diff --git a/lightrag/llm/ollama.py b/lightrag/llm/ollama.py
index 3541bd67..296e263e 100644
--- a/lightrag/llm/ollama.py
+++ b/lightrag/llm/ollama.py
@@ -66,6 +66,7 @@ from lightrag.exceptions import (
     RateLimitError,
     APITimeoutError,
 )
+from lightrag.api import __api_version__
 from lightrag.utils import extract_reasoning
 import numpy as np
 from typing import Union
@@ -93,11 +94,12 @@ async def ollama_model_if_cache(
     timeout = kwargs.pop("timeout", None)
     kwargs.pop("hashing_kv", None)
     api_key = kwargs.pop("api_key", None)
-    headers = (
-        {"Content-Type": "application/json", "Authorization": f"Bearer {api_key}"}
-        if api_key
-        else {"Content-Type": "application/json"}
-    )
+    headers = {
+        "Content-Type": "application/json",
+        "User-Agent": f"LightRAG/{__api_version__}",
+    }
+    if api_key:
+        headers["Authorization"] = f"Bearer {api_key}"
     ollama_client = ollama.AsyncClient(host=host, timeout=timeout, headers=headers)
     messages = []
     if system_prompt:
@@ -161,11 +163,12 @@ async def ollama_embedding(texts: list[str], embed_model, **kwargs) -> np.ndarra
 
 async def ollama_embed(texts: list[str], embed_model, **kwargs) -> np.ndarray:
     api_key = kwargs.pop("api_key", None)
-    headers = (
-        {"Content-Type": "application/json", "Authorization": api_key}
-        if api_key
-        else {"Content-Type": "application/json"}
-    )
+    headers = {
+        "Content-Type": "application/json",
+        "User-Agent": f"LightRAG/{__api_version__}",
+    }
+    if api_key:
+        headers["Authorization"] = api_key
     kwargs["headers"] = headers
     ollama_client = ollama.Client(**kwargs)
     data = ollama_client.embed(model=embed_model, input=texts)
diff --git a/lightrag/llm/openai.py b/lightrag/llm/openai.py
index 3f939d62..ca451bcf 100644
--- a/lightrag/llm/openai.py
+++ b/lightrag/llm/openai.py
@@ -73,6 +73,7 @@ from lightrag.utils import (
     logger,
 )
 from lightrag.types import GPTKeywordExtractionFormat
+from lightrag.api import __api_version__
 
 import numpy as np
 from typing import Union
@@ -102,8 +103,13 @@ async def openai_complete_if_cache(
     if api_key:
         os.environ["OPENAI_API_KEY"] = api_key
 
+    default_headers = {
+        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_8) LightRAG/{__api_version__}",
+        "Content-Type": "application/json"
+    }
     openai_async_client = (
-        AsyncOpenAI() if base_url is None else AsyncOpenAI(base_url=base_url)
+        AsyncOpenAI(default_headers=default_headers) if base_url is None 
+        else AsyncOpenAI(base_url=base_url, default_headers=default_headers)
     )
     kwargs.pop("hashing_kv", None)
     kwargs.pop("keyword_extraction", None)
@@ -287,8 +293,13 @@ async def openai_embed(
     if api_key:
         os.environ["OPENAI_API_KEY"] = api_key
 
+    default_headers = {
+        "User-Agent": f"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_8) LightRAG/{__api_version__}",
+        "Content-Type": "application/json"
+    }
     openai_async_client = (
-        AsyncOpenAI() if base_url is None else AsyncOpenAI(base_url=base_url)
+        AsyncOpenAI(default_headers=default_headers) if base_url is None 
+        else AsyncOpenAI(base_url=base_url, default_headers=default_headers)
     )
     response = await openai_async_client.embeddings.create(
         model=model, input=texts, encoding_format="float"