HKUDS/LightRAG

Pattern Findings

4290 matches across 17 categories. Click a row to expand file-level details.

Decorative Section Separators517 hits · 1906 pts

Severity	File	Line	Snippet
MEDIUM	lightrag/pipeline.py	204	# ============================================================
MEDIUM	lightrag/pipeline.py	206	# ============================================================
MEDIUM	lightrag/pipeline.py	2410	# ============================================================
MEDIUM	lightrag/pipeline.py	2412	# ============================================================
MEDIUM	lightrag/pipeline.py	3026	# ============================================================
MEDIUM	lightrag/pipeline.py	3028	# ============================================================
MEDIUM	lightrag/pipeline.py	1162	# ============================================================
MEDIUM	lightrag/pipeline.py	1164	# ============================================================
MEDIUM	lightrag/pipeline.py	1432	# ============================================================
MEDIUM	lightrag/pipeline.py	1434	# ============================================================
MEDIUM	lightrag/pipeline.py	1731	# ============================================================
MEDIUM	lightrag/pipeline.py	1733	# ============================================================
MEDIUM	lightrag/pipeline.py	2591	# ============================================================
MEDIUM	lightrag/pipeline.py	2593	# ============================================================
MEDIUM	lightrag/pipeline.py	3703	# ============================================================
MEDIUM	lightrag/pipeline.py	3705	# ============================================================
MEDIUM	lightrag/multimodal_context.py	87	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	91	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	131	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	134	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	187	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	189	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	266	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	268	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	462	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	464	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	686	# ---------------------------------------------------------------------------
MEDIUM	lightrag/multimodal_context.py	688	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	565	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	567	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	592	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	594	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	440	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	442	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	490	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	492	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	630	# ---------------------------------------------------------------------------
MEDIUM	lightrag/utils_pipeline.py	632	# ---------------------------------------------------------------------------
MEDIUM	lightrag/llm/binding_options.py	421	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	423	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	433	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	587	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	589	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	596	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	633	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	635	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	641	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	663	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	665	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	675	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	32	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	34	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	68	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	538	# =============================================================================
MEDIUM	lightrag/llm/binding_options.py	540	# =============================================================================
MEDIUM	lightrag/parser/routing.py	67	# ---------------------------------------------------------------------------
MEDIUM	lightrag/parser/routing.py	69	# ---------------------------------------------------------------------------
MEDIUM	lightrag/parser/routing.py	166	# ---------------------------------------------------------------------------
MEDIUM	lightrag/parser/routing.py	178	# ---------------------------------------------------------------------------
MEDIUM	lightrag/parser/external/docling/ir_builder.py	97	# ------------------------------------------------------------------
457 more matches not shown…

Hyper-Verbose Identifiers2123 hits · 1789 pts

Severity	File	Line	Snippet
LOW	reproduce/Step_3_openai_compatible.py	57	def run_queries_and_save_to_json(
LOW	reproduce/Step_3.py	26	def run_queries_and_save_to_json(
LOW	lightrag/rerank.py	22	def chunk_documents_for_rerank(
LOW	lightrag/addon_params.py	30	def _emit_deprecated_addon_warnings(params: Mapping[str, Any]) -> None:
LOW	lightrag/llm_roles.py	125	def register_role_llm_builder(
LOW	lightrag/llm_roles.py	157	def _get_effective_role_llm_kwargs(self, role: str) -> dict[str, Any]:
LOW	lightrag/llm_roles.py	165	def _get_effective_role_llm_timeout(self, role: str) -> int:
LOW	lightrag/llm_roles.py	169	def _get_effective_role_llm_max_async(self, role: str) -> int:
LOW	lightrag/llm_roles.py	206	def _rebuild_single_role_llm_func(self, role: str) -> None:
LOW	lightrag/llm_roles.py	222	def _schedule_retired_llm_queue_cleanup(
LOW	lightrag/llm_roles.py	250	def _finalize_retired_llm_queue_cleanup(self, task: asyncio.Task) -> None:
LOW	lightrag/llm_roles.py	259	async def wait_for_retired_llm_queues(self) -> None:
LOW	lightrag/llm_roles.py	270	def _apply_llm_role_config_update(
LOW	lightrag/llm_roles.py	564	async def get_embedding_queue_status(self) -> dict[str, Any]:
LOW	lightrag/lightrag.py	654	def _set_runtime_addon_params(self, addon_params: Mapping[str, Any] \| None) -> None:
LOW	lightrag/lightrag.py	658	def _apply_chunk_size_overlay(self) -> None:
LOW	lightrag/lightrag.py	780	def _refresh_addon_params_cache(self) -> None:
LOW	lightrag/lightrag.py	800	def _ensure_addon_params_cache(self) -> None:
LOW	lightrag/lightrag.py	833	def _build_role_llm_cache_identity(
LOW	lightrag/lightrag.py	1438	async def _process_extract_entities(
LOW	lightrag/lightrag.py	2208	async def _update_delete_retry_state(
LOW	lightrag/lightrag.py	2253	async def _get_existing_llm_cache_ids(self, cache_ids: list[str]) -> list[str]:
LOW	lightrag/operate.py	84	def _get_relationship_vdb_timeout_seconds(global_config: dict[str, Any]) -> float:
LOW	lightrag/operate.py	101	def _format_relation_edge_label(edge_key: tuple[str, str] \| list[str]) -> str:
LOW	lightrag/operate.py	109	def _truncate_entity_identifier(
LOW	lightrag/operate.py	187	async def _handle_entity_relation_summary(
LOW	lightrag/operate.py	410	def _handle_single_entity_extraction(
LOW	lightrag/operate.py	497	def _handle_single_relationship_extraction(
LOW	lightrag/operate.py	584	def _normalize_text_extraction_record_attributes(
LOW	lightrag/operate.py	606	def _looks_like_json_extraction_result(result: str) -> bool:
LOW	lightrag/operate.py	622	async def _process_json_extraction_result(
LOW	lightrag/operate.py	809	async def rebuild_knowledge_from_chunks(
LOW	lightrag/operate.py	993	async def _locked_rebuild_relationship(src, tgt, chunk_ids):
LOW	lightrag/operate.py	1096	async def _get_cached_extraction_results(
LOW	lightrag/operate.py	1186	async def _process_extraction_result(
LOW	lightrag/operate.py	1317	async def _rebuild_from_extraction_result(
LOW	lightrag/operate.py	1618	async def _rebuild_single_relationship(
LOW	lightrag/operate.py	2900	async def _locked_process_entity_name(entity_name, entities):
LOW	lightrag/operate.py	3938	def _strip_markdown_code_fence(text: str) -> str:
LOW	lightrag/operate.py	5016	async def _find_most_related_edges_from_entities(
LOW	lightrag/operate.py	5072	async def _find_related_text_unit_from_entities(
LOW	lightrag/operate.py	5290	async def _find_most_related_entities_from_relationships(
LOW	lightrag/operate.py	5323	async def _find_related_text_unit_from_relations(
LOW	lightrag/utils.py	97	def _patch_ascii_colors_console_handler() -> None:
LOW	lightrag/utils.py	137	async def safe_vdb_operation_with_exception(
LOW	lightrag/utils.py	703	def serialize_llm_cache_identity(identity: Any) -> str:
LOW	lightrag/utils.py	708	def _validate_cached_response_format(response_format: Any \| None) -> None:
LOW	lightrag/utils.py	734	def get_unique_filename_in_parsed(target_dir: Path, original_name: str) -> str:
LOW	lightrag/utils.py	856	def priority_limit_async_func_call(
LOW	lightrag/utils.py	1383	def wrap_embedding_func_with_attrs(**kwargs):
LOW	lightrag/utils.py	1481	def _sanitize_string_for_json(text: str) -> str:
LOW	lightrag/utils.py	1721	def pack_user_ass_to_openai_messages(*args: str):
LOW	lightrag/utils.py	1728	def split_string_by_multi_markers(content: str, markers: list[str]) -> list[str]:
LOW	lightrag/utils.py	1741	def truncate_list_by_token_size(
LOW	lightrag/utils.py	1780	def split_text_units_for_hard_fallback(text: str) -> list[str]:
LOW	lightrag/utils.py	1796	def split_text_by_token_limit(
LOW	lightrag/utils.py	1850	def _normalized_child_offsets(
LOW	lightrag/utils.py	1938	def enforce_chunk_token_limit_before_embedding(
LOW	lightrag/utils.py	2798	def sanitize_and_normalize_extracted_text(
LOW	lightrag/utils.py	2951	def sanitize_text_for_encoding(text: str, replacement_char: str = "") -> str:
2063 more matches not shown…

Excessive Try-Catch Wrapping673 hits · 539 pts

Severity	File	Line	Snippet
LOW	reproduce/Step_1_openai_compatible.py	50	except Exception as e:
LOW	reproduce/Step_0.py	41	except Exception as e:
MEDIUM	reproduce/Step_0.py	42	print(f"An error occurred while processing file {filename}: {e}")
LOW	reproduce/Step_0.py	54	except Exception as e:
MEDIUM	reproduce/Step_0.py	55	print(f"An error occurred while saving to the file {output_filename}: {e}")
LOW	reproduce/Step_1.py	19	except Exception as e:
LOW	reproduce/Step_3_openai_compatible.py	53	except Exception as e:
MEDIUM	reproduce/Step_3_openai_compatible.py	49	def process_query(query_text, rag_instance, query_param):
LOW	reproduce/Step_3.py	22	except Exception as e:
MEDIUM	reproduce/Step_3.py	18	def process_query(query_text, rag_instance, query_param):
LOW	lightrag/rerank.py	58	except Exception as e:
LOW	lightrag/rerank.py	544	except Exception as e:
LOW	lightrag/rerank.py	559	except Exception as e:
LOW	lightrag/rerank.py	574	except Exception as e:
LOW	lightrag/llm_roles.py	256	except Exception as e:
LOW	lightrag/llm_roles.py	342	except Exception:
LOW	lightrag/lightrag.py	12	except Exception: # pragma: no cover - optional dependency
LOW	lightrag/lightrag.py	1210	except Exception as e:
LOW	lightrag/lightrag.py	1451	except Exception as e:
LOW	lightrag/lightrag.py	1756	except Exception as e:
LOW	lightrag/lightrag.py	2167	except Exception as e:
LOW	lightrag/lightrag.py	2268	except Exception as verification_error:
LOW	lightrag/lightrag.py	2302	except Exception as e:
LOW	lightrag/lightrag.py	2482	except Exception as e:
LOW	lightrag/lightrag.py	2637	except Exception as e:
LOW	lightrag/lightrag.py	2654	except Exception as e:
LOW	lightrag/lightrag.py	2687	except Exception as e:
LOW	lightrag/lightrag.py	2750	except Exception as e:
LOW	lightrag/lightrag.py	2757	except Exception as e:
LOW	lightrag/lightrag.py	2778	except Exception as e:
LOW	lightrag/lightrag.py	2786	except Exception as e:
LOW	lightrag/lightrag.py	3000	except Exception as cache_err:
LOW	lightrag/lightrag.py	3013	except Exception as e:
LOW	lightrag/lightrag.py	3072	except Exception as cache_collect_error:
LOW	lightrag/lightrag.py	3091	except Exception as status_write_error:
LOW	lightrag/lightrag.py	3171	except Exception as e:
LOW	lightrag/lightrag.py	3349	except Exception as e:
LOW	lightrag/lightrag.py	3370	except Exception as e:
LOW	lightrag/lightrag.py	3408	except Exception as e:
LOW	lightrag/lightrag.py	3505	except Exception as e:
LOW	lightrag/lightrag.py	3513	except Exception as e:
LOW	lightrag/lightrag.py	3536	except Exception as e:
LOW	lightrag/lightrag.py	3574	except Exception as cache_delete_error:
LOW	lightrag/lightrag.py	3591	except Exception as e:
LOW	lightrag/lightrag.py	3606	except Exception as e:
LOW	lightrag/lightrag.py	3619	except Exception as e:
LOW	lightrag/lightrag.py	3638	except Exception as status_update_error:
LOW	lightrag/lightrag.py	3662	except Exception as persistence_error:
LOW	lightrag/operate.py	490	except Exception as e:
LOW	lightrag/operate.py	577	except Exception as e:
LOW	lightrag/operate.py	648	except Exception as e:
LOW	lightrag/operate.py	720	except Exception as e:
LOW	lightrag/operate.py	800	except Exception as e:
LOW	lightrag/operate.py	943	except Exception as e:
LOW	lightrag/operate.py	984	except Exception as e:
LOW	lightrag/operate.py	1022	except Exception as e:
LOW	lightrag/operate.py	1067	except Exception as e:
LOW	lightrag/operate.py	1441	except Exception as e:
LOW	lightrag/operate.py	1847	except Exception as e:
LOW	lightrag/operate.py	1876	except Exception as e:
613 more matches not shown…

Cross-File Repetition106 hits · 530 pts

Severity	File	Line	Snippet
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
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
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
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
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
HIGH	lightrag/kg/qdrant_impl.py	0	buffered vector upsert waiting for embedding and/or bulk flush.
HIGH	lightrag/kg/mongo_impl.py	0	buffered vector upsert waiting for embedding and/or bulk flush.
HIGH	lightrag/kg/opensearch_impl.py	0	buffered vector upsert waiting for embedding and/or bulk flush.
HIGH	lightrag/kg/milvus_impl.py	0	buffered vector upsert waiting for embedding and/or bulk flush.
HIGH	lightrag/kg/qdrant_impl.py	0	buffer an entity vector delete by computing its hash id.
HIGH	lightrag/kg/mongo_impl.py	0	buffer an entity vector delete by computing its hash id.
HIGH	lightrag/kg/opensearch_impl.py	0	buffer an entity vector delete by computing its hash id.
HIGH	lightrag/kg/milvus_impl.py	0	buffer an entity vector delete by computing its hash id.
HIGH	lightrag/kg/qdrant_impl.py	0	get multiple vector data by their ids (read-your-writes), preserving order.
HIGH	lightrag/kg/mongo_impl.py	0	get multiple vector data by their ids (read-your-writes), preserving order.
HIGH	lightrag/kg/milvus_impl.py	0	get multiple vector data by their ids (read-your-writes), preserving order.
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
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
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
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
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
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
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
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
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
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
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
HIGH	lightrag/kg/mongo_impl.py	0	drop the storage by removing all documents in the collection. returns: dict[str, str]: status of the operation with keys
HIGH	lightrag/kg/mongo_impl.py	0	drop the storage by removing all documents in the collection. returns: dict[str, str]: status of the operation with keys
HIGH	lightrag/kg/mongo_impl.py	0	drop the storage by removing all documents in the collection. returns: dict[str, str]: status of the operation with keys
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 '
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 '
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 '
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 '
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
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
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
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
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
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
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
HIGH	lightrag/kg/json_doc_status_impl.py	0	get documents with pagination support args: status_filter: filter by document status, none for all statuses page: page n
HIGH	lightrag/kg/redis_impl.py	0	get documents with pagination support args: status_filter: filter by document status, none for all statuses page: page n
HIGH	tests/setup/test_misc.py	0	set -euo pipefail source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" reset_state load_existing_env_if_pr
HIGH	tests/setup/test_misc.py	0	set -euo pipefail source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" reset_state load_existing_env_if_pr
HIGH	tests/setup/test_misc.py	0	set -euo pipefail source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" reset_state load_existing_env_if_pr
HIGH	tests/setup/test_misc.py	0	set -euo pipefail source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" reset_state load_existing_env_if_pr
HIGH	tests/setup/test_misc.py	0	set -euo pipefail source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" reset_state load_existing_env_if_pr
HIGH	tests/setup/test_misc.py	0	set -euo pipefail source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" reset_state load_existing_env_if_pr
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_misc.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
HIGH	tests/setup/test_validate.py	0	source "{repo_root}/scripts/setup/setup.sh" repo_root="{tmp_path}" security_check_env_file
46 more matches not shown…

Redundant / Tautological Comments166 hits · 243 pts

Severity	File	Line	Snippet
LOW	docker-build-push.sh	38	# Check if buildx builder exists, create if not
LOW	lightrag/lightrag.py	2136	# Check if query_result is None
LOW	lightrag/operate.py	1055	# Check if any task raised an exception and ensure all exceptions are retrieved
LOW	lightrag/operate.py	2453	# Check if this is a placeholder record
LOW	lightrag/operate.py	3251	# Check if JSON structured output mode is enabled
LOW	lightrag/operate.py	3610	# Check if any task raised an exception and ensure all exceptions are retrieved
LOW	lightrag/operate.py	3878	# Check if pre-defined keywords are already provided
LOW	lightrag/operate.py	5416	# Check if any relations still have chunks after deduplication
LOW	lightrag/utils.py	373	# Check if record has the required attributes for an access log
LOW	lightrag/utils.py	550	# Check if func is already an EmbeddingFunc instance and unwrap it
LOW	lightrag/utils.py	573	# Check if user provided embedding_dim parameter
LOW	lightrag/utils.py	597	# Check if underlying function supports max_token_size and inject if not provided
LOW	lightrag/utils.py	610	# Check if total elements can be evenly divided by embedding_dim
LOW	lightrag/utils.py	953	# Check if task was cancelled before worker started
LOW	lightrag/utils.py	2089	# Check if we already have identical content cached
LOW	lightrag/utils.py	3078	# Check if there are still unused chunks
LOW	lightrag/utils.py	3326	# Check if results are in the new index-based format
LOW	lightrag/pipeline.py	1253	# Check if corresponding content exists in full_docs
LOW	lightrag/pipeline.py	1256	# Check if this is a failed document that should be preserved
LOW	lightrag/pipeline.py	1329	# Check if document has corresponding content in full_docs (consistency check)
LOW	lightrag/pipeline.py	1332	# Check if document is in interrupted status
LOW	lightrag/storage_migrations.py	34	# Check if migration is needed:
LOW	lightrag/storage_migrations.py	54	# Check if full_entities and full_relations are empty
LOW	lightrag/utils_graph.py	97	# Check if the entity exists
LOW	lightrag/utils_graph.py	198	# Check if the relation exists
LOW	lightrag/utils_graph.py	849	# Check if storage has existing data
LOW	lightrag/utils_graph.py	963	# Check if entity already exists
LOW	lightrag/utils_graph.py	1082	# Check if both entities exist
LOW	lightrag/utils_graph.py	1091	# Check if relation already exists
LOW	lightrag/base.py	237	# Check if model_name exists (model_name is optional in EmbeddingFunc)
LOW	lightrag/tools/clean_llm_query_cache.py	205	# Check if config.ini has configuration
LOW	lightrag/tools/clean_llm_query_cache.py	969	# Check if choice is valid
LOW	lightrag/tools/clean_llm_query_cache.py	1067	# Check if user cancelled
LOW	lightrag/tools/clean_llm_query_cache.py	1129	# Check if there are any records to delete
LOW	lightrag/tools/download_cache.py	39	# Check if TIKTOKEN_CACHE_DIR is already set in environment
LOW	lightrag/tools/check_initialization.py	101	# Print results
LOW	lightrag/tools/prepare_qdrant_legacy_data.py	548	# Print result
LOW	lightrag/tools/migrate_llm_cache.py	211	# Check if storage requires configuration
LOW	lightrag/tools/migrate_llm_cache.py	218	# Check if has environment variables
LOW	lightrag/tools/migrate_llm_cache.py	223	# Check if has config.ini configuration
LOW	lightrag/tools/migrate_llm_cache.py	190	# Check if config.ini has configuration
LOW	lightrag/tools/migrate_llm_cache.py	1060	# Check if choice is valid
LOW	lightrag/tools/migrate_llm_cache.py	1429	# Check if user cancelled (setup_storage returns None for all fields)
LOW	lightrag/tools/migrate_llm_cache.py	1433	# Check if there are at least 2 storage types available
LOW	lightrag/tools/lightrag_visualizer/graph_visualizer.py	920	# Check if node is behind camera
LOW	lightrag/llm/jina.py	28	# Check if the error response is HTML (common for 502, 503, etc.)
LOW	lightrag/llm/gemini.py	258	# Check if this part is thought content using the 'thought' attribute
LOW	lightrag/llm/binding_options.py	213	# Check if this is a dataclass and use dataclass fields
LOW	lightrag/llm/openai.py	516	# Check if this chunk has usage information (final chunk)
LOW	lightrag/llm/openai.py	523	# Check if choices exists and is not empty
LOW	lightrag/llm/openai.py	531	# Check if delta exists
LOW	lightrag/llm/openai.py	47	# Check if required Langfuse environment variables are set
LOW	lightrag/llm/openai.py	714	# Check if we should include reasoning content
LOW	lightrag/parser/docx/numbering_resolver.py	199	# Check if this style has numPr
LOW	lightrag/parser/docx/parse_document.py	601	# Check if this block can be absorbed (table_chunk_role constraints)
LOW	lightrag/parser/docx/parse_document.py	617	# Check if combined size doesn't exceed MAX
LOW	lightrag/parser/docx/parse_document.py	892	# Check if this block starts with a split table chunk (has _chunk_heading metadata)
LOW	lightrag/parser/docx/parse_document.py	1579	# Check if this is a heading using the new function
LOW	lightrag/parser/docx/parse_document.py	1761	# Check if table needs splitting (disabled in fixlevel mode)
LOW	lightrag/parser/docx/utils.py	361	# Check if it mentions billing which indicates permanent quota issue
106 more matches not shown…

Deep Nesting307 hits · 216 pts

Severity	File	Line
LOW	reproduce/Step_0.py	7
LOW	reproduce/Step_3_openai_compatible.py	57
LOW	reproduce/Step_3.py	26
LOW	lightrag/rerank.py	22
LOW	lightrag/rerank.py	116
LOW	lightrag/rerank.py	182
LOW	lightrag/table_markup.py	94
LOW	lightrag/llm_roles.py	270
LOW	lightrag/lightrag.py	848
LOW	lightrag/lightrag.py	1182
LOW	lightrag/lightrag.py	1496
LOW	lightrag/lightrag.py	2043
LOW	lightrag/lightrag.py	2383
LOW	lightrag/lightrag.py	2794
LOW	lightrag/operate.py	187
LOW	lightrag/operate.py	809
LOW	lightrag/operate.py	1186
LOW	lightrag/operate.py	1371
LOW	lightrag/operate.py	1618
LOW	lightrag/operate.py	1901
LOW	lightrag/operate.py	2230
LOW	lightrag/operate.py	2815
LOW	lightrag/operate.py	3221
LOW	lightrag/operate.py	3951
LOW	lightrag/operate.py	4169
LOW	lightrag/operate.py	5072
LOW	lightrag/operate.py	5323
LOW	lightrag/operate.py	3309
LOW	lightrag/utils.py	137
LOW	lightrag/utils.py	856
LOW	lightrag/utils.py	1796
LOW	lightrag/utils.py	1938
LOW	lightrag/utils.py	2180
LOW	lightrag/utils.py	3093
LOW	lightrag/utils.py	3273
LOW	lightrag/utils.py	3357
LOW	lightrag/utils.py	3778
LOW	lightrag/utils.py	887
LOW	lightrag/utils.py	924
LOW	lightrag/utils.py	1016
LOW	lightrag/pipeline.py	208
LOW	lightrag/pipeline.py	990
LOW	lightrag/pipeline.py	1436
LOW	lightrag/pipeline.py	1608
LOW	lightrag/pipeline.py	1735
LOW	lightrag/pipeline.py	3164
LOW	lightrag/pipeline.py	3707
LOW	lightrag/pipeline.py	4592
LOW	lightrag/pipeline.py	439
LOW	lightrag/storage_migrations.py	30
LOW	lightrag/storage_migrations.py	100
LOW	lightrag/storage_migrations.py	197
LOW	lightrag/multimodal_context.py	192
LOW	lightrag/multimodal_context.py	467
LOW	lightrag/multimodal_context.py	591
LOW	lightrag/utils_graph.py	262
LOW	lightrag/utils_graph.py	528
LOW	lightrag/utils_graph.py	737
LOW	lightrag/utils_graph.py	1198
LOW	lightrag/utils_graph.py	1626
247 more matches not shown…

Docstring Block Structure43 hits · 215 pts

Severity	File	Line	Snippet
HIGH	lightrag/utils.py	1246	Execute function with enhanced priority-based concurrency control and timeout handling Args:
HIGH	lightrag/pipeline.py	221	Pipeline for Processing Documents 1. Validate ids if provided or generate MD5 hash IDs and remove dupl
HIGH	lightrag/tools/clean_llm_query_cache.py	250	Initialize storage instance with fallback to config.ini and defaults Args: storage_name: Storage im
HIGH	lightrag/tools/migrate_llm_cache.py	263	Initialize storage instance with fallback to config.ini and defaults Args: storage_name: Storage im
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
HIGH	lightrag/llm/voyageai.py	61	Generate embeddings for a list of texts using VoyageAI's API. Args: texts: List of texts to embed.
HIGH	lightrag/llm/gemini.py	302	Complete a prompt using Gemini's API with Chain of Thought (COT) support. This function supports automatic int
HIGH	lightrag/llm/gemini.py	624	Generate embeddings for a list of texts using Gemini's API. This function uses Google's Gemini embedding model to g
HIGH	lightrag/llm/openai.py	259	Complete a prompt using OpenAI's API with caching support and Chain of Thought (COT) integration. This function sup
HIGH	lightrag/llm/openai.py	912	Generate embeddings for a list of texts using OpenAI's API with automatic text truncation. This function supports b
HIGH	lightrag/parser/docx/utils.py	94	Create Gemini client for AI Studio or Vertex AI. Supports two modes: - AI Studio (default): Uses GOOGLE_AP
HIGH	lightrag/parser/docx/utils.py	171	Create OpenAI client with optional custom base URL. Environment variables: - OPENAI_API_KEY: Required API
HIGH	lightrag/kg/postgres_impl.py	519	Execute a database operation with automatic retry for transient failures. Args: operation:
HIGH	lightrag/kg/memgraph_impl.py	134	Check if a node exists in the graph. Args: node_id: The ID of the node to check.
HIGH	lightrag/kg/memgraph_impl.py	174	Check if an edge exists between two nodes in the graph. Args: source_node_id: The ID of th
HIGH	lightrag/kg/memgraph_impl.py	222	Get node by its label identifier, return only node properties Args: node_id: The node label to look
HIGH	lightrag/kg/memgraph_impl.py	277	Get the degree (number of relationships) of a node with the given label. If multiple nodes have the same label,
HIGH	lightrag/kg/memgraph_impl.py	364	Retrieves all edges (relationships) for a particular node identified by its label. Args: source_nod
HIGH	lightrag/kg/memgraph_impl.py	430	Get edge properties between two nodes. Args: source_node_id: Label of the source node t
HIGH	lightrag/kg/neo4j_impl.py	440	Check if a node with the given label exists in the database Args: node_id: Label of the no
HIGH	lightrag/kg/neo4j_impl.py	474	Check if an edge exists between two nodes Args: source_node_id: Label of the source node
HIGH	lightrag/kg/neo4j_impl.py	516	Get node by its label identifier, return only node properties Args: node_id: The node label to look
HIGH	lightrag/kg/neo4j_impl.py	607	Get the degree (number of relationships) of a node with the given label. If multiple nodes have the same label,
HIGH	lightrag/kg/neo4j_impl.py	744	Get edge properties between two nodes. Args: source_node_id: Label of the source node t
HIGH	lightrag/kg/neo4j_impl.py	881	Retrieves all edges (relationships) for a particular node identified by its label. Args: source_nod
HIGH	lightrag/api/auth.py	121	Validate JWT token Args: token: JWT token Returns: dict: Dictionary c
HIGH	lightrag/api/routers/query_routes.py	330	Comprehensive RAG query endpoint with non-streaming response. Parameter "stream" is ignored. This endp
HIGH	lightrag/api/routers/query_routes.py	540	Advanced RAG query endpoint with flexible streaming response. This endpoint provides the most flexible
HIGH	lightrag/api/routers/query_routes.py	1043	Advanced data retrieval endpoint for structured RAG analysis. This endpoint provides raw retrieval res
HIGH	lightrag/api/routers/document_routes.py	113	Sanitize uploaded filename to prevent Path Traversal attacks. Args: filename: The original filename fr
HIGH	lightrag/api/routers/document_routes.py	1576	Extract PDF content using pypdf (synchronous). Args: file_bytes: PDF file content as bytes password
HIGH	lightrag/api/routers/document_routes.py	3094	Upload a file to the input directory and index it. This API endpoint accepts a file through an HTTP PO
HIGH	lightrag/api/routers/document_routes.py	3336	Insert text into the RAG system. This endpoint allows you to insert text data into the RAG system for
HIGH	lightrag/api/routers/document_routes.py	3440	Insert multiple texts into the RAG system. This endpoint allows you to insert multiple text entries in
HIGH	lightrag/api/routers/document_routes.py	3990	Delete documents and all their associated data by their IDs using background processing. Deletes speci
HIGH	lightrag/api/routers/document_routes.py	4080	Clear all cache data from the LLM response cache storage. This endpoint clears all cached LLM response
HIGH	lightrag/api/routers/document_routes.py	4114	Delete an entity and all its relationships from the knowledge graph. Args: request (Delete
HIGH	lightrag/api/routers/document_routes.py	4150	Delete a relationship between two entities from the knowledge graph. Args: request (Delete
HIGH	lightrag/api/routers/document_routes.py	4189	Get the processing status of documents by tracking ID. This endpoint retrieves all documents associate
HIGH	lightrag/api/routers/document_routes.py	4265	Get documents with pagination support. This endpoint retrieves documents with pagination, filtering, a
HIGH	lightrag/evaluation/eval_rag_quality.py	295	Generate RAG response by calling LightRAG API. Args: question: The user query.
HIGH	lightrag/chunker/paragraph_semantic.py	1275	Paragraph Semantic Chunking — the ``chunking="P"`` strategy. Reads structured blocks emitted by the docx native par
HIGH	tests/api/test_lightrag_ollama_chat.py	147	Send an HTTP request with retry mechanism Args: url: Request URL data: Request data stream:

Magic Placeholder Names35 hits · 182 pts

Severity	File	Line	Snippet
HIGH	tests/setup/test_misc.py	297	"LLM_BINDING_API_KEY=your_api_key",
HIGH	tests/setup/test_misc.py	302	"EMBEDDING_BINDING_API_KEY=your_api_key",
HIGH	docs/LightRAG-API-Server.md	118	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server.md	124	# EMBEDDING_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server.md	135	# LLM_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server.md	143	# EMBEDDING_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server.md	265	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server.md	276	EMBEDDING_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server.md	759	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server.md	996	LLM_BINDING_API_KEY=your-api-key
HIGH	docs/ProgramingWithCore.md	852	export OPENAI_API_KEY=your-api-key
HIGH	docs/ProgramingWithCore.md	866	OPENAI_API_KEY=your-api-key \
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	26	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	122	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	203	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	220	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/RoleSpecificLLMConfiguration-zh.md	333	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server-zh.md	118	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server-zh.md	124	# EMBEDDING_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server-zh.md	135	# LLM_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server-zh.md	143	# EMBEDDING_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server-zh.md	265	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server-zh.md	276	EMBEDDING_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server-zh.md	759	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/LightRAG-API-Server-zh.md	996	LLM_BINDING_API_KEY=your-api-key
HIGH	docs/RoleSpecificLLMConfiguration.md	26	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/RoleSpecificLLMConfiguration.md	122	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/RoleSpecificLLMConfiguration.md	203	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/RoleSpecificLLMConfiguration.md	220	LLM_BINDING_API_KEY=your_api_key
HIGH	docs/RoleSpecificLLMConfiguration.md	333	LLM_BINDING_API_KEY=your_api_key
HIGH	examples/lightrag_gemini_postgres_demo.py	28	GEMINI_API_KEY=your-api-key
HIGH	examples/lightrag_gemini_demo.py	37	"Please set it with: export GEMINI_API_KEY='your-api-key'"
HIGH	examples/lightrag_openai_opensearch_graph_demo.py	23	OPENAI_API_KEY=your-api-key
HIGH	…s/unofficial-sample/lightrag_llamaindex_direct_demo.py	29	OPENAI_API_KEY = os.environ.get("OPENAI_API_KEY", "your-api-key-here")
HIGH	examples/unofficial-sample/lightrag_cloudflare_demo.py	20	cloudflare_api_key = "YOUR_API_KEY"

Self-Referential Comments50 hits · 148 pts

Severity	File	Line	Snippet
MEDIUM	reproduce/Step_1_openai_compatible.py	77	# Initialize RAG instance
MEDIUM	reproduce/Step_1.py	42	# Initialize RAG instance
MEDIUM	lightrag/lightrag.py	964	# Create a NEW EmbeddingFunc instance with the wrapped func to avoid mutating the caller's object
MEDIUM	lightrag/lightrag.py	1951	# Create a copy of param to avoid modifying the original
MEDIUM	lightrag/operate.py	5619	# Create a preliminary system prompt with empty content_data to calculate overhead
MEDIUM	lightrag/utils.py	3980	# Create a list of (file_path, count, first_index) tuples
MEDIUM	lightrag/pipeline.py	790	# Create a new record with unique ID for this duplicate attempt
MEDIUM	lightrag/tools/migrate_llm_cache.py	701	# Create a snapshot of matching items while holding the lock
MEDIUM	lightrag/llm/openai.py	173	# Create a merged config dict with precedence: explicit params > client_configs
MEDIUM	lightrag/llm/openai.py	205	# Create a merged config dict with precedence: explicit params > client_configs > defaults
MEDIUM	lightrag/llm/openai.py	375	# Create the OpenAI client (supports both OpenAI and Azure)
MEDIUM	lightrag/llm/openai.py	996	# Create the OpenAI client (supports both OpenAI and Azure)
MEDIUM	lightrag/llm/bedrock.py	320	# Create a session that will be used throughout the streaming process
MEDIUM	lightrag/llm/bedrock.py	330	# Define the generator function that will manage the client lifecycle
MEDIUM	lightrag/kg/mongo_impl.py	2409	# Create the improved search index (async, no waiting)
MEDIUM	lightrag/kg/mongo_impl.py	363	# Create a copy of v for $set operation, excluding create_time to avoid conflicts
MEDIUM	lightrag/kg/mongo_impl.py	2738	# Define the aggregation pipeline with the converted query vector
MEDIUM	lightrag/kg/postgres_impl.py	1431	# Define the field changes needed
MEDIUM	lightrag/kg/faiss_impl.py	233	# Create an empty Faiss index for inner product (useful for normalized vectors = cosine similarity).
MEDIUM	lightrag/kg/shared_storage.py	17	# Define a direct print function for critical logs that must be visible in all processes
MEDIUM	lightrag/kg/shared_storage.py	1286	# Create a shared list object for history_messages
MEDIUM	lightrag/kg/shared_storage.py	1358	# Create a simple mutable object to store boolean value for compatibility with mutiprocess
MEDIUM	lightrag/kg/json_kv_impl.py	253	# Create a copy to avoid modifying the original data
MEDIUM	lightrag/kg/json_kv_impl.py	268	# Create a copy to avoid modifying the original data
MEDIUM	lightrag/api/run_with_gunicorn.py	118	# Define a custom application class that loads our config
MEDIUM	lightrag/api/run_with_gunicorn.py	248	# Create the application
MEDIUM	lightrag/api/lightrag_server.py	1834	# Create the EmbeddingFunc instance (now returns complete EmbeddingFunc with max_token_size)
MEDIUM	lightrag/api/routers/ollama_api.py	149	# Create an instance of the model
MEDIUM	lightrag/api/routers/query_routes.py	431	# Create a mapping from reference_id to chunk content
MEDIUM	lightrag/api/routers/query_routes.py	685	# Create a mapping from reference_id to chunk content
MEDIUM	tests/kg/test_graph_storage.py	108	# Initialize the storage instance
MEDIUM	tests/kg/test_graph_storage.py	1475	# Initialize storage instance
MEDIUM	tests/kg/postgres_impl/test_postgres_index_name.py	84	# Create a table name that results in exactly 63 bytes
MEDIUM	tests/api/auth/test_token_auto_renewal.py	16	# Create a simple token renewal cache for testing
MEDIUM	tests/api/auth/test_token_auto_renewal.py	323	# Create a mock JWT payload
MEDIUM	tests/chunker/test_rerank_chunking.py	39	# Create a very long document that exceeds character limit
MEDIUM	examples/graph_visual_with_html.py	15	# Create a Pyvis network
MEDIUM	examples/lightrag_openai_compatible_demo.py	150	# Initialize RAG instance
MEDIUM	examples/lightrag_openai_mongodb_graph_demo.py	72	# Initialize RAG instance
MEDIUM	examples/lightrag_openai_demo.py	119	# Initialize RAG instance
MEDIUM	examples/lightrag_ollama_demo.py	139	# Initialize RAG instance
MEDIUM	examples/graph_visual_with_neo4j.py	159	# Create a Neo4j driver
MEDIUM	…mples/unofficial-sample/lightrag_embedding_prefixes.py	156	# Initialize RAG instance
MEDIUM	…/unofficial-sample/lightrag_llamaindex_litellm_demo.py	103	# Initialize RAG instance
MEDIUM	…cial-sample/lightrag_openai_neo4j_milvus_redis_demo.py	73	# Initialize RAG instance
MEDIUM	…s/unofficial-sample/lightrag_llamaindex_direct_demo.py	101	# Initialize RAG instance
MEDIUM	…ficial-sample/lightrag_llamaindex_litellm_opik_demo.py	114	# Initialize RAG instance
MEDIUM	examples/unofficial-sample/lightrag_cloudflare_demo.py	251	# Initialize RAG instance
MEDIUM	examples/unofficial-sample/lightrag_lmdeploy_demo.py	69	# Initialize RAG instance
MEDIUM	examples/unofficial-sample/lightrag_nvidia_demo.py	123	# Initialize RAG instance

Unused Imports140 hits · 132 pts

Severity	File	Line
LOW	lightrag/rerank.py	1
LOW	lightrag/file_atomic.py	29
LOW	lightrag/addon_params.py	15
LOW	lightrag/table_markup.py	17
LOW	lightrag/llm_roles.py	11
LOW	lightrag/lightrag.py	1
LOW	lightrag/lightrag.py	140
LOW	lightrag/__init__.py	3
LOW	lightrag/types.py	1
LOW	lightrag/operate.py	1
LOW	lightrag/utils.py	1
LOW	lightrag/utils.py	301
LOW	lightrag/utils.py	301
LOW	lightrag/utils.py	301
LOW	lightrag/pipeline.py	12
LOW	lightrag/storage_migrations.py	13
LOW	lightrag/exceptions.py	1
LOW	lightrag/multimodal_context.py	64
LOW	lightrag/utils_graph.py	1
LOW	lightrag/prompt.py	1
LOW	lightrag/utils_pipeline.py	10
LOW	lightrag/namespace.py	1
LOW	lightrag/chunk_schema.py	24
LOW	lightrag/base.py	1
LOW	lightrag/prompt_multimodal.py	31
LOW	lightrag/llm/gemini.py	10
LOW	lightrag/llm/_vision_utils.py	20
LOW	lightrag/llm/azure_openai.py	12
LOW	lightrag/llm/azure_openai.py	12
LOW	lightrag/llm/azure_openai.py	12
LOW	lightrag/parser/cli.py	17
LOW	lightrag/parser/_markdown.py	10
LOW	lightrag/parser/routing.py	1
LOW	lightrag/parser/debug.py	16
LOW	lightrag/parser/external/_manifest.py	18
LOW	lightrag/parser/external/_zip.py	10
LOW	lightrag/parser/external/_common.py	11
LOW	lightrag/parser/external/__init__.py	16
LOW	lightrag/parser/external/__init__.py	16
LOW	lightrag/parser/external/__init__.py	16
LOW	lightrag/parser/external/__init__.py	16
LOW	lightrag/parser/external/__init__.py	16
LOW	lightrag/parser/external/__init__.py	16
LOW	lightrag/parser/external/__init__.py	24
LOW	lightrag/parser/external/__init__.py	24
LOW	lightrag/parser/external/__init__.py	24
LOW	lightrag/parser/external/__init__.py	24
LOW	lightrag/parser/external/__init__.py	24
LOW	lightrag/parser/external/__init__.py	24
LOW	lightrag/parser/external/__init__.py	24
LOW	lightrag/parser/external/__init__.py	33
LOW	lightrag/parser/external/docling/ir_builder.py	43
LOW	lightrag/parser/external/docling/manifest.py	11
LOW	lightrag/parser/external/docling/client.py	20
LOW	lightrag/parser/external/docling/cache.py	30
LOW	lightrag/parser/external/docling/__init__.py	8
LOW	lightrag/parser/external/docling/__init__.py	23
LOW	lightrag/parser/external/docling/__init__.py	26
LOW	lightrag/parser/external/docling/__init__.py	29
LOW	lightrag/parser/external/mineru/ir_builder.py	43
80 more matches not shown…

Verbosity Indicators31 hits · 50 pts

Severity	File	Line	Snippet
LOW	lightrag/lightrag.py	945	# Step 1: Capture embedding_func and max_token_size before applying rate_limit decorator
LOW	lightrag/lightrag.py	963	# Step 2: Apply priority wrapper decorator to EmbeddingFunc's inner func
LOW	lightrag/operate.py	5094	# Step 1: Collect all text chunks for each entity
LOW	lightrag/operate.py	5121	# Step 2: Count chunk occurrences and deduplicate (keep chunks from earlier positioned entities)
LOW	lightrag/operate.py	5138	# Step 3: Sort chunks for each entity by occurrence count (higher count = higher priority)
LOW	lightrag/operate.py	5151	# Step 4: Apply the selected chunk selection algorithm
LOW	lightrag/operate.py	5205	# Step 5: Batch retrieve chunk data
LOW	lightrag/operate.py	5211	# Step 6: Build result chunks with valid data and update chunk tracking
LOW	lightrag/operate.py	5345	# Step 1: Collect all text chunks for each relationship
LOW	lightrag/operate.py	5380	# Step 2: Count chunk occurrences and deduplicate (keep chunks from earlier positioned relationships)
LOW	lightrag/operate.py	5429	# Step 3: Sort chunks for each relationship by occurrence count (higher count = higher priority)
LOW	lightrag/operate.py	5444	# Step 4: Apply the selected chunk selection algorithm
LOW	lightrag/operate.py	5500	# Step 5: Batch retrieve chunk data
LOW	lightrag/operate.py	5506	# Step 6: Build result chunks with valid data and update chunk tracking
LOW	lightrag/utils.py	3572	# Step 1: Remove chunks that are no longer needed
LOW	lightrag/utils.py	3577	# Step 2: Add new chunks (preserving order from new_chunk_ids)
LOW	lightrag/kg/milvus_impl.py	1089	# Step 3: Rename origin collection (keep for safety)
LOW	lightrag/kg/milvus_impl.py	1109	# Step 4: Rename temporary collection to original name
LOW	lightrag/kg/milvus_impl.py	1004	# Step 1: Create temporary collection with new schema
LOW	lightrag/kg/milvus_impl.py	1025	# Step 2: Copy data using query_iterator (solves query window limitation)
LOW	lightrag/api/lightrag_server.py	1503	# Step 1: Import provider function and extract default attributes
LOW	lightrag/api/lightrag_server.py	1556	# Step 2: Apply priority (user config > provider default)
LOW	lightrag/api/lightrag_server.py	1576	# Step 3: Create optimized embedding function (calls underlying function directly)
LOW	lightrag/api/lightrag_server.py	1771	# Step 4: Wrap in EmbeddingFunc and return
LOW	lightrag/chunker/paragraph_semantic.py	849	# Step 1: expand each oversized table paragraph into row-bounded
LOW	lightrag/chunker/paragraph_semantic.py	873	# Step 2: greedy-pack pieces into chunks ≤ target_max. A piece
LOW	tests/kg/postgres_impl/test_postgres_migration.py	662	# Step 1: Simulate workspace_a initialization (Case 3 - only legacy exists)
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)
LOW	examples/lightrag_ag2_multiagent_demo.py	267	# Step 1: Set up LightRAG (async, runs on the background loop)
LOW	examples/lightrag_ag2_multiagent_demo.py	270	# Step 2: Create AG2 agents with LightRAG tools
LOW	examples/lightrag_ag2_multiagent_demo.py	273	# Step 3: Ask a complex question

Over-Commented Block58 hits · 42 pts

Severity	File	Line	Snippet
LOW	docker-compose.podman.yml	1	# Podman-compatible compose file for LightRAG
LOW	lightrag/lightrag.py	721	if "chunk_overlap_token_size" not in sub:
LOW	lightrag/lightrag.py	741	chunker_cfg["paragraph_semantic"].setdefault(
LOW	lightrag/lightrag.py	1581	# Relationship storage is undirected, so keep only the last update
LOW	lightrag/lightrag.py	4081	# `addon_params` is declared as an InitVar on the dataclass so it can still be
LOW	lightrag/constants.py	101	)
LOW	lightrag/constants.py	281	# because both engines are resource-intensive (GPU/CPU + memory) and tend to
LOW	lightrag/utils.py	3801
LOW	lightrag/pipeline.py	281	# processing loop because (a) full_docs is upserted before
LOW	lightrag/pipeline.py	661	# this, two enqueues for the same content (e.g. /upload during
LOW	lightrag/pipeline.py	1041	"Another process is already processing the document queue. Request queued."
LOW	lightrag/pipeline.py	1481	# Stamp parsing_start_time on the in-memory status_doc so
LOW	lightrag/pipeline.py	1661	# Mirror analyze-stage outcome as a 3-way decision so the
LOW	lightrag/pipeline.py	1841	# follows the standardized file-chunker contract
LOW	lightrag/pipeline.py	2061	# Explicit selector in process_options: reflect
LOW	lightrag/pipeline.py	2121	"Applied hard fallback split before embedding for "
LOW	lightrag/utils_pipeline.py	181	# tables missing ``w14:paraId``) that admins should be able to surface
LOW	lightrag/utils_pipeline.py	201	# operators can distinguish "analyze actually completed" from "analyze
LOW	lightrag/utils_pipeline.py	701	# over all chunk_results. It has been moved into
LOW	lightrag/llm/binding_options.py	41	# - Handles default values and type information for each parameter
LOW	lightrag/llm/binding_options.py	421	# =============================================================================
LOW	lightrag/llm/binding_options.py	661
LOW	lightrag/llm/openai.py	461	# A "could not parse JSON body" 400 is transient (corrupted/truncated
LOW	lightrag/parser/routing.py	161	skip_kg=PROCESS_OPTION_SKIP_KG in chars,
LOW	lightrag/parser/external/docling/cache.py	41
LOW	lightrag/kg/mongo_impl.py	1081
LOW	lightrag/kg/mongo_impl.py	1101	# "target_node_id" : "ProductX",
LOW	lightrag/kg/postgres_impl.py	5081
LOW	lightrag/kg/postgres_impl.py	6041	target_node_id (str): Label of the target node (used as identifier)
LOW	lightrag/kg/faiss_impl.py	241	# Minimal pending area for deferred embedding: custom-id -> _PendingFaissDoc.
LOW	lightrag/kg/shared_storage.py	1301	# Exclusive subset of ``scanning``: only True during the
LOW	lightrag/kg/milvus_impl.py	1361	self._validate_embedding_func()
LOW	lightrag/kg/milvus_impl.py	1381	# "hnsw_m": 32,
LOW	lightrag/api/routers/document_routes.py	2581	except Exception as move_error:
LOW	lightrag/api/routers/document_routes.py	2681	# True for the rest of the task lifecycle (releases in
LOW	lightrag/api/routers/document_routes.py	3161	Raises:
LOW	lightrag/chunker/paragraph_semantic.py	821	candidates.append({"index": idx, "text": text, "position": cumulative})
LOW	tests/chunker/test_chunking.py	661	split_by_character=None,
LOW	tests/chunker/test_chunking.py	1021	chunk_overlap_token_size=2,
LOW	…ts/chunker/test_paragraph_semantic_split_long_block.py	61	# recursive-character splitting so ``target_max`` is honored without
LOW	docs/LightRAG-API-Server.md	1001	VLM_PROCESS_ENABLE=false
LOW	docs/LightRAG-API-Server.md	1021	# EMBEDDING_DOCUMENT_PREFIX="search_document: "
LOW	docs/RoleSpecificLLMConfiguration-zh.md	241	# have a valid OpenAI configuration.
LOW	docs/LightRAG-API-Server-zh.md	1001	VLM_PROCESS_ENABLE=false
LOW	docs/LightRAG-API-Server-zh.md	1021	# EMBEDDING_DOCUMENT_PREFIX="search_document: "
LOW	docs/RoleSpecificLLMConfiguration.md	241	# have a valid OpenAI configuration.
LOW	examples/milvus_kwargs_configuration_demo.py	21	# os.environ["MILVUS_USER"] = "root"
LOW	examples/milvus_kwargs_configuration_demo.py	41	"index_type": "HNSW",
LOW	k8s-deploy/databases/neo4j/values.yaml	1	# Version
LOW	k8s-deploy/databases/neo4j/values.yaml	21	# description: Memory, the unit is Gi.
LOW	k8s-deploy/databases/postgresql/values.yaml	1	## description: service version.
LOW	k8s-deploy/databases/postgresql/values.yaml	21	## default: 0.5
LOW	k8s-deploy/databases/redis/values.yaml	1	## description: Cluster version.
LOW	k8s-deploy/databases/redis/values.yaml	21
LOW	k8s-deploy/databases/mongodb/values.yaml	1	## description: Cluster version.
LOW	k8s-deploy/databases/qdrant/values.yaml	1	## description: The version of Qdrant.
LOW	k8s-deploy/databases/elasticsearch/values.yaml	1	## description: The version of ElasticSearch.
LOW	k8s-deploy/lightrag/values.yaml	1	replicaCount: 1

Cross-Language Confusion9 hits · 40 pts

Severity	File	Line	Snippet
HIGH	lightrag/pipeline.py	2722	# ``positions: [{"type": "paraid", "range": null}]``.
HIGH	lightrag/kg/postgres_impl.py	6082	" $1::text \|\| E'\\x01' \|\|"
HIGH	lightrag/api/lightrag_server.py	123	if (!data \|\| data.type !== 'lightrag:set-docs-theme') return;
HIGH	lightrag/api/routers/graph_routes.py	308	"merge_error": null,
HIGH	lightrag/api/routers/graph_routes.py	310	"target_entity": null,
HIGH	lightrag/api/routers/graph_routes.py	336	"merge_error": null,
HIGH	…sts/kg/postgres_impl/test_postgres_cypher_injection.py	135	"formula": "x < 5 && y > 3",
HIGH	…sts/kg/postgres_impl/test_postgres_cypher_injection.py	146	assert '`formula`: "x < 5 && y > 3"' in call["sql"]
HIGH	…s/kg/postgres_impl/test_postgres_upsert_edge_cypher.py	171	assert "$1::text \|\| E'\\x01' \|\|" in lock_sql

AI Slop Vocabulary11 hits · 23 pts

Severity	File	Line	Snippet
LOW	lightrag/pipeline.py	1038	# Another process is busy, just set request flag and return
MEDIUM	lightrag/tools/clean_llm_query_cache.py	870	"""Print comprehensive cleanup report
MEDIUM	lightrag/tools/migrate_llm_cache.py	1517	# Print comprehensive migration report
MEDIUM	lightrag/tools/migrate_llm_cache.py	1349	"""Print comprehensive migration report
MEDIUM	lightrag/kg/mongo_impl.py	2153	"""Try Atlas Search using compound query for comprehensive matching."""
MEDIUM	lightrag/kg/shared_storage.py	984	"""Release all locks with comprehensive error handling, protected from cancellation"""
MEDIUM	lightrag/api/routers/document_routes.py	4239	# Handle both DocStatus enum and string cases for robust deserialization
MEDIUM	tests/api/routes/test_aquery_data_endpoint.py	493	"mode": "mix", # Use mixed mode to get the most comprehensive results
MEDIUM	tests/chunker/test_chunking_raw_lightrag_parity.py	56	# Shared fixtures (mirrors the harness used by test_pipeline_release_closure)
MEDIUM	lightrag_webui/src/features/RetrievalTesting.tsx	269	// Use the new robust COT parsing function
MEDIUM	lightrag_webui/src/features/RetrievalTesting.tsx	635	// Handle copying message content with robust clipboard support

Fake / Example Data17 hits · 14 pts

Severity	File	Line	Snippet
LOW	lightrag/api/routers/document_routes.py	680	"metadata": {"author": "John Doe", "year": 2025},
LOW	lightrag/api/routers/document_routes.py	744	"metadata": {"author": "John Doe"},
LOW	lightrag/api/routers/document_routes.py	786	"metadata": {"author": "John Doe", "year": 2025},
LOW	lightrag/api/routers/document_routes.py	904	"metadata": {"author": "John Doe", "year": 2025},
LOW	tests/kg/json_impl/test_write_json_optimization.py	30	"name": "John Doe",
LOW	tests/api/routes/test_description_api_validation.py	228	["entity", "Alice", "Acme Corp", "founded", "Alice founded Acme Corp."],
LOW	tests/api/routes/test_description_api_validation.py	240	assert relation["tgt_id"] == "Acme Corp"
LOW	tests/api/routes/test_description_api_validation.py	261	["entity", "Alice", "Acme Corp", "founded", " "],
LOW	tests/api/routes/test_description_api_validation.py	276	["edge", "Alice", "Acme Corp", "founded", "Alice founded Acme Corp."],
LOW	tests/extraction/test_entity_extraction_stability.py	420	assert set(nodes) == {"Alice", "Acme Corp"}
LOW	tests/extraction/test_entity_extraction_stability.py	421	assert ("Alice", "Acme Corp") in edges
LOW	tests/extraction/test_entity_extraction_stability.py	612	assert set(entities.keys()) == {"Alice", "Acme Corp"}
LOW	tests/extraction/test_entity_extraction_stability.py	616	assert relation_data["tgt_id"] == "Acme Corp"
LOW	tests/extraction/test_entity_extraction_stability.py	184	"name": "Acme Corp",
LOW	tests/extraction/test_entity_extraction_stability.py	192	"target": "Acme Corp",
LOW	tests/extraction/test_entity_extraction_stability.py	570	assert next(iter(relationships.keys())) == ("Alice", "Acme Corp")
LOW	tests/extraction/test_entity_extraction_stability.py	593	assert relation_data["tgt_id"] == "Acme Corp"

Slop Phrases2 hits · 5 pts

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

Example Usage Blocks2 hits · 4 pts

Severity	File	Line	Snippet
LOW	docker-compose.podman.yml	3	# Usage:
LOW	lightrag/llm/binding_options.py	671	# Usage:

Score History

Severity Breakdown

Pattern Findings