docs(vertex.md): adding vertex ai model garden support to docs

This commit is contained in:
Krrish Dholakia
2024-02-02 18:42:56 -08:00
parent 5631b3357b
commit aac8106c37
+27 -3
View File
@@ -1,4 +1,4 @@
# VertexAI - Google [Gemini]
# VertexAI - Google [Gemini, Model Garden]
<a target="_blank" href="https://colab.research.google.com/github/BerriAI/litellm/blob/main/cookbook/liteLLM_VertextAI_Example.ipynb">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
@@ -67,16 +67,39 @@ os.environ["VERTEXAI_LOCATION"] = "us-central1 # Your Location
# set directly on module
litellm.vertex_location = "us-central1 # Your Location
```
## Model Garden
| Model Name | Function Call |
|------------------|--------------------------------------|
| llama2 | `completion('vertex_ai/<endpoint_id>', messages)` |
#### Using Model Garden
```python
from litellm import completion
import os
## set ENV variables
os.environ["VERTEXAI_PROJECT"] = "hardy-device-38811"
os.environ["VERTEXAI_LOCATION"] = "us-central1"
response = completion(
model="vertex_ai/<your-endpoint-id>",
messages=[{ "content": "Hello, how are you?","role": "user"}]
)
```
## Gemini Pro
| Model Name | Function Call |
|------------------|--------------------------------------|
| gemini-pro | `completion('gemini-pro', messages)` |
| gemini-pro | `completion('gemini-pro', messages)`, `completion('vertex_ai/gemini-pro', messages)` |
## Gemini Pro Vision
| Model Name | Function Call |
|------------------|--------------------------------------|
| gemini-pro-vision | `completion('gemini-pro-vision', messages)` |
| gemini-pro-vision | `completion('gemini-pro-vision', messages)`, `completion('vertex_ai/gemini-pro-vision', messages)`|
#### Using Gemini Pro Vision
@@ -114,6 +137,7 @@ response = litellm.completion(
print(response)
```
## Chat Models
| Model Name | Function Call |
|------------------|--------------------------------------|