scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-08 22:21:35 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 78

fix(vertex.md): adding gemini-pro support to docs

Browse source
This commit is contained in:
Krrish Dholakia 2023-12-13 14:38:55 -08:00
parent 7b8851cce5
commit 88d09fc5a7
2 changed files with 31 additions and 11 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
docs/my-website/docs/providers/vertex.md
View file

@ -10,6 +10,16 @@
* run `gcloud auth application-default login` See [Google Cloud Docs](https://cloud.google.com/docs/authentication/external/set-up-adc)
* Alternatively you can set `application_default_credentials.json`
## Sample Usage
```python
import litellm
litellm.vertex_project = "hardy-device-38811" # Your Project ID
litellm.vertex_location = "us-central1" # proj location
response = completion(model="gemini-pro", messages=[{"role": "user", "content": "write code for saying hi from LiteLLM"}])
```
## Set Vertex Project & Vertex Location
All calls using Vertex AI require the following parameters:
* Your Project ID
@ -37,14 +47,10 @@ os.environ["VERTEXAI_LOCATION"] = "us-central1 # Your Location
litellm.vertex_location = "us-central1 # Your Location
```
## Sample Usage
```python
import litellm
litellm.vertex_project = "hardy-device-38811" # Your Project ID
litellm.vertex_location = "us-central1" # proj location
response = completion(model="chat-bison", messages=[{"role": "user", "content": "write code for saying hi from LiteLLM"}])
```
## Gemini
| Model Name | Function Call |
|------------------|--------------------------------------|
| gemini-pro | `completion('gemini-pro', messages)` |
## Chat Models
| Model Name | Function Call |

20
litellm/tests/test_amazing_vertex_completion.py
View file

@ -63,6 +63,21 @@ def load_vertex_ai_credentials():
# Export the temporary file as GOOGLE_APPLICATION_CREDENTIALS
os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = os.path.abspath(temp_file.name)
def test_vertex_ai_sdk():
load_vertex_ai_credentials()
from vertexai.preview.generative_models import GenerativeModel, Part, GenerationConfig
llm_model = GenerativeModel("gemini-pro")
chat = llm_model.start_chat()
print(chat.send_message("write code for saying hi from LiteLLM", generation_config=GenerationConfig(**{})).text)
test_vertex_ai_sdk()
def simple_test_vertex_ai():
try:
load_vertex_ai_credentials()
response = completion(model="gemini-pro", messages=[{"role": "user", "content": "write code for saying hi from LiteLLM"}])
print(f'response: {response}')
except Exception as e:
pytest.fail(f"An exception occurred - {str(e)}")
def test_vertex_ai():
import random
@ -97,8 +112,7 @@ def test_vertex_ai_stream():
test_models = litellm.vertex_chat_models + litellm.vertex_code_chat_models + litellm.vertex_text_models + litellm.vertex_code_text_models
test_models = random.sample(test_models, 4)
# test_models += litellm.vertex_language_models # always test gemini-pro
test_models = ["code-gecko@001"]
test_models += litellm.vertex_language_models # always test gemini-pro
for model in test_models:
try:
if model in ["code-gecko", "code-gecko@001", "code-gecko@002", "code-gecko@latest", "code-bison@001", "text-bison@001"]:
@ -117,7 +131,7 @@ def test_vertex_ai_stream():
assert len(completed_str) > 4
except Exception as e:
pytest.fail(f"Error occurred: {e}")
test_vertex_ai_stream()
# test_vertex_ai_stream()
@pytest.mark.asyncio
async def test_async_vertexai_response():