gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix lint

Browse Source
This commit is contained in:
zrguo
2025-03-17 23:36:00 +08:00
parent bf18a5406e
commit 6115f60072
2 changed files with 73 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files

49
lightrag/lightrag.py
View File

@@ -563,7 +563,9 @@ class LightRAG:
"""
loop = always_get_an_event_loop()
loop.run_until_complete(
self.ainsert(input, split_by_character, split_by_character_only, ids, file_paths)
self.ainsert(
input, split_by_character, split_by_character_only, ids, file_paths
)
)
async def ainsert(
@@ -659,7 +661,10 @@ class LightRAG:
await self._insert_done()
async def apipeline_enqueue_documents(
self, input: str | list[str], ids: list[str] | None = None, file_paths: str | list[str] | None = None
self,
input: str | list[str],
ids: list[str] | None = None,
file_paths: str | list[str] | None = None,
) -> None:
"""
Pipeline for Processing Documents
@@ -687,7 +692,9 @@ class LightRAG:
if isinstance(file_paths, str):
file_paths = [file_paths]
if len(file_paths) != len(input):
raise ValueError("Number of file paths must match the number of documents")
raise ValueError(
"Number of file paths must match the number of documents"
)
else:
# If no file paths provided, use placeholder
file_paths = ["unknown_source"] * len(input)
@@ -703,11 +710,15 @@ class LightRAG:
raise ValueError("IDs must be unique")
# Generate contents dict of IDs provided by user and documents
contents = {id_: {"content": doc, "file_path": path}
for id_, doc, path in zip(ids, input, file_paths)}
contents = {
id_: {"content": doc, "file_path": path}
for id_, doc, path in zip(ids, input, file_paths)
}
else:
# Clean input text and remove duplicates
cleaned_input = [(clean_text(doc), path) for doc, path in zip(input, file_paths)]
cleaned_input = [
(clean_text(doc), path) for doc, path in zip(input, file_paths)
]
unique_content_with_paths = {}
# Keep track of unique content and their paths
@@ -716,9 +727,13 @@ class LightRAG:
unique_content_with_paths[content] = path
# Generate contents dict of MD5 hash IDs and documents with paths
contents = {compute_mdhash_id(content, prefix="doc-"):
{"content": content, "file_path": path}
for content, path in unique_content_with_paths.items()}
contents = {
compute_mdhash_id(content, prefix="doc-"): {
"content": content,
"file_path": path,
}
for content, path in unique_content_with_paths.items()
}
# 2. Remove duplicate contents
unique_contents = {}
@@ -729,8 +744,10 @@ class LightRAG:
unique_contents[content] = (id_, file_path)
# Reconstruct contents with unique content
contents = {id_: {"content": content, "file_path": file_path}
for content, (id_, file_path) in unique_contents.items()}
contents = {
id_: {"content": content, "file_path": file_path}
for content, (id_, file_path) in unique_contents.items()
}
# 3. Generate document initial status
new_docs: dict[str, Any] = {
@@ -741,7 +758,9 @@ class LightRAG:
"content_length": len(content_data["content"]),
"created_at": datetime.now().isoformat(),
"updated_at": datetime.now().isoformat(),
"file_path": content_data["file_path"], # Store file path in document status
"file_path": content_data[
"file_path"
], # Store file path in document status
}
for id_, content_data in contents.items()
}
@@ -1109,7 +1128,10 @@ class LightRAG:
loop.run_until_complete(self.ainsert_custom_kg(custom_kg, full_doc_id))
async def ainsert_custom_kg(
self, custom_kg: dict[str, Any], full_doc_id: str = None, file_path: str = "custom_kg"
self,
custom_kg: dict[str, Any],
full_doc_id: str = None,
file_path: str = "custom_kg",
) -> None:
update_storage = False
try:
@@ -3125,4 +3147,3 @@ class LightRAG:
]
]
)

35
lightrag/operate.py
View File

@@ -224,7 +224,9 @@ async def _merge_nodes_then_upsert(
split_string_by_multi_markers(already_node["source_id"], [GRAPH_FIELD_SEP])
)
already_file_paths.extend(
split_string_by_multi_markers(already_node["metadata"]["file_path"], [GRAPH_FIELD_SEP])
split_string_by_multi_markers(
already_node["metadata"]["file_path"], [GRAPH_FIELD_SEP]
)
)
already_description.append(already_node["description"])
@@ -336,7 +338,14 @@ async def _merge_edges_then_upsert(
)
)
file_path = GRAPH_FIELD_SEP.join(
set([dp["metadata"]["file_path"] for dp in edges_data if dp.get("metadata", {}).get("file_path")] + already_file_paths)
set(
[
dp["metadata"]["file_path"]
for dp in edges_data
if dp.get("metadata", {}).get("file_path")
]
+ already_file_paths
)
)
for need_insert_id in [src_id, tgt_id]:
@@ -482,7 +491,9 @@ async def extract_entities(
else:
return await use_llm_func(input_text)
async def _process_extraction_result(result: str, chunk_key: str, file_path: str = "unknown_source"):
async def _process_extraction_result(
result: str, chunk_key: str, file_path: str = "unknown_source"
):
"""Process a single extraction result (either initial or gleaning)
Args:
result (str): The extraction result to process
@@ -669,7 +680,9 @@ async def extract_entities(
"file_path": dp.get("metadata", {}).get("file_path", "unknown_source"),
"metadata": {
"created_at": dp.get("metadata", {}).get("created_at", time.time()),
"file_path": dp.get("metadata", {}).get("file_path", "unknown_source"),
"file_path": dp.get("metadata", {}).get(
"file_path", "unknown_source"
),
},
}
for dp in all_entities_data
@@ -687,7 +700,9 @@ async def extract_entities(
"file_path": dp.get("metadata", {}).get("file_path", "unknown_source"),
"metadata": {
"created_at": dp.get("metadata", {}).get("created_at", time.time()),
"file_path": dp.get("metadata", {}).get("file_path", "unknown_source"),
"file_path": dp.get("metadata", {}).get(
"file_path", "unknown_source"
),
},
}
for dp in all_relationships_data
@@ -1574,15 +1589,7 @@ async def _get_edge_data(
relations_context = list_of_list_to_csv(relations_section_list)
entites_section_list = [
[
"id",
"entity",
"type",
"description",
"rank",
"created_at",
"file_path"
]
["id", "entity", "type", "description", "rank", "created_at", "file_path"]
]
for i, n in enumerate(use_entities):
created_at = n.get("created_at", "Unknown")