Repository navigation
feat(integrations): add MongoDB-backed memory service - #7512
Closed
theshanbhag wants to merge 14 commits into
Closed
theshanbhag wants to merge 14 commits into
theshanbhag wants to merge 14 commits into
Conversation
Add `use_mongodb_auto_embedding` and `mongodb_auto_embedding_model` to MongoDbToolSettings. When enabled, the search tools send the query as plain text (`query.text`) instead of embedding it through the genai client first: Atlas generates the embedding itself with the Voyage AI model configured on the index's `autoEmbed` field (Atlas Automated Embedding, Preview), so deployments that already store data on Atlas need no Google embedding credentials. The default mode (Google embedding models via `queryVector`) is unchanged. Split from google#7291.
MongoDbSessionService persists sessions, events, and app:/user:-scoped state in MongoDB, exported from google.adk.integrations.mongodb behind the MONGODB_SESSION_SERVICE experimental feature (default on). Concurrency model: within a process a per-session lock serializes append_event; across runner replicas the optimistic-concurrency revision on the session document is the only guard, and the losing writer gets StaleSessionError. Multi-document writes run in a transaction on replica sets / sharded clusters / Atlas; on deployments without transaction support (standalone mongod) the verdict is cached and writes fall back to sequential with the revision check. Optional `ensure_indexes` creates the recommended secondary indexes on first use. mongomock joins the test dependencies for the new unit tests. NO_UNIT_GUIDE=The integration README documents the service, including its document layout, concurrency model, and least-privilege setup; a per-unit guide will follow when the experimental API stabilizes. Split from google#7291.
MongoDbMemoryService ingests session events into a memory collection and recalls them by keyword matching, exported from google.adk.integrations.mongodb behind the MONGODB_MEMORY_SERVICE experimental feature (default on). Ingestion is idempotent (memory documents are keyed by app/user/session/event), and `ensure_indexes` creates the app/user/keywords index on first use. Retrieval is intentionally keyword-only: it needs no embedding model, no Google credentials, and no vector index, so it works on any MongoDB deployment at zero per-query cost. Vector recall is a possible follow-up building on this integration's own search tools. NO_UNIT_GUIDE=The integration README documents the service, including its storage layout and least-privilege setup; a per-unit guide will follow when the experimental API stabilizes. Split from google#7291.
9 tasks done
9 tasks done
…b-session-service # Conflicts: # constraints-3.11.txt # constraints-3.12.txt # constraints-3.13.txt # constraints-3.14.txt
…n MongoDbSessionService Review follow-up from google#7533: list_sessions fetched each user's state with a separate find_one per user (N+1); it now issues a single $in query against the user_states collection. Index creation on first use is also serialized with a thread lock (double-checked flag), so concurrent first calls no longer issue duplicate create_index calls. Addresses gemini-code-assist review comments on google#7533.
Review follow-up from google#7533: add_session_to_memory issued one replace_one round-trip per event; it now batches all upserts into a single bulk_write (ordered=False). First-use index creation is serialized with a thread lock (double-checked flag) so concurrent startup calls no longer issue duplicate create_index calls. Tests carry a shim for mongomock's BulkOperationBuilder, which rejects the `sort` key pymongo 4.9+ adds to bulk operations. Addresses gemini-code-assist review comments on google#7533.
…b-session-service # Conflicts: # docs/guides/integrations/mongodb/mongodb_toolset/index.md # src/google/adk/integrations/mongodb/README.md # tests/unittests/integrations/mongodb/test_search_tool.py
These local-only sample/utility files (mongodb_samples/, .codegraph/, setup_mongodb_sample.py) were never meant to be committed; a git add -A in the merge commit included them by mistake. They stay on disk, just untracked again.
# Conflicts: # src/google/adk/integrations/mongodb/README.md
copybara-service Bot
pushed a commit
that referenced
this pull request
Oct 23, 2026
Merge #7512 PiperOrigin-RevId: 1005681851
Collaborator
|
Thank you @theshanbhag for your contribution! 🎉 Your changes have been successfully imported and merged via Copybara in commit cbca417. Closing this PR as the changes are now in the main branch. |
adk-bot
pushed a commit
that referenced
this pull request
Oct 23, 2026
Merge #7512 PiperOrigin-RevId: 1005681851
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
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.
Adds
MongoDbMemoryService: session events ingested into a keyword-indexed memory collection for long-term recall, exported fromgoogle.adk.integrations.mongodbbehind the newMONGODB_MEMORY_SERVICEexperimental feature (default on, matching the integration's existing flags).Split 4 of 4 from #7291 (reviewer-requested split). Contains the session-service PR (#7511) beneath it; the memory-service commits are the last ones.
Please ensure you have read the contribution guide before creating a pull request.
Link to Issue or Description of Change
Problem:
ADK's MongoDB integration has no long-term memory service; sessions end, and their content is not recallable across sessions.
Solution:
MongoDbMemoryServicestores one memory document per ingested event, keyed by<app_name>/<user_id>/<session_id>/<event_id>(so re-ingesting a session overwrites rather than duplicates), each carrying the lowercase keywords extracted from its text (stop-word list customizable).search_memorymatches documents whose keyword array intersects the query's keywords, scoped per app and user.ensure_indexes=Trueoptionally creates theapp_user_keywordsmultikey index.Keyword-only retrieval is intentional (reviewer question on #7291): it needs no embedding model, no Google credentials, and no vector index, so it works on any MongoDB deployment (including standalone and free-tier clusters) at zero per-query cost and with predictable behavior. Vector recall is a reasonable follow-up that can build directly on this integration's own
mongodb_vector_searchtooling; this PR keeps the first version dependency-free. This rationale is stated in the README as well.Not in this PR, per the #7291 review: pickling for Agent Engine (comes with the follow-up that wires the services into Agent Engine).
NO_UNIT_GUIDE=The integration README documents the service, including its storage layout and least-privilege setup; a per-unit guide will follow when the experimental API stabilizes.
Testing Plan
Unit Tests:
pytest tests/unittests/integrations/mongodb/ tests/unittests/features/→ 119 passed (mongomock-backed): ingest/recall round trips, per-user scoping, ingestion idempotency, stop-word handling, index creation, and feature-registry tests. All pre-commit hooks pass.Manual End-to-End (E2E) Tests:
Against a live Atlas 8.0.34 cluster: ingesting sessions and recalling by keyword returns the ingested events, memories are scoped per user, and re-ingesting the same session never duplicates entries.
Checklist