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

fix: drop backend_config from create_corpus — rely on pre-flight PATCH alone

Browse Source 
SDK 1.153.1 has a bug in set_backend_config where it calls .CopyFrom()
on RagManagedDb which is not a real protobuf message.
The project-level ragEngineConfig PATCH already sets basic tier,
so passing backend_config is unnecessary and breaks corpus creation.
This commit is contained in:
chrischristiansen-glitch 2026-05-24 19:04:31 +02:00
parent 46b3c52607
commit 2beb6a359d
1 changed files with 11 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
agents/rag/setup_corpus.py
View File

@ -3,12 +3,9 @@
setup_corpus.py — Create a Vertex AI RAG Engine corpus and import documents. setup_corpus.py — Create a Vertex AI RAG Engine corpus and import documents.
Project: propane-will-491900-m5 Project: propane-will-491900-m5
Explicitly uses Serverless (RagManagedDb) to avoid Spanner allowlist Serverless mode is controlled via the project-level ragEngineConfig PATCH
restrictions on new projects in us-central1. (ensure_serverless_engine_config). Passing backend_config to create_corpus
triggers a SDK 1.153.1 bug and must be omitted.
Tested against vertexai SDK 1.153.1:
RagVectorDbConfig(vector_db=RagManagedDb())
RagManagedDb is a no-arg marker class — selecting it is sufficient for serverless.
""" """
import os import os
@ -31,7 +28,8 @@ GCS_SOURCE = os.environ.get(
def ensure_serverless_engine_config() -> None: def ensure_serverless_engine_config() -> None:
""" """
Pre-flight: set project-level RAG Engine Config to basic (serverless) tier. Pre-flight: set project-level RAG Engine Config to basic (serverless) tier.
Idempotent — safe to re-run. This is what actually controls the backend — backend_config in create_corpus
is intentionally omitted due to SDK bug in 1.153.1.
""" """
print("Ensuring RAG Engine Config is set to serverless (basic) tier...") print("Ensuring RAG Engine Config is set to serverless (basic) tier...")
endpoint = ( endpoint = (
@ -71,21 +69,17 @@ def ensure_serverless_engine_config() -> None:
def get_or_create_corpus() -> RagCorpus: def get_or_create_corpus() -> RagCorpus:
"""Return existing corpus by display name, or create a new serverless one.""" """Return existing corpus by display name, or create a new one."""
for c in rag.list_corpora(): for c in rag.list_corpora():
if c.display_name == CORPUS_DISPLAY_NAME: if c.display_name == CORPUS_DISPLAY_NAME:
print(f"Corpus '{CORPUS_DISPLAY_NAME}' already exists: {c.name}") print(f"Corpus '{CORPUS_DISPLAY_NAME}' already exists: {c.name}")
return c return c
print(f"Creating corpus '{CORPUS_DISPLAY_NAME}' in {LOCATION} (serverless)...") print(f"Creating corpus '{CORPUS_DISPLAY_NAME}' in {LOCATION}...")
corpus = rag.create_corpus( # NOTE: backend_config is intentionally omitted.
display_name=CORPUS_DISPLAY_NAME, # SDK 1.153.1 has a bug where passing any backend_config crashes.
# RagManagedDb() is a no-arg marker class in SDK 1.153.1 # Serverless mode is already guaranteed by ensure_serverless_engine_config().
# Selecting it routes to serverless managed DB (basic tier) corpus = rag.create_corpus(display_name=CORPUS_DISPLAY_NAME)
backend_config=rag.RagVectorDbConfig(
vector_db=rag.RagManagedDb()
),
)
print(f"✓ Corpus created: {corpus.name}") print(f"✓ Corpus created: {corpus.name}")
return corpus return corpus