scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 86

docs fix

Browse source
This commit is contained in:
Ishaan Jaffer 2025-10-09 18:56:15 -07:00
parent 25a001c65e
commit 68a6e4aa27
3 changed files with 9 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
docs/my-website/docs/providers/vertex_self_deployed.md
View file

@ -135,7 +135,7 @@ Deploy Gemma models on custom Vertex AI prediction endpoints with OpenAI-compati
model_list:
- model_name: gemma-model
litellm_params:
model: vertex_ai/gemma/gemma-3-12b-it-1759525599171
model: vertex_ai/gemma/gemma-3-12b-it-1222199011122
api_base: https://ENDPOINT.us-central1-PROJECT.prediction.vertexai.goog/v1/projects/PROJECT_ID/locations/us-central1/endpoints/ENDPOINT_ID:predict
vertex_project: "my-project-id"
vertex_location: "us-central1"
@ -168,7 +168,7 @@ curl http://0.0.0.0:4000/v1/chat/completions \
from litellm import completion
response = completion(
model="vertex_ai/gemma/gemma-3-12b-it-1759525599171",
model="vertex_ai/gemma/gemma-3-12b-it-1222199011122",
messages=[{"role": "user", "content": "What is machine learning?"}],
api_base="https://ENDPOINT.us-central1-PROJECT.prediction.vertexai.goog/v1/projects/PROJECT_ID/locations/us-central1/endpoints/ENDPOINT_ID:predict",
vertex_project="my-project-id",

2
litellm/llms/vertex_ai/vertex_gemma_models/main.py
View file

@ -7,7 +7,7 @@ with @requestFormat: "chatCompletions" and returns responses wrapped in 'predict
Usage:
response = litellm.completion(
model="vertex_ai/gemma/gemma-3-12b-it-1759525599171",
model="vertex_ai/gemma/gemma-3-12b-it-1222199011122",
messages=[{"role": "user", "content": "What is machine learning?"}],
vertex_project="your-project-id",
vertex_location="us-central1",

12
tests/test_litellm/llms/vertex_ai/vertex_gemma_models/test_vertex_gemma_transformation.py
View file

@ -42,8 +42,8 @@ class TestVertexGemmaCompletion:
Expected Vertex Response:
{
"deployedModelId": "1207280419999999999",
"model": "projects/993702345710/locations/us-central1/models/gemma-3-12b-it-1759525599171",
"modelDisplayName": "gemma-3-12b-it-1759525599171",
"model": "projects/993702345710/locations/us-central1/models/gemma-3-12b-it-1222199011122",
"modelDisplayName": "gemma-3-12b-it-1222199011122",
"modelVersionId": "1",
"predictions": {
"choices": [
@ -79,8 +79,8 @@ class TestVertexGemmaCompletion:
# Real Vertex response from user's spec
mock_vertex_response = {
"deployedModelId": "1207280419999999999",
"model": "projects/993702345710/locations/us-central1/models/gemma-3-12b-it-1759525599171",
"modelDisplayName": "gemma-3-12b-it-1759525599171",
"model": "projects/993702345710/locations/us-central1/models/gemma-3-12b-it-1222199011122",
"modelDisplayName": "gemma-3-12b-it-1222199011122",
"modelVersionId": "1",
"predictions": {
"choices": [
@ -122,7 +122,7 @@ class TestVertexGemmaCompletion:
# Call litellm.acompletion()
response = await litellm.acompletion(
model="vertex_ai/gemma/gemma-3-12b-it-1759525599171",
model="vertex_ai/gemma/gemma-3-12b-it-1222199011122",
messages=[{"role": "user", "content": "What is machine learning?"}],
max_tokens=100,
api_base="https://32277599999999999.us-central1-10582012152.prediction.vertexai.goog/v1/projects/PROJECT_ID/locations/us-central1/endpoints/ENDPOINT_ID:predict",
@ -162,7 +162,7 @@ class TestVertexGemmaCompletion:
assert response.object == "chat.completion"
assert response.created == 1759863903
# Model name has the gemma/ prefix stripped during processing
assert response.model == "gemma-3-12b-it-1759525599171"
assert response.model == "gemma-3-12b-it-1222199011122"
# Validate choices
assert len(response.choices) == 1