doc updates

Author: thushan

docs/content/integrations/backend/litellm.md

@@ -290,23 +290,23 @@ LiteLLM supports provider-prefixed model names:
 ```python
 import openai
 
-client = openai.OpenAI(base_url="http://localhost:40114/olla/openai")
+client = openai.OpenAI(base_url="http://localhost:40114/olla/litellm/v1")
 
-# Routes to OpenAI
+# Routes to OpenAI via LiteLLM
 response = client.chat.completions.create(
-    model="gpt-4",
+    model="openai/gpt-4",
     messages=[{"role": "user", "content": "Hello!"}]
 )
 
 # Routes to Anthropic via LiteLLM
 response = client.chat.completions.create(
-    model="claude-4-opus",
+    model="anthropic/claude-3-opus-20240229",
     messages=[{"role": "user", "content": "Hello!"}]
 )
 
 # Routes to AWS Bedrock via LiteLLM
 response = client.chat.completions.create(
-    model="claude-4-bedrock",
+    model="bedrock/anthropic.claude-3-sonnet",
     messages=[{"role": "user", "content": "Hello!"}]
 )
 ```

docs/content/integrations/backend/lmstudio.md

@@ -13,7 +13,7 @@ keywords: LM Studio, Olla, LLM proxy, local inference, OpenAI compatible, model
     </tr>
     <tr>
         <th>Since</th>
-        <td>Olla <code>v0.0.7</code></td>
+        <td>Olla <code>v0.0.12</code></td>
     </tr>
     <tr>
         <th>Type</th>

docs/content/usage.md

@@ -35,6 +35,7 @@ Perfect for enthusiasts running multiple LLM instances:
 ```yaml
 # Home lab config - local first, cloud fallback
 discovery:
+  type: "static"
   static:
     endpoints:
       - name: "rtx-4090-mobile"
@@ -86,6 +87,7 @@ Seamlessly combine local and cloud models with native LiteLLM support:
 ```yaml
 # Hybrid setup with LiteLLM
 discovery:
+  type: "static"
   static:
     endpoints:
       # Local models for privacy/cost