chris/OSVauco
1
0
Fork 0
Code Issues 1 Pull Requests Actions 2 Packages Projects Releases Wiki Activity

fix: use vector_db=RagManagedDb(tier=1) — correct field names for SDK 1.153.1

Browse Source 
RagVectorDbConfig takes vector_db= not rag_managed_db=.
The db type is RagManagedDb, not RagManagedDbConfig.
This commit is contained in:
chrischristiansen-glitch 2026-05-24 18:58:00 +02:00
parent ad8597f434
commit 582967a994
1 changed files with 8 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
agents/rag/setup_corpus.py
View File

@ -3,8 +3,12 @@
setup_corpus.py — Create a Vertex AI RAG Engine corpus and import documents.
Project: propane-will-491900-m5
Explicitly uses Serverless (RagManagedDbConfig basic tier) to avoid
Explicitly uses Serverless (RagManagedDb basic tier) to avoid
Spanner allowlist restrictions on new projects in us-central1.
Tested against vertexai SDK 1.153.1:
RagVectorDbConfig(vector_db=RagManagedDb(tier=1))
tier=1 == BASIC (serverless), tier=2 == ENTERPRISE
"""
import os
@ -23,8 +27,7 @@ GCS_SOURCE = os.environ.get(
f"gs://{PROJECT_ID}-agent-staging/rag-docs/",
)
# RagManagedDbConfig.Tier enum may not exist in older SDK versions.
# tier=1 == BASIC, tier=2 == ENTERPRISE
# tier=1 == BASIC (serverless), tier=2 == ENTERPRISE
_TIER_BASIC = 1
@ -81,8 +84,8 @@ def get_or_create_corpus() -> RagCorpus:
corpus = rag.create_corpus(
display_name=CORPUS_DISPLAY_NAME,
backend_config=rag.RagVectorDbConfig(
rag_managed_db=rag.RagManagedDbConfig(
tier=_TIER_BASIC, # 1 = BASIC (serverless), 2 = ENTERPRISE
vector_db=rag.RagManagedDb(
tier=_TIER_BASIC, # 1 = BASIC (serverless)
)
),
)