LarFii commited on
Commit
1b6df6e
·
1 Parent(s): 2f4b338

Fix linting error

Browse files
lightrag/kg/jsondocstatus_impl.py CHANGED
@@ -116,7 +116,7 @@ class JsonDocStatusStorage(DocStatusStorage):
116
  for k, v in self._data.items()
117
  if v["status"] == DocStatus.PROCESSED
118
  }
119
-
120
  async def get_processing_docs(self) -> dict[str, DocProcessingStatus]:
121
  """Get all processing documents"""
122
  return {
 
116
  for k, v in self._data.items()
117
  if v["status"] == DocStatus.PROCESSED
118
  }
119
+
120
  async def get_processing_docs(self) -> dict[str, DocProcessingStatus]:
121
  """Get all processing documents"""
122
  return {
lightrag/llm/openai.py CHANGED
@@ -113,7 +113,9 @@ async def openai_complete_if_cache(
113
  openai_async_client = (
114
  AsyncOpenAI(default_headers=default_headers, api_key=api_key)
115
  if base_url is None
116
- else AsyncOpenAI(base_url=base_url, default_headers=default_headers, api_key=api_key)
 
 
117
  )
118
  kwargs.pop("hashing_kv", None)
119
  kwargs.pop("keyword_extraction", None)
@@ -304,7 +306,9 @@ async def openai_embed(
304
  openai_async_client = (
305
  AsyncOpenAI(default_headers=default_headers, api_key=api_key)
306
  if base_url is None
307
- else AsyncOpenAI(base_url=base_url, default_headers=default_headers, api_key=api_key)
 
 
308
  )
309
  response = await openai_async_client.embeddings.create(
310
  model=model, input=texts, encoding_format="float"
 
113
  openai_async_client = (
114
  AsyncOpenAI(default_headers=default_headers, api_key=api_key)
115
  if base_url is None
116
+ else AsyncOpenAI(
117
+ base_url=base_url, default_headers=default_headers, api_key=api_key
118
+ )
119
  )
120
  kwargs.pop("hashing_kv", None)
121
  kwargs.pop("keyword_extraction", None)
 
306
  openai_async_client = (
307
  AsyncOpenAI(default_headers=default_headers, api_key=api_key)
308
  if base_url is None
309
+ else AsyncOpenAI(
310
+ base_url=base_url, default_headers=default_headers, api_key=api_key
311
+ )
312
  )
313
  response = await openai_async_client.embeddings.create(
314
  model=model, input=texts, encoding_format="float"