feat(context-grounding): expose index_id on UnifiedQueryResult#1534
Open
feat(context-grounding): expose index_id on UnifiedQueryResult#1534
Conversation
unified_search and unified_search_async already resolve the index by name to get its ID for the API call, but discard it before returning. This adds index_id to UnifiedQueryResult and sets it from the resolved index, so callers can include it in trace spans for debugging. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
github-actions
bot
added
the
test:uipath-langchain
cfauchere
pushed a commit
to UiPath/uipath-langchain-python
that referenced
this pull request
Mar 31, 2026
Depends on UiPath/uipath-python#1534 which exposes index_id on the result. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
cfauchere
pushed a commit
to UiPath/uipath-langchain-python
that referenced
this pull request
Apr 1, 2026
Depends on UiPath/uipath-python#1534. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Extend index_id to all CG operations, not just unified_search: - start_deep_rag / start_deep_rag_async - start_batch_transform / start_batch_transform_async - start_deep_rag_ephemeral / start_deep_rag_ephemeral_async - start_batch_transform_ephemeral / start_batch_transform_ephemeral_async Added index_id field to BatchTransformCreationResponse and DeepRagCreationResponse models. Every CG operation that resolves or receives an index_id now returns it on the response, so traces can include it for debugging. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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
index_idfield toUnifiedQueryResultunified_searchandunified_search_asyncContext
unified_searchresolves the index by name (self.retrieve(name)) to get its ID for the API call (/ecs_/v1.2/search/{index_id}), but discards it before returning. Downstream consumers (uipath-langchain-python, uipath-agents-python) need the index ID to write it to thecontextGroundingTooltrace span for debugging CG issues.Without
index_idin the trace, investigating empty search results requires manual lookup of the index — you can't go from the trace to the CG service logs.No extra API call — the index is already resolved.
Related PRs
index_idfrom tool output)Test plan
unified_searchresult hasindex_idsetunified_search_asyncresult hasindex_idsetindex_idappears incontextGroundingTooltrace span end-to-end🤖 Generated with Claude Code