valid chunk past the provider context window; over budget	COMMENT
MEDIUM	lightrag/constants.py	720	# over the embedding model's context limit after chunking. Independent from	COMMENT
MEDIUM	lightrag/operate.py	323	# embedding model's own context limit — not a real-world budget.	COMMENT
MEDIUM	lightrag/operate.py	4117	# an otherwise-valid chunk past the provider context window. When the	COMMENT
MEDIUM⚡	lightrag/pipeline.py	2275	# Pipeline orchestration	COMMENT
MEDIUM	lightrag/pipeline.py	184	# fully event-driven (``await get_document()``) and never polls.	COMMENT
MEDIUM	lightrag/pipeline.py	7245	# absolute legacy RAG-Anything/MinerU path, a ``..`` escape)	COMMENT
MEDIUM	lightrag/pipeline.py	7473	# it for their model's context window.	COMMENT
MEDIUM⚡	lightrag/tools/download_cache.py	158	"text-embedding-ada-002", # Legacy embedding model	CODE
MEDIUM⚡	lightrag/tools/download_cache.py	159	"text-embedding-3-small", # Small embedding model	CODE
MEDIUM⚡	lightrag/tools/download_cache.py	160	"text-embedding-3-large", # Large embedding model	CODE
MEDIUM	lightrag/tools/source_conflict_repair.py	762	# embedding model — full_docs is a plain KV, and reading it is what lets the	COMMENT
MEDIUM⚡	lightrag/tools/migrate_graph_storage.py	605	# Async orchestration — preconditions, write pipeline, compensation	COMMENT
MEDIUM	lightrag/llm/gemini.py	586	# model that burned the whole output budget on its reasoning trace is	COMMENT
MEDIUM	lightrag/llm/gemini.py	646	# A thinking model that spent its whole budget on the reasoning trace	COMMENT
MEDIUM	lightrag/llm/binding_options.py	632	# Whether the model may emit a hidden reasoning trace before its answer.	COMMENT
MEDIUM	lightrag/llm/ollama.py	398	# the reasoning trace). Raise like the OpenAI binding does,	COMMENT
MEDIUM	lightrag/parser/docx/parse_document.py	668	# (guardrails.is_visually_centered).	COMMENT
MEDIUM	lightrag/parser/docx/parse_document.py	1170	# --- smart path (pipeline + landing guardrails) ---------------	COMMENT
MEDIUM	lightrag/parser/docx/parse_document.py	1190	# Landing guardrails: any violation abandons the smart output for THIS	COMMENT
MEDIUM	lightrag/parser/docx/parse_document.py	1244	# three counts come from guardrails.plan_toc_output — the single visibility	COMMENT
MEDIUM	lightrag/parser/docx/smart_heading/features.py	341	#: is not visually centered (``guardrails.is_visually_centered``).	COMMENT
MEDIUM	lightrag/parser/docx/smart_heading/features.py	431	#: unit :func:`leading_pad_em` reports and ``guardrails.CENTER_MAX_LEADING_PAD_EM``	COMMENT
MEDIUM⚡	lightrag/parser/docx/smart_heading/heading_flow.py	2712	# whole-document orchestration	COMMENT
MEDIUM	lightrag/parser/docx/smart_heading/heading_flow.py	1844	#: - _Medical Graph RAG.docx's author line (96) absorbing its affiliation line	COMMENT
MEDIUM⚡	lightrag/parser/docx/smart_heading/guardrails.py	560	# Landing guardrails: canonicalization, I1/I2/I3 machine checks, TOC	COMMENT
MEDIUM	lightrag/parser/docx/smart_heading/guardrails.py	246	# dependency parser hallucinates sentence boundaries mid-word on short	COMMENT
MEDIUM	lightrag/parser/docx/smart_heading/title_block.py	1046	# candidate reuses single=True judge semantics (± context window; a	COMMENT
MEDIUM	lightrag/kg/mongo_impl.py	4510	# built under a different embedding model must NOT be	COMMENT
MEDIUM⚡	lightrag/kg/postgres_impl.py	2314	# with proper embedding model and dimension suffix for data isolation	STRING
MEDIUM	lightrag/kg/faiss_impl.py	1160	# the `is pdoc` identity check is defensive scaffolding: today the	COMMENT
MEDIUM	lightrag/kg/scan_job_store.py	227	# Timestamps, version, counters_dropped and the JSON scaffolding.	COMMENT
MEDIUM	lightrag/api/config.py	394	# RAG configuration	COMMENT
MEDIUM	lightrag/api/utils_api.py	714	# RAG Configuration	STRING
MEDIUM	lightrag/api/lightrag_server.py	737	# embedding model is configured. Without this, the provider's decorator	COMMENT
MEDIUM	lightrag/api/lightrag_server.py	1426	# ValueError inside a validator (the RAG query minimum, the non-empty	COMMENT
MEDIUM	lightrag/api/lightrag_server.py	1437	# A server with no configured embedding model cannot protect its vectors.	COMMENT
MEDIUM	lightrag/api/lightrag_server.py	2511	# Initialize RAG with unified configuration	COMMENT
MEDIUM	lightrag/api/lightrag_server.py	3003	# embedding model configuration binding/host address (if applicable)/model (if applicable)	COMMENT
MEDIUM	lightrag/api/routers/ollama_api.py	459	# Direct-LLM path: exempt from the RAG minimum, not from	COMMENT
MEDIUM	lightrag/api/routers/ollama_api.py	679	# the RAG branches normalize it themselves.	COMMENT
MEDIUM	lightrag/api/routers/query_routes.py	172	# Mode-independent: `bypass` is exempt from the RAG minimum below, not	COMMENT
MEDIUM	lightrag/evaluation/eval_rag_quality.py	19	# Specify custom RAG endpoint	STRING
MEDIUM⚡	lightrag/evaluation/eval_rag_quality.py	430	# all RAG responses from being generated at once when eval is slow	COMMENT
MEDIUM⚡	lightrag/evaluation/eval_rag_quality.py	435	# Stage 1: Generate RAG response	COMMENT
MEDIUM	lightrag/evaluation/eval_rag_quality.py	542	# down as if the RAG answer itself were bad.	COMMENT
MEDIUM	lightrag/evaluation/eval_rag_quality.py	589	# Stage 1: RAG generation - allow x2 concurrency to keep evaluation fed	COMMENT
MEDIUM	lightrag/evaluation/eval_rag_quality.py	615	max_connections=(max_async + 1) * 2, # Allow buffer for RAG stage	CODE
MEDIUM	lightrag/evaluation/eval_rag_quality.py	808	# Every case failed (e.g. an all-NaN RAGAS result, or every RAG	COMMENT
MEDIUM	lightrag/evaluation/eval_rag_quality.py	996	# Specify custom RAG endpoint	COMMENT
MEDIUM	…ation/sample_documents/05_evaluation_and_deployment.md	1	# RAG Evaluation Metrics and Deployment	COMMENT
42 more matches not shown…

Deep Nesting403 hits · 276 pts

Severity	File	Line	Context
LOW	reproduce/Step_0.py	7	CODE
LOW	reproduce/Step_3_openai_compatible.py	57	CODE
LOW	reproduce/Step_3.py	26	CODE
LOW	lightrag/rerank.py	36	CODE
LOW	lightrag/rerank.py	165	CODE
LOW	lightrag/rerank.py	240	CODE
LOW	lightrag/table_markup.py	133	CODE
LOW	lightrag/llm_roles.py	309	CODE
LOW	lightrag/lightrag.py	1638	CODE
LOW	lightrag/lightrag.py	2102	CODE
LOW	lightrag/lightrag.py	2163	CODE
LOW	lightrag/lightrag.py	2394	CODE
LOW	lightrag/lightrag.py	3692	CODE
LOW	lightrag/lightrag.py	4340	CODE
LOW	lightrag/lightrag.py	5114	CODE
LOW	lightrag/lightrag.py	6265	CODE
LOW	lightrag/lightrag.py	6727	CODE
LOW	lightrag/operate.py	249	CODE
LOW	lightrag/operate.py	372	CODE
LOW	lightrag/operate.py	1102	CODE
LOW	lightrag/operate.py	1508	CODE
LOW	lightrag/operate.py	1755	CODE
LOW	lightrag/operate.py	2027	CODE
LOW	lightrag/operate.py	2429	CODE
LOW	lightrag/operate.py	2782	CODE
LOW	lightrag/operate.py	3514	CODE
LOW	lightrag/operate.py	3942	CODE
LOW	lightrag/operate.py	5051	CODE
LOW	lightrag/operate.py	5280	CODE
LOW	lightrag/operate.py	6350	CODE
LOW	lightrag/operate.py	6621	CODE
LOW	lightrag/operate.py	4094	CODE
LOW	lightrag/utils.py	156	CODE
LOW	lightrag/utils.py	1193	CODE
LOW	lightrag/utils.py	4265	CODE
LOW	lightrag/utils.py	4581	CODE
LOW	lightrag/utils.py	4707	CODE
LOW	lightrag/utils.py	5515	CODE
LOW	lightrag/utils.py	6458	CODE
LOW	lightrag/utils.py	6486	CODE
LOW	lightrag/utils.py	6724	CODE
LOW	lightrag/utils.py	6924	CODE
LOW	lightrag/utils.py	7055	CODE
LOW	lightrag/utils.py	7183	CODE
LOW	lightrag/utils.py	7562	CODE
LOW	lightrag/utils.py	1240	CODE
LOW	lightrag/utils.py	3707	CODE
LOW	lightrag/utils.py	3832	CODE
LOW	lightrag/utils.py	3917	CODE
LOW	lightrag/utils.py	1451	CODE
LOW	lightrag/utils.py	1550	CODE
LOW	lightrag/utils.py	1655	CODE
LOW	lightrag/utils.py	1813	CODE
LOW	lightrag/utils.py	1912	CODE
LOW	lightrag/pipeline.py	740	CODE
LOW	lightrag/pipeline.py	1724	CODE
LOW	lightrag/pipeline.py	2507	CODE
LOW	lightrag/pipeline.py	2913	CODE
LOW	lightrag/pipeline.py	3924	CODE
LOW	lightrag/pipeline.py	4409	CODE
343 more matches not shown…

Docstring Block Structure50 hits · 250 pts

Severity	File	Line	Snippet	Context
HIGH	lightrag/lightrag.py	572	Drive an async coroutine to completion from a synchronous wrapper. The synchronous wrappers (``insert``, ``query``,	STRING
HIGH	lightrag/utils.py	2438	Execute function with enhanced priority-based concurrency control and timeout handling Args:	STRING
HIGH	lightrag/utils.py	7878	Validate a workspace name used to build per-workspace directories. File-based storages place their data in a subdir	STRING
HIGH	lightrag/utils.py	8179	Reject a node/edge attribute mapping no graph backend could store. Args: attributes: Attribute mapping abou	STRING
HIGH	lightrag/utils.py	8201	Reject attribute names a backend would read as something other than a name. The interpretation rule, not the seri	STRING
HIGH	lightrag/utils.py	8251	Reject attribute names or values XML cannot encode. For a GraphML-backed store. Names are checked as well as values	STRING
HIGH	lightrag/utils.py	8278	Reject attribute values no graph backend can store. See ``graph_attribute_value_rejection`` for the rules and `	STRING
HIGH	lightrag/pipeline.py	753	Pipeline for Processing Documents 1. Validate ids if provided or generate MD5 hash IDs and remove dupl	STRING
HIGH	lightrag/utils_graph.py	65	Return data reduced to well-typed, storable graph attributes. Two call shapes, because the two families of caller	STRING
HIGH	lightrag/tools/clean_llm_query_cache.py	252	Initialize storage instance with fallback to config.ini and defaults Args: storage_name: Storage im	STRING
HIGH	lightrag/tools/migrate_llm_cache.py	289	Initialize storage instance with fallback to config.ini and defaults Args: storage_name: Storage im	STRING
HIGH	lightrag/llm/jina.py	85	Generate embeddings for a list of texts using Jina AI's API. Args: texts: List of texts to embed. m	STRING
HIGH	lightrag/llm/voyageai.py	64	Generate embeddings for a list of texts using VoyageAI's API. Args: texts: List of texts to embed.	STRING
HIGH	lightrag/llm/gemini.py	331	Complete a prompt using Gemini's API with Chain of Thought (COT) support. This function supports automatic int	STRING
HIGH	lightrag/llm/gemini.py	742	Generate embeddings for a list of texts using Gemini's API. This function uses Google's Gemini embedding model to g	STRING
HIGH	lightrag/llm/openai.py	323	Complete a prompt using OpenAI's API with caching support and Chain of Thought (COT) integration. This function sup	STRING
HIGH	lightrag/llm/openai.py	1070	Generate embeddings for a list of texts using OpenAI's API with automatic text truncation. This function supports b	STRING
HIGH	lightrag/parser/docx/utils.py	96	Create Gemini client for AI Studio or Vertex AI. Supports two modes: - AI Studio (default): Uses GOOGLE_AP	STRING
HIGH	lightrag/parser/docx/utils.py	173	Create OpenAI client with optional custom base URL. Environment variables: - OPENAI_API_KEY: Required API	STRING
HIGH	lightrag/parser/docx/table_extractor.py	250	Extract table to 2D string array with metadata (paraIds, header info). Vertical merge behavior:	STRING
HIGH	lightrag/kg/postgres_impl.py	790	Execute a database operation with automatic retry for transient failures. Args: operation:	STRING
HIGH	lightrag/kg/memgraph_impl.py	135	Check if a node exists in the graph. Args: node_id: The ID of the node to check.	STRING
HIGH	lightrag/kg/memgraph_impl.py	175	Check if an edge exists between two nodes in the graph. Args: source_node_id: The ID of th	STRING
HIGH	lightrag/kg/memgraph_impl.py	223	Get node by its label identifier, return only node properties Args: node_id: The node label to look	STRING
HIGH	lightrag/kg/memgraph_impl.py	278	Get the degree (number of relationships) of a node with the given label. If multiple nodes have the same label,	STRING
HIGH	lightrag/kg/memgraph_impl.py	396	Retrieves all edges (relationships) for a particular node identified by its label. Args: source_nod	STRING
HIGH	lightrag/kg/memgraph_impl.py	471	Get edge properties between two nodes. Args: source_node_id: Label of the source node t	STRING
HIGH	lightrag/kg/neo4j_impl.py	487	Check if a node with the given label exists in the database Args: node_id: Label of the no	STRING
HIGH	lightrag/kg/neo4j_impl.py	521	Check if an edge exists between two nodes Args: source_node_id: Label of the source node	STRING
HIGH	lightrag/kg/neo4j_impl.py	563	Get node by its label identifier, return only node properties Args: node_id: The node label to look	STRING
HIGH	lightrag/kg/neo4j_impl.py	654	Get the degree (number of relationships) of a node with the given label. If multiple nodes have the same label,	STRING
HIGH	lightrag/kg/neo4j_impl.py	791	Get edge properties between two nodes. Args: source_node_id: Label of the source node t	STRING
HIGH	lightrag/kg/neo4j_impl.py	925	Retrieves all edges (relationships) for a particular node identified by its label. Args: source_nod	STRING
HIGH	lightrag/api/auth.py	186	Validate JWT token Args: token: JWT token Returns: dict: Dictionary c	STRING
HIGH	lightrag/api/routers/graph_routes.py	881	Delete an entity and all its relationships from the knowledge graph. Args: request (Delete	STRING
HIGH	lightrag/api/routers/graph_routes.py	923	Delete a relationship between two entities from the knowledge graph. Args: request (Delete	STRING
HIGH	lightrag/api/routers/query_routes.py	519	Comprehensive RAG query endpoint with non-streaming response. Parameter "stream" is ignored. **Query M	STRING
HIGH	lightrag/api/routers/query_routes.py	838	Advanced RAG query endpoint with flexible streaming response. This endpoint provides the most flexible	STRING
HIGH	lightrag/api/routers/query_routes.py	1424	Advanced data retrieval endpoint for structured RAG analysis. This endpoint provides raw retrieval res	STRING
HIGH	lightrag/api/routers/document_routes.py	266	Validate an uploaded filename and return it unchanged when safe. Uploaded filenames are document identifiers a	STRING
HIGH	lightrag/api/routers/document_routes.py	5232	Upload a file to the input directory and index it. This API endpoint accepts a file through an HTTP PO	STRING
HIGH	lightrag/api/routers/document_routes.py	5568	Insert text into the RAG system. This endpoint allows you to insert text data into the RAG system for	STRING
HIGH	lightrag/api/routers/document_routes.py	5700	Insert multiple texts into the RAG system. This endpoint allows you to insert multiple text entries in	STRING
HIGH	lightrag/api/routers/document_routes.py	6507	Delete documents and all their associated data by their IDs using background processing. Deletes speci	STRING
HIGH	lightrag/api/routers/document_routes.py	6630	Get the processing status of documents by tracking ID. This endpoint retrieves all documents associate	STRING
HIGH	lightrag/api/routers/document_routes.py	6706	Get documents with pagination support. This endpoint retrieves documents with pagination, filtering, a	STRING
HIGH	lightrag/evaluation/eval_rag_quality.py	306	Generate RAG response by calling LightRAG API. Args: question: The user query.	STRING
HIGH	lightrag/chunker/paragraph_semantic.py	2069	Paragraph Semantic Chunking — the ``chunking="P"`` strategy. Reads structured blocks from a ``.blocks.jsonl`` sidec	STRING
HIGH	lightrag/chunker/recursive_character.py	444	Recursive character splitter — the ``"R"`` chunking strategy. Args: tokenizer: LightRAG tokenizer; used as	STRING
HIGH	tests/api/test_lightrag_ollama_chat.py	147	Send an HTTP request with retry mechanism Args: url: Request URL data: Request data stream:	STRING

Magic Placeholder Names37 hits · 195 pts

Severity	File	Line	Snippet	Context
HIGH	tests/setup/test_misc.py	297	"LLM_BINDING_API_KEY=your_api_key",	STRING
HIGH	tests/setup/test_misc.py	302	"EMBEDDING_BINDING_API_KEY=your_api_key",	STRING
HIGH	docs/LightRAG-API-Server.md	149	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/LightRAG-API-Server.md	155	# EMBEDDING_BINDING_API_KEY=your_api_key	COMMENT
HIGH	docs/LightRAG-API-Server.md	166	# LLM_BINDING_API_KEY=your_api_key	COMMENT
HIGH	docs/LightRAG-API-Server.md	174	# EMBEDDING_BINDING_API_KEY=your_api_key	COMMENT
HIGH	docs/LightRAG-API-Server.md	311	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/LightRAG-API-Server.md	322	EMBEDDING_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/LightRAG-API-Server.md	833	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/LightRAG-API-Server.md	1132	LLM_BINDING_API_KEY=your-api-key	CODE
HIGH	docs/ParserServiceDeployment.md	48	"api_key": "your_api_key",	CODE
HIGH	docs/ProgramingWithCore.md	1233	export OPENAI_API_KEY=your-api-key	CODE
HIGH	docs/ProgramingWithCore.md	1247	OPENAI_API_KEY=your-api-key \	CODE
HIGH	docs/ParserServiceDeployment-zh.md	48	"api_key": "your_api_key",	CODE
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	26	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	132	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	213	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	230	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	343	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/LightRAG-API-Server-zh.md	149	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/LightRAG-API-Server-zh.md	155	# EMBEDDING_BINDING_API_KEY=your_api_key	COMMENT
HIGH	docs/LightRAG-API-Server-zh.md	166	# LLM_BINDING_API_KEY=your_api_key	COMMENT
HIGH	docs/LightRAG-API-Server-zh.md	174	# EMBEDDING_BINDING_API_KEY=your_api_key	COMMENT
HIGH	docs/LightRAG-API-Server-zh.md	311	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/LightRAG-API-Server-zh.md	322	EMBEDDING_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/LightRAG-API-Server-zh.md	833	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/LightRAG-API-Server-zh.md	1132	LLM_BINDING_API_KEY=your-api-key	CODE
HIGH	docs/RoleSpecificLLMConfiguration.md	26	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/RoleSpecificLLMConfiguration.md	132	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/RoleSpecificLLMConfiguration.md	213	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/RoleSpecificLLMConfiguration.md	230	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	docs/RoleSpecificLLMConfiguration.md	343	LLM_BINDING_API_KEY=your_api_key	CODE
HIGH	examples/lightrag_gemini_postgres_demo.py	28	GEMINI_API_KEY=your-api-key	STRING
HIGH⚡	examples/lightrag_gemini_demo.py	37	"Please set it with: export GEMINI_API_KEY='your-api-key'"	CODE
HIGH	examples/lightrag_openai_opensearch_graph_demo.py	23	OPENAI_API_KEY=your-api-key	STRING
HIGH	…s/unofficial-sample/lightrag_llamaindex_direct_demo.py	29	OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "your-api-key-here")	CODE
HIGH⚡	examples/unofficial-sample/lightrag_cloudflare_demo.py	20	cloudflare_api_key = "YOUR_API_KEY"	CODE

Redundant / Tautological Comments136 hits · 185 pts

Severity	File	Line	Snippet	Context
LOW	docker-build-push.sh	38	# Check if buildx builder exists, create if not	COMMENT
LOW	lightrag/lightrag.py	5223	# Check if query_result is None	COMMENT
LOW	lightrag/operate.py	3079	# Check if this is a placeholder record	COMMENT
LOW	lightrag/operate.py	3999	# Check if JSON structured output mode is enabled	COMMENT
LOW	lightrag/operate.py	4581	# Check if any task raised an exception and ensure all exceptions are retrieved.	COMMENT
LOW	lightrag/operate.py	4996	# Check if pre-defined keywords are already provided	COMMENT
LOW	lightrag/operate.py	6714	# Check if any relations still have chunks after deduplication	COMMENT
LOW	lightrag/utils.py	311	# Check if the resolved path is within the base directory	COMMENT
LOW	lightrag/utils.py	520	# Check if record has the required attributes for an access log	COMMENT
LOW	lightrag/utils.py	721	# Check if func is already an EmbeddingFunc instance and unwrap it	COMMENT
LOW	lightrag/utils.py	778	# Check if user provided embedding_dim parameter	COMMENT
LOW	lightrag/utils.py	802	# Check if underlying function supports max_token_size and inject if not provided	COMMENT
LOW	lightrag/utils.py	1580	# Check if task was cancelled before worker started	COMMENT
LOW	lightrag/utils.py	4515	# Check if we already have identical content cached	COMMENT
LOW	lightrag/utils.py	6709	# Check if there are still unused chunks	COMMENT
LOW	lightrag/utils.py	6981	# Check if results are in the new index-based format	COMMENT
LOW	lightrag/pipeline.py	2975	# Check if corresponding content exists in full_docs. Strict where	COMMENT
LOW	lightrag/pipeline.py	2984	# Check if this is a failed document that should be preserved	COMMENT
LOW	lightrag/storage_migrations.py	35	# Check if migration is needed:	COMMENT
LOW	lightrag/storage_migrations.py	55	# Check if full_entities and full_relations are empty	COMMENT
LOW	lightrag/utils_graph.py	619	# Check if the entity exists	COMMENT
LOW	lightrag/utils_graph.py	819	# Check if the relation exists	COMMENT
LOW	lightrag/utils_graph.py	2007	# Check if storage has existing data	COMMENT
LOW	lightrag/utils_graph.py	2375	# Check if the normalized entity already exists.	COMMENT
LOW	lightrag/utils_graph.py	2560	# Check if both entities exist	COMMENT
LOW	lightrag/utils_graph.py	2569	# Check if relation already exists	COMMENT
LOW	lightrag/base.py	368	# Check if model_name exists (model_name is optional in EmbeddingFunc)	COMMENT
LOW	lightrag/tools/clean_llm_query_cache.py	207	# Check if config.ini has configuration	COMMENT
LOW	lightrag/tools/clean_llm_query_cache.py	971	# Check if choice is valid	COMMENT
LOW	lightrag/tools/clean_llm_query_cache.py	1069	# Check if user cancelled	COMMENT
LOW	lightrag/tools/clean_llm_query_cache.py	1131	# Check if there are any records to delete	COMMENT
LOW	lightrag/tools/download_cache.py	131	# Check if TIKTOKEN_CACHE_DIR is already set in environment	COMMENT
LOW	lightrag/tools/check_initialization.py	101	# Print results	COMMENT
LOW⚡	lightrag/tools/migrate_llm_cache.py	237	# Check if storage requires configuration	COMMENT
LOW⚡	lightrag/tools/migrate_llm_cache.py	244	# Check if has environment variables	COMMENT
LOW⚡	lightrag/tools/migrate_llm_cache.py	249	# Check if has config.ini configuration	COMMENT
LOW	lightrag/tools/migrate_llm_cache.py	216	# Check if config.ini has configuration	COMMENT
LOW	lightrag/tools/migrate_llm_cache.py	1068	# Check if choice is valid	COMMENT
LOW	lightrag/tools/migrate_llm_cache.py	1438	# Check if user cancelled (setup_storage returns None for all fields)	COMMENT
LOW	lightrag/tools/migrate_llm_cache.py	1442	# Check if there are at least 2 storage types available	COMMENT
LOW	lightrag/llm/jina.py	28	# Check if the error response is HTML (common for 502, 503, etc.)	COMMENT
LOW	lightrag/llm/gemini.py	284	# Check if this part is thought content using the 'thought' attribute	COMMENT
LOW	lightrag/llm/binding_options.py	296	# Check if this is a dataclass and use dataclass fields	COMMENT
LOW⚡	lightrag/llm/openai.py	589	# Check if this chunk has usage information (final chunk)	COMMENT
LOW⚡	lightrag/llm/openai.py	596	# Check if choices exists and is not empty	COMMENT
LOW⚡	lightrag/llm/openai.py	604	# Check if delta exists	COMMENT
LOW	lightrag/llm/openai.py	53	# Check if required Langfuse environment variables are set	COMMENT
LOW	lightrag/llm/openai.py	820	# Check if we should include reasoning content	COMMENT
LOW	lightrag/parser/docx/utils.py	373	# Check if it mentions billing which indicates permanent quota issue	COMMENT
LOW	lightrag/kg/qdrant_impl.py	369	# Check if legacy collection has workspace_id to determine migration strategy	COMMENT
LOW	lightrag/kg/qdrant_impl.py	480	# Check if we've reached the end	COMMENT
LOW⚡	lightrag/kg/networkx_impl.py	1197	# Add neighbors to the queue with their degrees	COMMENT
LOW⚡	lightrag/kg/networkx_impl.py	1202	# Check if there are unexplored neighbors (skipped due to depth limit)	COMMENT
LOW⚡	lightrag/kg/networkx_impl.py	1210	# Check if we've reached max_nodes	COMMENT
LOW⚡	lightrag/kg/networkx_impl.py	1219	# Check if graph is truncated - either due to max_nodes limit or depth limit	COMMENT
LOW	lightrag/kg/networkx_impl.py	1135	# Check if graph is truncated	COMMENT
LOW	lightrag/kg/networkx_impl.py	1146	# Check if node exists	COMMENT
LOW⚡	lightrag/kg/mongo_impl.py	4075	# Check if we're using MongoDB Atlas (has search index capabilities)	COMMENT
LOW⚡	lightrag/kg/mongo_impl.py	4079	# Check if we need to rebuild the index	COMMENT
LOW⚡	lightrag/kg/mongo_impl.py	4085	# Check if index exists and drop it	COMMENT
76 more matches not shown…

Self-Referential Comments46 hits · 136 pts

Severity	File	Line	Snippet	Context
MEDIUM	reproduce/Step_1_openai_compatible.py	77	# Initialize RAG instance	COMMENT
MEDIUM	reproduce/Step_1.py	42	# Initialize RAG instance	COMMENT
MEDIUM⚡	lightrag/lightrag.py	1789	# Create a NEW EmbeddingFunc instance with the wrapped func to avoid mutating the caller's object	COMMENT
MEDIUM	lightrag/lightrag.py	5020	# Create a copy of param to avoid modifying the original	COMMENT
MEDIUM	lightrag/operate.py	6935	# Create a preliminary system prompt with empty content_data to calculate overhead.	COMMENT
MEDIUM	lightrag/utils.py	7764	# Create a list of (file_path, count, first_index) tuples	COMMENT
MEDIUM	lightrag/pipeline.py	1431	# Create a new record with unique ID for this duplicate attempt	COMMENT
MEDIUM	lightrag/tools/migrate_llm_cache.py	716	# Create a snapshot of matching items while holding the lock	COMMENT
MEDIUM	lightrag/llm/openai.py	229	# Create a merged config dict with precedence: explicit params > client_configs	COMMENT
MEDIUM	lightrag/llm/openai.py	263	# Create a merged config dict with precedence: explicit params > client_configs > defaults	COMMENT
MEDIUM	lightrag/llm/openai.py	443	# Create the OpenAI client (supports both OpenAI and Azure)	COMMENT
MEDIUM	lightrag/llm/openai.py	1166	# Create the OpenAI client (supports both OpenAI and Azure)	COMMENT
MEDIUM	lightrag/llm/bedrock.py	348	# Create a session that will be used throughout the streaming process	COMMENT
MEDIUM	lightrag/llm/bedrock.py	359	# Define the generator function that will manage the client lifecycle	COMMENT
MEDIUM⚡	lightrag/kg/mongo_impl.py	4090	# Create the improved search index (async, no waiting)	COMMENT
MEDIUM	lightrag/kg/mongo_impl.py	534	# Create a copy of v for $set operation, excluding create_time to avoid conflicts	COMMENT
MEDIUM	lightrag/kg/mongo_impl.py	4664	# Define the aggregation pipeline with the converted query vector	COMMENT
MEDIUM	lightrag/kg/postgres_impl.py	2171	# Define the field changes needed	COMMENT
MEDIUM	lightrag/kg/faiss_impl.py	159	# Create an empty Faiss index for inner product (useful for normalized vectors = cosine similarity).	COMMENT
MEDIUM	lightrag/kg/shared_storage.py	63	# Define a direct print function for critical logs that must be visible in all processes	COMMENT
MEDIUM	lightrag/kg/shared_storage.py	1672	# Create a shared list object for history_messages	COMMENT
MEDIUM	lightrag/kg/shared_storage.py	3725	# Create a simple mutable object to store boolean value for compatibility with mutiprocess	COMMENT
MEDIUM	lightrag/api/run_with_gunicorn.py	147	# Define a custom application class that loads our config	COMMENT
MEDIUM	lightrag/api/run_with_gunicorn.py	277	# Create the application	COMMENT
MEDIUM	lightrag/api/lightrag_server.py	1047	# Create the EmbeddingFunc instance (now returns complete EmbeddingFunc with max_token_size)	COMMENT
MEDIUM	lightrag/api/routers/ollama_api.py	240	# Create an instance of the model	COMMENT
MEDIUM	lightrag/api/routers/query_routes.py	623	# Create a mapping from reference_id to chunk content	COMMENT
MEDIUM	lightrag/api/routers/document_routes.py	4730	# Create the bounded job record BEFORE publishing the manual intent	COMMENT
MEDIUM	tests/kg/test_graph_storage.py	152	# Initialize the storage instance	COMMENT
MEDIUM	tests/kg/postgres_impl/test_postgres_index_name.py	84	# Create a table name that results in exactly 63 bytes	COMMENT
MEDIUM	tests/chunker/test_rerank_chunking.py	90	# Create a very long document that exceeds character limit	COMMENT
MEDIUM	examples/graph_visual_with_html.py	15	# Create a Pyvis network	COMMENT
MEDIUM	examples/lightrag_openai_compatible_demo.py	150	# Initialize RAG instance	COMMENT
MEDIUM	examples/lightrag_openai_mongodb_graph_demo.py	72	# Initialize RAG instance	COMMENT
MEDIUM	examples/lightrag_openai_demo.py	119	# Initialize RAG instance	COMMENT
MEDIUM	examples/lightrag_ollama_demo.py	139	# Initialize RAG instance	COMMENT
MEDIUM	examples/graph_visual_with_neo4j.py	159	# Create a Neo4j driver	STRING
MEDIUM	…mples/unofficial-sample/lightrag_embedding_prefixes.py	156	# Initialize RAG instance	COMMENT
MEDIUM	…/unofficial-sample/lightrag_llamaindex_litellm_demo.py	103	# Initialize RAG instance	COMMENT
MEDIUM	…cial-sample/lightrag_openai_neo4j_milvus_redis_demo.py	73	# Initialize RAG instance	COMMENT
MEDIUM	…s/unofficial-sample/lightrag_llamaindex_direct_demo.py	101	# Initialize RAG instance	COMMENT
MEDIUM	…ficial-sample/lightrag_llamaindex_litellm_opik_demo.py	114	# Initialize RAG instance	COMMENT
MEDIUM	examples/unofficial-sample/lightrag_cloudflare_demo.py	251	# Initialize RAG instance	COMMENT
MEDIUM	examples/unofficial-sample/lightrag_lmdeploy_demo.py	69	# Initialize RAG instance	COMMENT
MEDIUM	examples/unofficial-sample/lightrag_nvidia_demo.py	123	# Initialize RAG instance	COMMENT
MEDIUM	scripts/setup/apple-container.sh	272	# This file is a copy of the user's .env (real API keys) — keep it private.	COMMENT

Cross-Language Confusion24 hits · 124 pts

Severity	File	Line	Snippet	Context
HIGH	lightrag/utils.py	7371	``{"chunk_ids": null}``), which mean UNKNOWN. Only in the UNKNOWN case may a	STRING
HIGH	lightrag/utils.py	8141	``SET n += {k: null}`` silently deletes the property.	STRING
HIGH	lightrag/parser/docx/parser.py	149	# ``positions: [{"type": "paraid", "range": null}]``.	COMMENT
HIGH	lightrag/parser/docx/smart_heading/title_block.py	1129	- If false: set all six text fields to null, and classify EVERY index — {indices} — into exactly one of "headings" (a re	CODE
HIGH	lightrag/parser/docx/smart_heading/title_block.py	1132	{{"is_title_block": true\|false, "main_title": string\|null, "sub_title": string\|null, "doc_number": string\|null, "classif	CODE
HIGH	lightrag/kg/pgtable_impl.py	753	properties = lightrag_graph_nodes.properties \|\| EXCLUDED.properties,	CODE
HIGH	lightrag/kg/pgtable_impl.py	1573	properties = lightrag_graph_nodes.properties \|\| EXCLUDED.properties,	CODE
HIGH	lightrag/kg/mongo_impl.py	1394	# every doc with a real (non-null, existing) value.	COMMENT
HIGH	lightrag/kg/postgres_impl.py	7236	" $1::text \|\| E'\\x01' \|\|"	CODE
HIGH	lightrag/kg/postgres_impl.py	5996	CURRENT_TIMESTAMP) sort FIRST and encode as ``[null, id]`` so the	STRING
HIGH	lightrag/api/lightrag_server.py	148	if (!data \|\| data.type !== 'lightrag:set-docs-theme') return;	CODE
HIGH	lightrag/api/routers/graph_routes.py	427	"merge_error": null,	STRING
HIGH	lightrag/api/routers/graph_routes.py	429	"target_entity": null,	STRING
HIGH	lightrag/api/routers/graph_routes.py	455	"merge_error": null,	STRING
HIGH⚡	…kg/redis_impl/test_redis_kv_create_time_integration.py	356	# pattern must REFUSE (tail position, float, null, quoted) plus non-JSON.	COMMENT
HIGH⚡	…kg/redis_impl/test_redis_kv_create_time_integration.py	364	'{"create_time": null}',	CODE
HIGH⚡	tests/kg/postgres_impl/test_pg_scheduling_pages.py	199	the cursor encodes [null, id] instead of failing closed — a row-value	STRING
HIGH	…sts/kg/postgres_impl/test_postgres_cypher_injection.py	202	"formula": "x < 5 && y > 3",	CODE
HIGH	…sts/kg/postgres_impl/test_postgres_cypher_injection.py	213	assert '`formula`: "x < 5 && y > 3"' in call["sql"]	CODE
HIGH	…s/kg/postgres_impl/test_postgres_upsert_edge_cypher.py	183	assert "$1::text \|\| E'\\x01' \|\|" in lock_sql	CODE
HIGH	tests/kg/neo4j_impl/test_search_labels_sanitize.py	34	("foo && bar", "foo bar"),	CODE
HIGH⚡	tests/kg/pgtable_impl/test_pgtable_graph_storage.py	350	assert "lightrag_graph_nodes.properties \|\| EXCLUDED.properties" in sql	CODE
HIGH⚡	tests/kg/pgtable_impl/test_pgtable_graph_storage.py	366	assert "lightrag_graph_nodes.properties \|\| EXCLUDED.properties" in sql	CODE
HIGH⚡	tests/api/test_webui_title_injection.py	129	# null, not "": the client tests one falsy value, and the guard in the	COMMENT

Fake / Example Data77 hits · 76 pts

Severity	File	Line	Snippet	Context
LOW	lightrag/api/routers/document_routes.py	1151	"metadata": {"author": "John Doe", "year": 2025},	CODE
LOW	lightrag/api/routers/document_routes.py	1190	"metadata": {"author": "John Doe", "year": 2025},	CODE
LOW	lightrag/api/routers/document_routes.py	1308	"metadata": {"author": "John Doe", "year": 2025},	CODE
LOW	tests/setup/test_collect.py	860	prompt_secret_until_valid_with_default() {{ printf 'fake-key'; }}	CODE
LOW	tests/parser/docx/test_smart_heading_flow.py	3778	logs = [m for m in _log_messages(caplog) if "placeholder" in m]	CODE
LOW	tests/kg/json_impl/test_write_json_optimization.py	30	"name": "John Doe",	CODE
LOW⚡	tests/api/config/test_api_config_vlm_enable.py	76	monkeypatch.setenv("VLM_LLM_BINDING_API_KEY", "placeholder")	CODE
LOW⚡	tests/api/routes/test_description_api_validation.py	229	["entity", "Alice", "Acme Corp", "founded", "Alice founded Acme Corp."],	CODE
LOW	tests/api/routes/test_description_api_validation.py	241	assert relation["tgt_id"] == "Acme Corp"	CODE
LOW	tests/api/routes/test_description_api_validation.py	262	["entity", "Alice", "Acme Corp", "founded", " "],	CODE
LOW	tests/api/routes/test_description_api_validation.py	277	["edge", "Alice", "Acme Corp", "founded", "Alice founded Acme Corp."],	CODE
LOW	tests/extraction/test_relation_evidence_floor_repair.py	265	@pytest.mark.parametrize("placeholder", sorted(RELATION_NO_EVIDENCE_SOURCE_IDS))	CODE
LOW	tests/extraction/test_relation_evidence_floor_repair.py	327	@pytest.mark.parametrize("placeholder", sorted(RELATION_NO_EVIDENCE_SOURCE_IDS))	CODE
LOW⚡	tests/extraction/test_entity_extraction_stability.py	510	assert set(nodes) == {"Alice", "Acme Corp"}	CODE
LOW⚡	tests/extraction/test_entity_extraction_stability.py	511	assert ("Alice", "Acme Corp") in edges	CODE
LOW⚡	tests/extraction/test_entity_extraction_stability.py	702	assert set(entities.keys()) == {"Alice", "Acme Corp"}	CODE
LOW⚡	tests/extraction/test_entity_extraction_stability.py	706	assert relation_data["tgt_id"] == "Acme Corp"	CODE
LOW	tests/extraction/test_entity_extraction_stability.py	185	"name": "Acme Corp",	CODE
LOW	tests/extraction/test_entity_extraction_stability.py	193	"target": "Acme Corp",	CODE
LOW	tests/extraction/test_entity_extraction_stability.py	660	assert next(iter(relationships.keys())) == ("Alice", "Acme Corp")	CODE
LOW	tests/extraction/test_entity_extraction_stability.py	683	assert relation_data["tgt_id"] == "Acme Corp"	CODE
LOW	lightrag_webui/src/locales/zh.json	397	"placeholder": "页面内搜索节点...",	CODE
LOW	lightrag_webui/src/locales/zh.json	404	"placeholder": "搜索节点名称...",	CODE
LOW	lightrag_webui/src/locales/zh.json	444	"placeholder": "输入查询内容 (支持模式前缀: /<Query Mode>)",	CODE
LOW	lightrag_webui/src/locales/zh.json	509	"placeholder": "请输入 API Key",	CODE
LOW	lightrag_webui/src/locales/ja.json	397	"placeholder": "ページ内のノードを検索...",	CODE
LOW	lightrag_webui/src/locales/ja.json	404	"placeholder": "ノード名を検索...",	CODE
LOW	lightrag_webui/src/locales/ja.json	444	"placeholder": "クエリを入力（プレフィックス対応: /<クエリモード>）",	CODE
LOW	lightrag_webui/src/locales/ja.json	509	"placeholder": "APIキーを入力",	CODE
LOW	lightrag_webui/src/locales/de.json	397	"placeholder": "Knoten auf der Seite suchen...",	CODE
LOW	lightrag_webui/src/locales/de.json	404	"placeholder": "Knotenname suchen...",	CODE
LOW	lightrag_webui/src/locales/de.json	444	"placeholder": "Geben Sie Ihre Abfrage ein (Präfix unterstützt: /<Abfragemodus>)",	CODE
LOW	lightrag_webui/src/locales/de.json	509	"placeholder": "API-Schlüssel eingeben",	CODE
LOW	lightrag_webui/src/locales/ru.json	397	"placeholder": "Поиск узлов на странице...",	CODE
LOW	lightrag_webui/src/locales/ru.json	404	"placeholder": "Поиск имени узла...",	CODE
LOW	lightrag_webui/src/locales/ru.json	444	"placeholder": "Введите ваш запрос (Поддержка префикса: /<Режим запроса>)",	CODE
LOW	lightrag_webui/src/locales/ru.json	509	"placeholder": "Введите ваш API ключ",	CODE
LOW	lightrag_webui/src/locales/uk.json	397	"placeholder": "Шукати вузли на сторінці...",	CODE
LOW	lightrag_webui/src/locales/uk.json	404	"placeholder": "Шукати ім'я вузла...",	CODE
LOW	lightrag_webui/src/locales/uk.json	444	"placeholder": "Введіть ваш запит (Підтримка префіксу: /<Режим запиту>)",	CODE
LOW	lightrag_webui/src/locales/uk.json	509	"placeholder": "Введіть ваш API ключ",	CODE
LOW	lightrag_webui/src/locales/en.json	397	"placeholder": "Search nodes in page...",	CODE
LOW	lightrag_webui/src/locales/en.json	404	"placeholder": "Search node name...",	CODE
LOW	lightrag_webui/src/locales/en.json	444	"placeholder": "Enter your query (Support prefix: /<Query Mode>)",	CODE
LOW	lightrag_webui/src/locales/en.json	509	"placeholder": "Enter your API key",	CODE
LOW	lightrag_webui/src/locales/fr.json	397	"placeholder": "Rechercher des nœuds dans la page...",	CODE
LOW	lightrag_webui/src/locales/fr.json	404	"placeholder": "Rechercher le nom du nœud...",	CODE
LOW	lightrag_webui/src/locales/fr.json	444	"placeholder": "Tapez votre requête (Préfixe de requête : /<Query Mode>)",	CODE
LOW	lightrag_webui/src/locales/fr.json	509	"placeholder": "Entrez votre clé API",	CODE
LOW	lightrag_webui/src/locales/ko.json	397	"placeholder": "페이지 내 노드 검색...",	CODE
LOW	lightrag_webui/src/locales/ko.json	404	"placeholder": "노드 이름 검색...",	CODE
LOW	lightrag_webui/src/locales/ko.json	444	"placeholder": "질문을 입력하세요 (접두사 지원: /<쿼리 모드>)",	CODE
LOW	lightrag_webui/src/locales/ko.json	509	"placeholder": "API 키 입력",	CODE
LOW	lightrag_webui/src/locales/vi.json	397	"placeholder": "Tìm kiếm nút trong trang...",	CODE
LOW	lightrag_webui/src/locales/vi.json	404	"placeholder": "Tìm kiếm tên nút...",	CODE
LOW	lightrag_webui/src/locales/vi.json	444	"placeholder": "Nhập truy vấn của bạn (Hỗ trợ tiền tố: /<Chế Độ Truy Vấn>)",	CODE
LOW	lightrag_webui/src/locales/vi.json	509	"placeholder": "Nhập khóa API của bạn",	CODE
LOW	lightrag_webui/src/locales/id.json	397	"placeholder": "Cari node di halaman...",	CODE
LOW	lightrag_webui/src/locales/id.json	404	"placeholder": "Cari nama node...",	CODE
LOW	lightrag_webui/src/locales/id.json	444	"placeholder": "Masukkan query Anda (mendukung prefix: /<Query Mode>)",	CODE
17 more matches not shown…

Structural Annotation Overuse31 hits · 48 pts

Severity	File	Line	Snippet	Context
LOW⚡	lightrag/lightrag.py	1788	# Step 2: Apply priority wrapper decorator to EmbeddingFunc's inner func	COMMENT
LOW	lightrag/lightrag.py	1770	# Step 1: Capture embedding_func and max_token_size before applying rate_limit decorator	COMMENT
LOW⚡	lightrag/operate.py	6503	# Step 5: Batch retrieve chunk data	COMMENT
LOW⚡	lightrag/operate.py	6509	# Step 6: Build result chunks with valid data and update chunk tracking	COMMENT
LOW⚡	lightrag/operate.py	6800	# Step 5: Batch retrieve chunk data	COMMENT
LOW⚡	lightrag/operate.py	6806	# Step 6: Build result chunks with valid data and update chunk tracking	COMMENT
LOW	lightrag/operate.py	6372	# Step 1: Collect all text chunks for each entity	COMMENT
LOW	lightrag/operate.py	6399	# Step 2: Count chunk occurrences and deduplicate (keep chunks from earlier positioned entities)	COMMENT
LOW	lightrag/operate.py	6434	# Step 3: Sort chunks for each entity by occurrence count (higher count = higher priority)	COMMENT
LOW	lightrag/operate.py	6447	# Step 4: Apply the selected chunk selection algorithm	COMMENT
LOW	lightrag/operate.py	6643	# Step 1: Collect all text chunks for each relationship	COMMENT
LOW	lightrag/operate.py	6678	# Step 2: Count chunk occurrences and deduplicate (keep chunks from earlier positioned relationships)	COMMENT
LOW	lightrag/operate.py	6727	# Step 3: Sort chunks for each relationship by occurrence count (higher count = higher priority)	COMMENT
LOW	lightrag/operate.py	6742	# Step 4: Apply the selected chunk selection algorithm	COMMENT
LOW⚡	lightrag/utils.py	7329	# Step 1: Remove chunks that are no longer needed	COMMENT
LOW⚡	lightrag/utils.py	7335	# Step 2: Append genuine additions only (preserving order from new_chunk_ids).	COMMENT
LOW⚡	lightrag/api/lightrag_server.py	810	# Step 3: Create optimized embedding function (calls underlying function directly)	COMMENT
LOW	lightrag/api/lightrag_server.py	683	# Step 1: Import provider function and extract default attributes	COMMENT
LOW	lightrag/api/lightrag_server.py	790	# Step 2: Apply priority (user config > provider default)	COMMENT
LOW	lightrag/api/lightrag_server.py	1006	# Step 4: Wrap in EmbeddingFunc and return	COMMENT
LOW	lightrag/chunker/paragraph_semantic.py	1351	# Step 1: expand each oversized table paragraph into row-bounded	COMMENT
LOW	lightrag/chunker/paragraph_semantic.py	1375	# Step 2: greedy-pack pieces into chunks ≤ target_max. A piece	COMMENT
LOW	tests/kg/postgres_impl/test_postgres_migration.py	662	# Step 1: Simulate workspace_a initialization (Case 3 - only legacy exists)	COMMENT
LOW	tests/kg/postgres_impl/test_postgres_migration.py	760	# Step 2: Simulate workspace_b initialization (Case 3 - both exist, but legacy has B's data)	COMMENT
LOW	docs/OfflineDeployment.md	212	### Step 1: Prepare in Online Environment	COMMENT
LOW	docs/OfflineDeployment.md	231	### Step 2: Transfer to Offline Environment	COMMENT
LOW	docs/OfflineDeployment.md	241	### Step 3: Install in Offline Environment	COMMENT
LOW	docs/OfflineDeployment.md	262	### Step 4: Verify Installation	COMMENT
LOW⚡	examples/lightrag_ag2_multiagent_demo.py	267	# Step 1: Set up LightRAG (async, runs on the background loop)	COMMENT
LOW⚡	examples/lightrag_ag2_multiagent_demo.py	270	# Step 2: Create AG2 agents with LightRAG tools	COMMENT
LOW⚡	examples/lightrag_ag2_multiagent_demo.py	273	# Step 3: Ask a complex question	COMMENT

AI Slop Vocabulary16 hits · 43 pts

Severity	File	Line	Snippet	Context
MEDIUM	lightrag/tools/clean_llm_query_cache.py	872	"""Print comprehensive cleanup report	STRING
MEDIUM⚡	lightrag/tools/migrate_llm_cache.py	1526	# Print comprehensive migration report	COMMENT
MEDIUM	lightrag/tools/migrate_llm_cache.py	1358	"""Print comprehensive migration report	STRING
MEDIUM	lightrag/kg/mongo_impl.py	3828	"""Try Atlas Search using compound query for comprehensive matching."""	STRING
MEDIUM	lightrag/kg/shared_storage.py	1296	"""Release all locks with comprehensive error handling, protected from cancellation"""	STRING
MEDIUM	lightrag/api/routers/document_routes.py	6680	# Handle both DocStatus enum and string cases for robust deserialization	COMMENT
MEDIUM	tests/tools/test_migrate_graph_storage_networkx.py	53	# the pgtable harness exercises.	COMMENT
LOW	tests/workspace/test_workspace_isolation.py	696	# back in Test 8.2 and is legitimately False here, while ns_a/ns_b were just set.	COMMENT
MEDIUM⚡	tests/parser/docx/test_smart_heading_e2e.py	321	# harness	COMMENT
MEDIUM⚡	tests/kg/postgres_impl/test_postgres_graph_batch.py	16	# Capture harness	COMMENT
MEDIUM	tests/api/routes/test_aquery_data_endpoint.py	493	"mode": "mix", # Use mixed mode to get the most comprehensive results	CODE
MEDIUM⚡	…sts/chunker/test_paragraph_semantic_drop_references.py	122	# Filtering behaviour (assert on content markers, robust to LevelMerge)	COMMENT
MEDIUM⚡	tests/chunker/test_chunking_raw_lightrag_parity.py	62	# Shared fixtures (mirrors the harness used by test_pipeline_release_closure)	COMMENT
MEDIUM	…ghtrag_webui/src/features/retrieval/useQuerySession.ts	359	// Use the robust COT parsing function	COMMENT
MEDIUM	lightrag_webui/src/features/retrieval/MessageList.tsx	210	// Handle copying message content with robust clipboard support	COMMENT
MEDIUM	.github/workflows/webui-tests.yml	55	# proves the test harness stayed out of the bundle.	COMMENT

Verbosity Indicators27 hits · 43 pts

Severity	File	Line	Snippet	Context
LOW⚡	lightrag/lightrag.py	1788	# Step 2: Apply priority wrapper decorator to EmbeddingFunc's inner func	COMMENT
LOW	lightrag/lightrag.py	1770	# Step 1: Capture embedding_func and max_token_size before applying rate_limit decorator	COMMENT
LOW⚡	lightrag/operate.py	6503	# Step 5: Batch retrieve chunk data	COMMENT
LOW⚡	lightrag/operate.py	6509	# Step 6: Build result chunks with valid data and update chunk tracking	COMMENT
LOW⚡	lightrag/operate.py	6800	# Step 5: Batch retrieve chunk data	COMMENT
LOW⚡	lightrag/operate.py	6806	# Step 6: Build result chunks with valid data and update chunk tracking	COMMENT
LOW	lightrag/operate.py	6372	# Step 1: Collect all text chunks for each entity	COMMENT
LOW	lightrag/operate.py	6399	# Step 2: Count chunk occurrences and deduplicate (keep chunks from earlier positioned entities)	COMMENT
LOW	lightrag/operate.py	6434	# Step 3: Sort chunks for each entity by occurrence count (higher count = higher priority)	COMMENT
LOW	lightrag/operate.py	6447	# Step 4: Apply the selected chunk selection algorithm	COMMENT
LOW	lightrag/operate.py	6643	# Step 1: Collect all text chunks for each relationship	COMMENT
LOW	lightrag/operate.py	6678	# Step 2: Count chunk occurrences and deduplicate (keep chunks from earlier positioned relationships)	COMMENT
LOW	lightrag/operate.py	6727	# Step 3: Sort chunks for each relationship by occurrence count (higher count = higher priority)	COMMENT
LOW	lightrag/operate.py	6742	# Step 4: Apply the selected chunk selection algorithm	COMMENT
LOW⚡	lightrag/utils.py	7329	# Step 1: Remove chunks that are no longer needed	COMMENT
LOW⚡	lightrag/utils.py	7335	# Step 2: Append genuine additions only (preserving order from new_chunk_ids).	COMMENT
LOW⚡	lightrag/api/lightrag_server.py	810	# Step 3: Create optimized embedding function (calls underlying function directly)	COMMENT
LOW	lightrag/api/lightrag_server.py	683	# Step 1: Import provider function and extract default attributes	COMMENT
LOW	lightrag/api/lightrag_server.py	790	# Step 2: Apply priority (user config > provider default)	COMMENT
LOW	lightrag/api/lightrag_server.py	1006	# Step 4: Wrap in EmbeddingFunc and return	COMMENT
LOW	lightrag/chunker/paragraph_semantic.py	1351	# Step 1: expand each oversized table paragraph into row-bounded	COMMENT
LOW	lightrag/chunker/paragraph_semantic.py	1375	# Step 2: greedy-pack pieces into chunks ≤ target_max. A piece	COMMENT
LOW	tests/kg/postgres_impl/test_postgres_migration.py	662	# Step 1: Simulate workspace_a initialization (Case 3 - only legacy exists)	COMMENT
LOW	tests/kg/postgres_impl/test_postgres_migration.py	760	# Step 2: Simulate workspace_b initialization (Case 3 - both exist, but legacy has B's data)	COMMENT
LOW⚡	examples/lightrag_ag2_multiagent_demo.py	267	# Step 1: Set up LightRAG (async, runs on the background loop)	COMMENT
LOW⚡	examples/lightrag_ag2_multiagent_demo.py	270	# Step 2: Create AG2 agents with LightRAG tools	COMMENT
LOW⚡	examples/lightrag_ag2_multiagent_demo.py	273	# Step 3: Ask a complex question	COMMENT

Modern Structural Boilerplate40 hits · 40 pts

Severity	File	Line	Snippet	Context
LOW	lightrag/llm_roles.py	139	def set_role_llm_metadata(self, role: str, **metadata: Any) -> None:	CODE
LOW⚡	lightrag/lightrag.py	1426	def _set_runtime_addon_params(self, addon_params: Mapping[str, Any] \| None) -> None:	CODE
LOW	lightrag/__init__.py	5	__all__ = [	CODE
LOW⚡	lightrag/multimodal_context.py	83	logger = logging.getLogger(__name__)	CODE
LOW	lightrag/multimodal_context.py	1099	__all__ = [	CODE
LOW	lightrag/chunk_schema.py	376	__all__ = [	CODE
LOW	lightrag/prompt_multimodal.py	352	__all__ = [	STRING
LOW	lightrag/tools/chunk_tracking_repair.py	160	def set_metadata(self, **values: str) -> None:	CODE
LOW	lightrag/llm/gemini.py	865	__all__ = [	CODE
LOW	lightrag/llm/azure_openai.py	18	__all__ = [	CODE
LOW	lightrag/parser/_html_table.py	208	__all__ = [	CODE
LOW	lightrag/parser/_markdown.py	68	__all__ = [	CODE
LOW	lightrag/parser/markdown/ir_builder.py	230	__all__ = ["NativeMarkdownIRBuilder"]	CODE
LOW	lightrag/parser/markdown/raw_cache.py	249	__all__ = ["NativeImageRawCache", "native_md_options_signature"]	CODE
LOW	lightrag/parser/legacy/__init__.py	14	__all__ = ["LegacyExtractionError", "extract_text"]	CODE
LOW	lightrag/parser/external/_manifest.py	159	__all__ = [	CODE
LOW	lightrag/parser/external/_zip.py	99	__all__ = ["result_bundle_limits", "safe_extract_zip"]	CODE
LOW	lightrag/parser/external/_common.py	326	__all__ = [	CODE
LOW	lightrag/parser/external/__init__.py	35	__all__ = [	CODE
LOW	lightrag/parser/external/docling/ir_builder.py	1068	__all__ = ["DoclingIRBuilder"]	CODE
LOW	lightrag/parser/external/docling/manifest.py	126	__all__ = [	CODE
LOW	lightrag/parser/external/docling/client.py	523	__all__ = [	CODE
LOW	lightrag/parser/external/docling/cache.py	250	__all__ = [	CODE
LOW	lightrag/parser/external/docling/__init__.py	33	__all__ = [	CODE
LOW	lightrag/parser/external/mineru/ir_builder.py	885	__all__ = ["MinerUIRBuilder"]	CODE
LOW	lightrag/parser/external/mineru/manifest.py	155	__all__ = [	CODE
LOW	lightrag/parser/external/mineru/client.py	742	__all__ = ["MinerURawClient", "CONTENT_LIST_FILENAME"]	CODE
LOW	lightrag/parser/external/mineru/cache.py	421	__all__ = [	CODE
LOW	lightrag/parser/external/mineru/__init__.py	21	__all__ = [	CODE
LOW	lightrag/parser/docx/ir_builder.py	335	__all__ = ["NativeDocxIRBuilder"]	CODE
LOW	lightrag/parser/docx/zip_budget.py	199	__all__ = [	CODE
LOW	lightrag/api/routers/__init__.py	14	__all__ = ["OllamaAPI"]	CODE
LOW	lightrag/evaluation/__init__.py	16	__all__ = ["RAGEvaluator"]	CODE
LOW	lightrag/sidecar/__init__.py	29	__all__ = [	CODE
LOW	lightrag/chunker/__init__.py	97	__all__ = [	CODE
LOW⚡	tests/llm/bedrock_impl/test_bedrock_llm.py	643	def set_role_llm_metadata(self, _role: str, **_metadata) -> None:	CODE
LOW	tests/parser/docx/_native_docx_fixtures.py	329	__all__ = ["Scenario", "SCENARIOS", "_block"]	CODE
LOW	…ts/parser/docx/test_extract_blocks_characterization.py	54	def _set_para_id(para, hex_id: str) -> None:	CODE
LOW	tests/parser/docx/test_smart_heading_features.py	40	def _set_doc_default_size(doc: Document, half_points: int) -> None:	CODE
LOW	tests/api/test_lightrag_ollama_chat.py	70	def set_verbose(cls, verbose: bool) -> None:	CODE

Synthetic Comment Markers4 hits · 30 pts

Severity	File	Line	Snippet	Context
HIGH	lightrag/api/config.py	857	# AI-generated content notice shown under every answer in the two query	COMMENT
HIGH	lightrag/api/lightrag_server.py	1710	# Whether the two query UIs label every answer as AI-generated	COMMENT
HIGH	lightrag_webui/src/components/retrieval/ChatMessage.tsx	180	// AI-generated content notice (ENABLE_AI_CONTENT_NOTICE): a trailing item on	COMMENT
HIGH	lightrag_webui/src/lib/aiContentNotice.test.ts	29	// AI-generated would be false.	COMMENT

AI Structural Patterns31 hits · 23 pts

Severity	File	Line	Context
LOW	lightrag/llm_roles.py	309	CODE
LOW	lightrag/llm_roles.py	393	CODE
LOW	lightrag/llm_roles.py	428	CODE
LOW	lightrag/operate.py	2782	CODE
LOW	lightrag/operate.py	3514	CODE
LOW	lightrag/utils.py	5515	CODE
LOW	lightrag/pipeline.py	740	CODE
LOW	lightrag/llm/gemini.py	312	CODE
LOW	lightrag/llm/gemini.py	730	CODE
LOW	lightrag/llm/openai.py	305	CODE
LOW	lightrag/llm/openai.py	1032	CODE
LOW	lightrag/llm/openai.py	1054	CODE
LOW	lightrag/llm/openai.py	1216	CODE
LOW	lightrag/llm/openai.py	1298	CODE
LOW	lightrag/llm/openai.py	1307	CODE
LOW	lightrag/llm/llama_index_impl.py	224	CODE
LOW	lightrag/llm/bedrock.py	187	CODE
LOW	lightrag/llm/bedrock.py	551	CODE
LOW	lightrag/llm/hf.py	290	CODE
LOW	lightrag/parser/external/mineru/cache.py	278	CODE
LOW	lightrag/parser/docx/utils.py	752	CODE
LOW	lightrag/parser/docx/utils.py	803	CODE
LOW	lightrag/parser/docx/smart_heading/heading_flow.py	391	CODE
LOW	lightrag/parser/docx/smart_heading/title_block.py	504	CODE
LOW	lightrag/kg/opensearch_impl.py	5714	CODE
LOW	lightrag/kg/scan_job_store.py	258	CODE
LOW	lightrag/chunker/semantic_vector.py	464	CODE
LOW	tests/pipeline/test_insert_done_error_handling.py	91	CODE
LOW	tests/parser/external/docling/test_client.py	65	CODE
LOW	tests/kg/mongo_impl/test_mongo_scheduling_pages.py	102	CODE
LOW	tests/api/routes/test_document_routes_docx_archive.py	126	CODE

Slop Phrases2 hits · 6 pts

Severity	File	Line	Snippet	Context
MEDIUM⚡	examples/unofficial-sample/lightrag_cloudflare_demo.py	32	WORKING_DIR = "../dickens" # you can change output as desired	CODE
MEDIUM	examples/unofficial-sample/lightrag_nvidia_demo.py	112	# so you can adjust to be able to fit the NVIDIA model (future work)	COMMENT

Example Usage Blocks3 hits · 5 pts

Severity	File	Line	Snippet	Context
LOW	docker-compose.podman.yml	3	# Usage:	COMMENT
LOW⚡	lightrag/llm/binding_options.py	792	# Usage:	COMMENT
LOW	scripts/setup/apple-container.sh	35	# Usage:	COMMENT

Dead Code2 hits · 4 pts

Severity	File	Line	Snippet	Context
MEDIUM	lightrag/base.py	1131		CODE
MEDIUM	lightrag/base.py	1254		CODE

Maintenance and Governance Review

Risk Review · v3

What These Metrics Mean

Pattern-Signal History

Severity Breakdown

Directory Score Breakdown

Pattern Findings