Doc: Mem0 doc update

Author: Dev-Khant

server/services/memory/mem0.mdx

@@ -45,6 +45,10 @@ You'll also need to set up your Mem0 API key as an environment variable: `MEM0_A
   Configuration parameters for memory retrieval (see below)
 </ParamField>
 
+<ParamField path="local_config" type="dict" optional>
+  Configuration for using local LLMs and embedders instead of Mem0's cloud API (see Local Configuration section)
+</ParamField>
+
 <Tip>
   At least one of `user_id`, `agent_id`, or `run_id` must be provided to
   organize memories.
@@ -172,6 +176,42 @@ pipeline = Pipeline([
 ])
 ```
 
+### Using Local Configuration
+
+The `local_config` parameter allows you to use your own LLM and embedding providers instead of Mem0's cloud API. This is useful for self-hosted deployments or when you want more control over the memory processing.
+
+```python
+local_config = {
+    "llm": {
+        "provider": str,  # LLM provider name (e.g., "anthropic", "openai")
+        "config": {
+            # Provider-specific configuration
+            "model": str,  # Model name
+            "api_key": str,  # API key for the provider
+            # Other provider-specific parameters
+        }
+    },
+    "embedder": {
+        "provider": str,  # Embedding provider name (e.g., "openai")
+        "config": {
+            # Provider-specific configuration
+            "model": str,  # Model name
+            # Other provider-specific parameters
+        }
+    }
+}
+
+# Initialize Mem0 memory service with local configuration
+memory = Mem0MemoryService(
+    local_config=local_config,  # Use local LLM for memory processing
+    user_id="user123",          # Unique identifier for the user
+)
+```
+
+<Warning>
+  When using `local_config` do not provide the `api_key` parameter.
+</Warning>
+
 ## Frame Flow
 
 ```mermaid