Merge pull request #2229 from BerriAI/litellm_vertex_docs

[Docs] Proxy - Pass vertex_params

docs/my-website/docs/providers/vertex.md

@@ -1,3 +1,6 @@
+import Tabs from '@theme/Tabs';
+import TabItem from '@theme/TabItem';
+
 # VertexAI - Google [Gemini, Model Garden]
 
 <a target="_blank" href="https://colab.research.google.com/github/BerriAI/litellm/blob/main/cookbook/liteLLM_VertextAI_Example.ipynb">
@@ -22,8 +25,36 @@ response = litellm.completion(model="gemini-pro", messages=[{"role": "user", "co
 
 ## OpenAI Proxy Usage 
 
+Here's how to use Vertex AI with the LiteLLM Proxy Server
+
 1. Modify the config.yaml 
 
+<Tabs>
+
+<TabItem value="completion_param" label="Different location per model">
+
+Use this when you need to set a different location for each vertex model
+
+```yaml
+model_list:
+  - model_name: gemini-vision
+    litellm_params:
+      model: vertex_ai/gemini-1.0-pro-vision-001
+      vertex_project: "project-id"
+      vertex_location: "us-central1"
+  - model_name: gemini-vision
+    litellm_params:
+      model: vertex_ai/gemini-1.0-pro-vision-001
+      vertex_project: "project-id2"
+      vertex_location: "us-east"
+```
+
+</TabItem>
+
+<TabItem value="litellm_param" label="One location all vertex models">
+
+Use this when you have one vertex location for all models
+
 ```yaml
 litellm_settings: 
   vertex_project: "hardy-device-38811" # Your Project ID
@@ -35,6 +66,10 @@ model_list:
      model: gemini-pro
 ```
 
+</TabItem>
+
+</Tabs>
+
 2. Start the proxy 
 
 ```bash

litellm/model_prices_and_context_window_backup.json

@@ -687,6 +687,15 @@
         "litellm_provider": "vertex_ai-language-models",
         "mode": "chat"
     },
+    "gemini-1.5-pro-preview-0215": { 
+        "max_tokens": 8192,
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0, 
+        "output_cost_per_token": 0,
+        "litellm_provider": "vertex_ai-language-models",
+        "mode": "chat"
+    },
     "gemini-pro-vision": {
         "max_tokens": 16384,
         "max_output_tokens": 2048,