feat: add Vertex AI Search and Vector Search data connectors for agentic_rag#791
Merged
eliasecchig merged 2 commits intomainfrom Feb 16, 2026
Merged
feat: add Vertex AI Search and Vector Search data connectors for agentic_rag#791eliasecchig merged 2 commits intomainfrom
eliasecchig merged 2 commits intomainfrom
Conversation
…or for vertex_ai_search - Switch agentic_rag agent from LangChain retriever to native ADK VertexAiSearchTool for vertex_ai_search datastore type - Replace Vertex AI Pipeline-based ingestion with GCS Data Connector approach using Discovery Engine setUpDataConnectorV2 API - Add Terraform null_resource + external data source pattern for managing data connectors and retrieving auto-created data store IDs - Add shell scripts for connector setup, data store ID retrieval, and on-demand sync - Add Makefile sync-data target for triggering manual data syncs - Skip data_ingestion pipeline file copy for vertex_ai_search projects - Update CI/CD pipelines to only include pipeline steps for vertex_ai_vector_search - Update deployment target service.tf files to use external data source references
Contributor
Summary of ChangesHello @eliasecchig, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly enhances the Highlights
Changelog
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
eliasecchig
force-pushed
the
feat/vas-data-connector
branch
from
0218d42 to
4d16d3f
Compare
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request is a significant and well-executed refactoring to introduce support for Vertex AI Search and Vector Search 2.0 data connectors for the agentic_rag agent. The changes are comprehensive, touching everything from the agent logic and data ingestion pipelines to Terraform infrastructure, CI/CD workflows, and documentation. Key improvements include migrating data ingestion to be agent-specific, replacing shell scripts with more maintainable Python scripts for resource management, and simplifying the CLI by removing the --include-data-ingestion flag. The code is generally of high quality. I've identified a few opportunities to reduce code duplication in the Terraform configuration and to improve the configurability of the data processing component. Overall, this is an excellent contribution that enhances the flexibility and usability of the starter pack.
...er_pack/agents/agentic_rag/data_ingestion/data_ingestion_pipeline/components/process_data.py
Show resolved
Hide resolved
eliasecchig
force-pushed
the
feat/vas-data-connector
branch
3 times, most recently
from
d3ec170 to
b5d50b2
Compare
…tic_rag - Migrate data ingestion from shared location to agent-specific `agents/agentic_rag/data_ingestion/` - Replace shell scripts with Python scripts for data connector setup and management - Add Vector Search 2.0 Collections API support alongside Vertex AI Search - Add `setup-datastore` CLI command and sample data for both datastore types - Use dedicated asp-rag GCP projects for agentic_rag e2e tests - Conditionally enable vectorsearch API only when datastore type requires it - Add --wait flag to connector run for blocking sync support
eliasecchig
force-pushed
the
feat/vas-data-connector
branch
from
b5d50b2 to
9d43485
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
agent_starter_pack/data_ingestion/to agent-specificagents/agentic_rag/data_ingestion/setup-datastoreCLI command and sample data for both datastore typesasp-ragGCP projects for agentic_rag e2e testsvectorsearch.googleapis.comAPI only when datastore type requires it--waitflag to connector run for blocking sync supportChanges
--include-data-ingestionflag with auto-derivation from--datastoreoption; addsetup-datastorecommandagentic_ragagent and retrievers to support both Vertex AI Search and Vector Search datastoresagents/agentic_rag/deployment/terraform/; add Vector Search resources