Epic 150: real AI semantic meaning via ONNX entity embeddings - #110
Merged
Conversation
Add OnnxEntityEmbedder to spatialrust-semantic behind a model feature: it runs entity feature vectors through an already-open model session with explicit copy policy and produces an Embedding for the semantic search index. Wire the facade semantic-model feature and add an integration test that drives a committed 134-byte ONNX Add fixture through the real ONNX Runtime path (feature -> session -> embedding -> search).
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Connects real ONNX inference to spatial semantic entities, turning point-cloud features into searchable embeddings.
Deliverables
spatialrust-semantic::OnnxEntityEmbedder(modelfeature): embeds entity feature vectors through an already-openModelSessionwith explicitCopyPolicy, validating feature count, finiteness, output shape, and bytes. Never loads a model or picks a backend.double_dynamic.onnxfixture (Add: [1,3]→[1,3] doubling) driving a facade integration test through the real ONNX Runtime: feature → session →Embedding→SemanticSearchIndex.semantic-modelfeature wiring; 9 semantic unit tests + 2 ONNX integration tests.Contract
semanticdefault build andspatialrust-semanticdefault stay dependency-light; ONNX remains behindai-onnxruntime.Verification
cargo test -p spatialrust-semantic --features model— 9 testscargo test -p spatialrust --features "ai-onnxruntime semantic-model" --test onnx_semantic— 2 tests-D warningsclean;cargo fmt --all --checkclean; workspace tests pass