[Update] Default LLM (#3587)

docs/open-source/features/async-memory.mdx

@@ -202,7 +202,7 @@ async def chat_with_memories(message: str, user_id: str = "default_user") -> str
         # Generate assistant response
         system_prompt = f"You are a helpful AI. Answer the question based on query and memories.\nUser Memories:\n{memories_str}"
         messages = [{"role": "system", "content": system_prompt}, {"role": "user", "content": message}]
-        response = await async_openai_client.chat.completions.create(model="gpt-4o-mini", messages=messages)
+        response = await async_openai_client.chat.completions.create(model="gpt-4.1-nano-2025-04-14", messages=messages)
         assistant_response = response.choices[0].message.content
 
         # Create new memories from the conversation
@@ -249,7 +249,7 @@ async def handle_initialization_errors():
         # Initialize with custom config
         config = MemoryConfig(
             vector_store={"provider": "chroma", "config": {"path": "./chroma_db"}},
-            llm={"provider": "openai", "config": {"model": "gpt-4o-mini"}}
+            llm={"provider": "openai", "config": {"model": "gpt-4.1-nano-2025-04-14"}}
         )
         memory = AsyncMemory(config=config)
         print("AsyncMemory initialized successfully")

docs/open-source/features/custom-fact-extraction-prompt.mdx

@@ -76,7 +76,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }

docs/open-source/features/openai_compatibility.mdx

@@ -27,7 +27,7 @@ messages = [
 user_id = "alice"
 chat_completion = client.chat.completions.create(
     messages=messages,
-    model="gpt-4o-mini",
+    model="gpt-4.1-nano-2025-04-14",
     user_id=user_id
 )
 # Memory saved after this will look like: "Loves Indian food. Allergic to cheese and cannot eat pizza."
@@ -42,7 +42,7 @@ messages = [
 
 chat_completion = client.chat.completions.create(
     messages=messages,
-    model="gpt-4o-mini",
+    model="gpt-4.1-nano-2025-04-14",
     user_id=user_id
 )
 print(chat_completion.choices[0].message.content)
@@ -73,7 +73,7 @@ chat_completion = client.chat.completions.create(
             "content": "What's the capital of France?",
         }
     ],
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
 )
 ```
 

docs/open-source/graph_memory/overview.mdx

@@ -54,7 +54,7 @@ You can also customize the LLM for Graph Memory from the [Supported LLM list](ht
 
 1. **Main Configuration**: If `llm` is set in the main config, it will be used for all graph operations.
 2. **Graph Store Configuration**: If `llm` is set in the graph_store config, it will override the main config `llm` and be used specifically for graph operations.
-3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4o-2024-08-06`) will be used for all graph operations.
+3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4.1-nano-2025-04-14) will be used for all graph operations.
 
 Here's how you can do it:
 
@@ -100,7 +100,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4o",
+            "model": "gpt-4.1-nano-2025-04-14",
             "temperature": 0.2,
             "max_tokens": 2000,
         }
@@ -115,7 +115,7 @@ config = {
         "llm" : {
             "provider": "openai",
             "config": {
-                "model": "gpt-4o-mini",
+                "model": "gpt-4.1-nano-2025-04-14",
                 "temperature": 0.0,
             }
         }
@@ -130,7 +130,7 @@ const config = {
     llm: {
         provider: "openai",
         config: {
-            model: "gpt-4o",
+            model: "gpt-4.1-nano-2025-04-14",
             temperature: 0.2,
             max_tokens: 2000,
         }
@@ -146,7 +146,7 @@ const config = {
         llm: {
             provider: "openai",
             config: {
-                model: "gpt-4o-mini",
+                model: "gpt-4.1-nano-2025-04-14",
                 temperature: 0.0,
             }
         }
@@ -177,7 +177,7 @@ You can also customize the LLM for Graph Memory from the [Supported LLM list](ht
 
 1. **Main Configuration**: If `llm` is set in the main config, it will be used for all graph operations.
 2. **Graph Store Configuration**: If `llm` is set in the graph_store config, it will override the main config `llm` and be used specifically for graph operations.
-3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4o-2024-08-06`) will be used for all graph operations.
+3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4.1-nano-2025-04-142025-04-14) will be used for all graph operations.
 
 Here's how you can do it:
 
@@ -241,7 +241,7 @@ User can also customize the LLM for Graph Memory from the [Supported LLM list](h
 
 1. **Main Configuration**: If `llm` is set in the main config, it will be used for all graph operations.
 2. **Graph Store Configuration**: If `llm` is set in the graph_store config, it will override the main config `llm` and be used specifically for graph operations.
-3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4o-2024-08-06`) will be used for all graph operations.
+3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4.1-nano-2025-04-14) will be used for all graph operations.
 
 Here's how you can do it:
 
@@ -290,7 +290,7 @@ User can also customize the LLM for Graph Memory from the [Supported LLM list](h
 
 1. **Main Configuration**: If `llm` is set in the main config, it will be used for all graph operations.
 2. **Graph Store Configuration**: If `llm` is set in the graph_store config, it will override the main config `llm` and be used specifically for graph operations.
-3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4o-2024-08-06`) will be used for all graph operations.
+3. **Default Configuration**: If no custom LLM is set, the default LLM (`gpt-4.1-nano-2025-04-14) will be used for all graph operations.
 
 Here's how you can do it:
 

docs/open-source/python-quickstart.mdx

@@ -504,7 +504,7 @@ chat_completion = client.chat.completions.create(
             "content": "What's the capital of France?",
         }
     ],
-    model="gpt-4o",
+    model="gpt-4.1-nano-2025-04-14",
 )
 ```