Fixed missing imports bug and fixed linting

.gitignore

@@ -23,4 +23,4 @@ examples/input/
 examples/output/
 .DS_Store
 #Remove config.ini from repo
-*.ini
+*.ini

lightrag/api/lightrag_server.py

@@ -684,7 +684,9 @@ def create_app(args):
                         trace_exception(e)
                         logging.error(f"Error indexing file {file_path}: {str(e)}")
 
-                ASCIIColors.info(f"Indexed {len(new_files)} documents from {args.input_dir}")
+                ASCIIColors.info(
+                    f"Indexed {len(new_files)} documents from {args.input_dir}"
+                )
             except Exception as e:
                 logging.error(f"Error during startup indexing: {str(e)}")
         yield
@@ -917,7 +919,6 @@ def create_app(args):
         else:
             logging.warning(f"No content extracted from file: {file_path}")
 
-
     @app.post("/documents/scan", dependencies=[Depends(optional_api_key)])
     async def scan_for_new_documents():
         """

lightrag/api/static/index.html

@@ -622,7 +622,7 @@
           const data = await response.json();
           // Convert indexed_files to array if it's not already
           const files = Array.isArray(data.indexed_files) ? data.indexed_files : data.indexed_files.split(',');
-          
+
           healthInfo.innerHTML = `
             <div class="space-y-4">
               <div class="flex items-center">

lightrag/exceptions.py

@@ -1,6 +1,7 @@
 import httpx
 from typing import Literal
 
+
 class APIStatusError(Exception):
     """Raised when an API response has a status code of 4xx or 5xx."""
 
@@ -8,14 +9,19 @@ class APIStatusError(Exception):
     status_code: int
     request_id: str | None
 
-    def __init__(self, message: str, *, response: httpx.Response, body: object | None) -> None:
+    def __init__(
+        self, message: str, *, response: httpx.Response, body: object | None
+    ) -> None:
         super().__init__(message, response.request, body=body)
         self.response = response
         self.status_code = response.status_code
         self.request_id = response.headers.get("x-request-id")
 
+
 class APIConnectionError(Exception):
-    def __init__(self, *, message: str = "Connection error.", request: httpx.Request) -> None:
+    def __init__(
+        self, *, message: str = "Connection error.", request: httpx.Request
+    ) -> None:
         super().__init__(message, request, body=None)
 
 
@@ -46,10 +52,7 @@ class UnprocessableEntityError(APIStatusError):
 class RateLimitError(APIStatusError):
     status_code: Literal[429] = 429  # pyright: ignore[reportIncompatibleVariableOverride]
 
+
 class APITimeoutError(APIConnectionError):
     def __init__(self, request: httpx.Request) -> None:
         super().__init__(message="Request timed out.", request=request)
-
-
-class BadRequestError(APIStatusError):
-    status_code: Literal[400] = 400  # pyright: ignore[reportIncompatibleVariableOverride]

lightrag/kg/redis_impl.py

@@ -1,6 +1,7 @@
 import os
 from tqdm.asyncio import tqdm as tqdm_async
 from dataclasses import dataclass
+
 # aioredis is a depricated library, replaced with redis
 from redis.asyncio import Redis
 from lightrag.utils import logger

lightrag/llm/azure_openai.py

@@ -42,7 +42,7 @@ __status__ = "Production"
 
 
 import os
-import pipmaster as pm # Pipmaster for dynamic library install
+import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
 if not pm.is_installed("openai"):
@@ -71,6 +71,7 @@ from lightrag.utils import (
 
 import numpy as np
 
+
 @retry(
     stop=stop_after_attempt(3),
     wait=wait_exponential(multiplier=1, min=4, max=10),
@@ -153,6 +154,7 @@ async def azure_openai_complete(
         return locate_json_string_body_from_string(result)
     return result
 
+
 @wrap_embedding_func_with_attrs(embedding_dim=1536, max_token_size=8191)
 @retry(
     stop=stop_after_attempt(3),
@@ -185,4 +187,3 @@ async def azure_openai_embed(
         model=model, input=texts, encoding_format="float"
     )
     return np.array([dp.embedding for dp in response.data])
-

lightrag/llm/bedrock.py

@@ -41,12 +41,12 @@ __author__ = "lightrag Team"
 __status__ = "Production"
 
 
-import sys
 import copy
 import os
 import json
 
-import pipmaster as pm # Pipmaster for dynamic library install
+import pipmaster as pm  # Pipmaster for dynamic library install
+
 if not pm.is_installed("aioboto3"):
     pm.install("aioboto3")
 if not pm.is_installed("tenacity"):
@@ -60,15 +60,11 @@ from tenacity import (
     retry_if_exception_type,
 )
 
-from lightrag.exceptions import (
-    APIConnectionError,
-    RateLimitError,
-    APITimeoutError,
-)
 from lightrag.utils import (
     locate_json_string_body_from_string,
 )
 
+
 class BedrockError(Exception):
     """Generic error for issues related to Amazon Bedrock"""
 

lightrag/llm/hf.py

@@ -42,7 +42,7 @@ __status__ = "Production"
 
 import copy
 import os
-import pipmaster as pm # Pipmaster for dynamic library install
+import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
 if not pm.is_installed("transformers"):
@@ -69,9 +69,11 @@ from lightrag.utils import (
     locate_json_string_body_from_string,
 )
 import torch
+import numpy as np
 
 os.environ["TOKENIZERS_PARALLELISM"] = "false"
 
+
 @lru_cache(maxsize=1)
 def initialize_hf_model(model_name):
     hf_tokenizer = AutoTokenizer.from_pretrained(
@@ -155,7 +157,6 @@ async def hf_model_if_cache(
     return response_text
 
 
-
 async def hf_model_complete(
     prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
 ) -> str:

lightrag/llm/jina.py

@@ -39,7 +39,7 @@ __author__ = "lightrag Team"
 __status__ = "Production"
 
 import os
-import pipmaster as pm # Pipmaster for dynamic library install
+import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
 if not pm.is_installed("lmdeploy"):
@@ -47,25 +47,8 @@ if not pm.is_installed("lmdeploy"):
 if not pm.is_installed("tenacity"):
     pm.install("tenacity")
 
-from tenacity import (
-    retry,
-    stop_after_attempt,
-    wait_exponential,
-    retry_if_exception_type,
-)
-
-from lightrag.utils import (
-    wrap_embedding_func_with_attrs,
-    locate_json_string_body_from_string,
-    safe_unicode_decode,
-    logger,
-)
-
-from lightrag.types import GPTKeywordExtractionFormat
-from functools import lru_cache
 
 import numpy as np
-from typing import Union
 import aiohttp
 
 
@@ -101,4 +84,3 @@ async def jina_embed(
     }
     data_list = await fetch_data(url, headers, data)
     return np.array([dp["embedding"] for dp in data_list])
-

lightrag/llm/lmdeploy.py

@@ -40,7 +40,7 @@ __version__ = "1.0.0"
 __author__ = "lightrag Team"
 __status__ = "Production"
 
-import pipmaster as pm # Pipmaster for dynamic library install
+import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
 if not pm.is_installed("lmdeploy"):
@@ -63,6 +63,7 @@ from tenacity import (
 
 from functools import lru_cache
 
+
 @lru_cache(maxsize=1)
 def initialize_lmdeploy_pipeline(
     model,
@@ -187,4 +188,4 @@ async def lmdeploy_model_if_cache(
         session_id=1,
     ):
         response += res.response
-    return response
+    return response

lightrag/llm/lollms.py

@@ -62,11 +62,13 @@ __status__ = "Production"
 __project_url__ = "https://github.com/ParisNeo/lollms"
 __doc_url__ = "https://github.com/ParisNeo/lollms/docs"
 import sys
+
 if sys.version_info < (3, 9):
     from typing import AsyncIterator
 else:
     from collections.abc import AsyncIterator
-import pipmaster as pm # Pipmaster for dynamic library install
+import pipmaster as pm  # Pipmaster for dynamic library install
+
 if not pm.is_installed("aiohttp"):
     pm.install("aiohttp")
 if not pm.is_installed("tenacity"):
@@ -89,6 +91,7 @@ from lightrag.exceptions import (
 from typing import Union, List
 import numpy as np
 
+
 @retry(
     stop=stop_after_attempt(3),
     wait=wait_exponential(multiplier=1, min=4, max=10),
@@ -185,7 +188,6 @@ async def lollms_model_complete(
     )
 
 
-
 async def lollms_embed(
     texts: List[str], embed_model=None, base_url="http://localhost:9600", **kwargs
 ) -> np.ndarray:
@@ -219,4 +221,4 @@ async def lollms_embed(
                 result = await response.json()
                 embeddings.append(result["vector"])
 
-        return np.array(embeddings)
+        return np.array(embeddings)

lightrag/llm/nvidia_openai.py

@@ -41,15 +41,14 @@ __author__ = "lightrag Team"
 __status__ = "Production"
 
 
-
 import sys
 import os
 
 if sys.version_info < (3, 9):
-    from typing import AsyncIterator
+    pass
 else:
-    from collections.abc import AsyncIterator
-import pipmaster as pm # Pipmaster for dynamic library install
+    pass
+import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
 if not pm.is_installed("openai"):
@@ -70,15 +69,12 @@ from tenacity import (
 
 from lightrag.utils import (
     wrap_embedding_func_with_attrs,
-    locate_json_string_body_from_string,
-    safe_unicode_decode,
-    logger,
 )
 
-from lightrag.types import GPTKeywordExtractionFormat
 
 import numpy as np
 
+
 @wrap_embedding_func_with_attrs(embedding_dim=2048, max_token_size=512)
 @retry(
     stop=stop_after_attempt(3),

lightrag/llm/ollama.py

@@ -41,11 +41,12 @@ __author__ = "lightrag Team"
 __status__ = "Production"
 
 import sys
+
 if sys.version_info < (3, 9):
     from typing import AsyncIterator
 else:
     from collections.abc import AsyncIterator
-import pipmaster as pm # Pipmaster for dynamic library install
+import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
 if not pm.is_installed("ollama"):
@@ -114,6 +115,7 @@ async def ollama_model_if_cache(
     else:
         return response["message"]["content"]
 
+
 async def ollama_model_complete(
     prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
 ) -> Union[str, AsyncIterator[str]]:
@@ -129,6 +131,7 @@ async def ollama_model_complete(
         **kwargs,
     )
 
+
 async def ollama_embedding(texts: list[str], embed_model, **kwargs) -> np.ndarray:
     """
     Deprecated in favor of `embed`.
@@ -152,4 +155,4 @@ async def ollama_embed(texts: list[str], embed_model, **kwargs) -> np.ndarray:
     kwargs["headers"] = headers
     ollama_client = ollama.Client(**kwargs)
     data = ollama_client.embed(model=embed_model, input=texts)
-    return data["embeddings"]
+    return data["embeddings"]

lightrag/llm/openai.py

@@ -41,7 +41,6 @@ __author__ = "lightrag Team"
 __status__ = "Production"
 
 
-
 import sys
 import os
 
@@ -49,7 +48,7 @@ if sys.version_info < (3, 9):
     from typing import AsyncIterator
 else:
     from collections.abc import AsyncIterator
-import pipmaster as pm # Pipmaster for dynamic library install
+import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
 if not pm.is_installed("openai"):
@@ -78,6 +77,7 @@ from lightrag.types import GPTKeywordExtractionFormat
 import numpy as np
 from typing import Union
 
+
 @retry(
     stop=stop_after_attempt(3),
     wait=wait_exponential(multiplier=1, min=4, max=10),
@@ -141,7 +141,6 @@ async def openai_complete_if_cache(
         return content
 
 
-
 async def openai_complete(
     prompt, system_prompt=None, history_messages=[], keyword_extraction=False, **kwargs
 ) -> Union[str, AsyncIterator[str]]:
@@ -205,7 +204,6 @@ async def nvidia_openai_complete(
     return result
 
 
-
 @wrap_embedding_func_with_attrs(embedding_dim=1536, max_token_size=8192)
 @retry(
     stop=stop_after_attempt(3),

lightrag/llm/siliconcloud.py

@@ -39,23 +39,18 @@ __author__ = "lightrag Team"
 __status__ = "Production"
 
 import sys
-import copy
-import os
-import json
 
 if sys.version_info < (3, 9):
-    from typing import AsyncIterator
+    pass
 else:
-    from collections.abc import AsyncIterator
-import pipmaster as pm # Pipmaster for dynamic library install
+    pass
+import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
 if not pm.is_installed("lmdeploy"):
     pm.install("lmdeploy")
 
 from openai import (
-    AsyncOpenAI,
-    AsyncAzureOpenAI,
     APIConnectionError,
     RateLimitError,
     APITimeoutError,
@@ -67,19 +62,12 @@ from tenacity import (
     retry_if_exception_type,
 )
 
-from lightrag.utils import (
-    wrap_embedding_func_with_attrs,
-    locate_json_string_body_from_string,
-    safe_unicode_decode,
-    logger,
-)
-
-from lightrag.types import GPTKeywordExtractionFormat
-from functools import lru_cache
 
 import numpy as np
-from typing import Union
 import aiohttp
+import base64
+import struct
+
 
 @retry(
     stop=stop_after_attempt(3),

lightrag/llm/zhipu.py

@@ -45,18 +45,16 @@ import re
 import json
 
 if sys.version_info < (3, 9):
-    from typing import AsyncIterator
+    pass
 else:
-    from collections.abc import AsyncIterator
-import pipmaster as pm # Pipmaster for dynamic library install
+    pass
+import pipmaster as pm  # Pipmaster for dynamic library install
 
 # install specific modules
 if not pm.is_installed("zhipuai"):
     pm.install("zhipuai")
 
 from openai import (
-    AsyncOpenAI,
-    AsyncAzureOpenAI,
     APIConnectionError,
     RateLimitError,
     APITimeoutError,
@@ -70,17 +68,15 @@ from tenacity import (
 
 from lightrag.utils import (
     wrap_embedding_func_with_attrs,
-    locate_json_string_body_from_string,
-    safe_unicode_decode,
     logger,
 )
 
 from lightrag.types import GPTKeywordExtractionFormat
-from functools import lru_cache
 
 import numpy as np
 from typing import Union, List, Optional, Dict
 
+
 @retry(
     stop=stop_after_attempt(3),
     wait=wait_exponential(multiplier=1, min=4, max=10),
@@ -247,4 +243,4 @@ async def zhipu_embedding(
         except Exception as e:
             raise Exception(f"Error calling ChatGLM Embedding API: {str(e)}")
 
-    return np.array(embeddings)
+    return np.array(embeddings)

lightrag/storage.py

@@ -6,7 +6,6 @@ from dataclasses import dataclass
 from typing import Any, Union, cast, Dict
 import networkx as nx
 import numpy as np
-import pipmaster as pm
 
 from nano_vectordb import NanoVectorDB
 import time

lightrag/types.py

@@ -1,6 +1,7 @@
 from pydantic import BaseModel
 from typing import List
 
+
 class GPTKeywordExtractionFormat(BaseModel):
     high_level_keywords: List[str]
     low_level_keywords: List[str]

lightrag/utils.py

@@ -535,7 +535,8 @@ class CacheData:
     min_val: Optional[float] = None
     max_val: Optional[float] = None
     mode: str = "default"
-    cache_type: str ="query"
+    cache_type: str = "query"
+
 
 async def save_to_cache(hashing_kv, cache_data: CacheData):
     if hashing_kv is None or hasattr(cache_data.content, "__aiter__"):

requirements.txt

@@ -1,7 +1,6 @@
 accelerate
 aiofiles
 aiohttp
-redis
 asyncpg
 configparser
 
@@ -30,6 +29,7 @@ python-docx
 python-dotenv
 python-pptx
 pyvis
+redis
 setuptools
 sqlalchemy
 tenacity
@@ -39,4 +39,3 @@ tenacity
 tiktoken
 tqdm
 xxhash
-