Add VDB runtime summary observability#2198
Draft
jioffe502 wants to merge 9 commits into
Draft
Conversation
…hybrid-search # Conflicts: # nemo_retriever/src/nemo_retriever/vdb/lancedb.py
jioffe502
force-pushed
the
codex/vdb-runtime-observability
branch
from
dc4a790 to
3f0022e
Compare
jioffe502
force-pushed
the
codex/vdb-runtime-observability
branch
from
3f0022e to
07e295a
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Stacked on #2040. The intended review surface is the final commit on
jioffe502:codex/vdb-runtime-observabilityuntil #2040 lands.Adds a VDB-neutral runtime summary block to pipeline runtime metrics so harness/session artifacts can report which backend target and retrieval mode were actually configured.
describe_vdb_runtime(...)for JSON-safe VDB runtime summariesvdbblock beside the legacyvdb_opin graph pipeline runtime summariesuses_query_textsquery_textsTesting
uv run --extra dev pytest -q tests/test_vdb_runtime.py tests/test_graph_pipeline_cli.pyuvx pre-commit run --all-filespython -m nemo_retriever.examples.graph_pipeline /datasets/nv-ingest/jp20 --run-mode inprocess --evaluation-mode beir --vdb-kwargs-json ...hybrid=true...vdb.retrieval.mode = "hybrid",signals = ["dense_vector", "lexical_text"], anduses_query_texts = true.