harsh/embeddings/refactor#62
Merged
harshkedia177 merged 10 commits intomainfrom Mar 25, 2026
Merged
Conversation
Owner
harshkedia177
commented
Mar 25, 2026
harshkedia177
commented
- refactor: enhance writable storage initialization and error messaging in Axon CLI
- feat(embeddings): switch to nomic-embed-text-v1.5 with passage_embed/query_embed
- feat(embeddings): add token budget to text generation
- feat(storage): switch to FLOAT[384] schema and parameterized vector queries
- feat(embeddings): add model metadata to meta.json and auto-migration on model change
- test(embeddings): add integration test with real nomic model
- fix(embeddings): apply _MAX_TEXT_CHARS in embed_nodes, treat missing model key as mismatch
- feat(embeddings): enhance embedding management and background processing
… in Axon CLI - Updated the `_initialize_writable_storage` function to include an `auto_index` parameter, allowing for more flexible error handling when no index exists. - Improved error messages to guide users on running the indexing command. - Adjusted the `setup` command output to clarify configuration instructions for Claude Code and Cursor. - Modified tests to reflect changes in expected output for the setup command.
…ueries - Change Embedding table from DOUBLE[] to FLOAT[384] (fixed-dimension, 32-bit) - Replace inline vector literal with parameterized query using CAST($vec, 'FLOAT[384]') - Remove _safe_vec_literal helper and unused math import
…model key as mismatch
- Introduced functions to check for existing index metadata and database, improving the initialization process. - Added background embedding generation capability, allowing embeddings to be processed asynchronously. - Updated the embedding model handling to ensure current embeddings are used, with automatic re-embedding on model changes. - Adjusted default batch size for embeddings from 128 to 32 for better performance. - Enhanced tests to cover new embedding migration and initialization scenarios.
# Conflicts: # src/axon/cli/main.py
…ctor # Conflicts: # src/axon/core/embeddings/embedder.py # src/axon/core/ingestion/pipeline.py # src/axon/core/storage/base.py # tests/core/test_embedder.py
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.