github-featured/google--adk-python
2
0
Fork 0
Code Issues Pull Requests Actions 7 Deployments Models Agent Notes Packages Projects Releases Wiki Activity

fix(deps): bump google-genai minimum to >=1.64.0 for gemini-embedding-2-preview

Browse Source 
The gemini-embedding-2-preview model requires the Vertex AI
:embedContent endpoint instead of the legacy :predict endpoint used
by older models (text-embedding-004, text-embedding-005).

In google-genai <1.64.0, embed_content() unconditionally routed to
:predict on Vertex AI, which returns FAILED_PRECONDITION for this
model.

v1.64.0 (googleapis/python-genai@af40cc6) introduced model-aware
dispatch in embed_content(): models with "gemini" in the name are
routed to :embedContent via t_is_vertex_embed_content_model(), while
older text-embedding-* models continue to use :predict.

This version also enforces a single-content-per-call limit for the
embedContent API, which is why FilesRetrieval sets embed_batch_size=1.

Co-authored-by: Xiang (Sean) Zhou <seanzhougoogle@google.com>
PiperOrigin-RevId: 883689438
This commit is contained in:
Xiang (Sean) Zhou
2026-03-14 10:33:20 -07:00
committed by Copybara-Service
parent 4010716470
commit f8270c826b
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
pyproject.toml
+1 -1
View File
@@ -44,7 +44,7 @@ dependencies = [
"google-cloud-spanner>=3.56.0, <4.0.0", # For Spanner database
"google-cloud-speech>=2.30.0, <3.0.0", # For Audio Transcription
"google-cloud-storage>=2.18.0, <4.0.0", # For GCS Artifact service
"google-genai>=1.56.0, <2.0.0", # Google GenAI SDK
"google-genai>=1.64.0, <2.0.0", # Google GenAI SDK
"graphviz>=0.20.2, <1.0.0", # Graphviz for graph rendering
"httpx>=0.27.0, <1.0.0", # HTTP client library
"jsonschema>=4.23.0, <5.0.0", # Agent Builder config validation