修复 args_hash在使用常规缓存时候才计算导致embedding缓存时没有计算的bug

lightrag/llm.py

@@ -1,12 +1,16 @@
-import os
+import base64
 import copy
-from functools import lru_cache
 import json
+import os
+import struct
+from functools import lru_cache
+from typing import List, Dict, Callable, Any
+
 import aioboto3
 import aiohttp
 import numpy as np
 import ollama
-
+import torch
 from openai import (
     AsyncOpenAI,
     APIConnectionError,
@@ -14,10 +18,7 @@ from openai import (
     Timeout,
     AsyncAzureOpenAI,
 )
-
-import base64
-import struct
-
+from pydantic import BaseModel, Field
 from tenacity import (
     retry,
     stop_after_attempt,
@@ -25,9 +26,7 @@ from tenacity import (
     retry_if_exception_type,
 )
 from transformers import AutoTokenizer, AutoModelForCausalLM
-import torch
-from pydantic import BaseModel, Field
-from typing import List, Dict, Callable, Any
+
 from .base import BaseKVStorage
 from .utils import (
     compute_args_hash,
@@ -867,7 +866,8 @@ async def openai_embedding(
 )
 async def nvidia_openai_embedding(
     texts: list[str],
-    model: str = "nvidia/llama-3.2-nv-embedqa-1b-v1",  # refer to https://build.nvidia.com/nim?filters=usecase%3Ausecase_text_to_embedding
+    model: str = "nvidia/llama-3.2-nv-embedqa-1b-v1",
+    # refer to https://build.nvidia.com/nim?filters=usecase%3Ausecase_text_to_embedding
     base_url: str = "https://integrate.api.nvidia.com/v1",
     api_key: str = None,
     input_type: str = "passage",  # query for retrieval, passage for embedding