-
Notifications
You must be signed in to change notification settings - Fork 0
Dev #134
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
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
…_system_from_json This commit updates the `load_memory_system_from_json` function to include a tier parameter when storing memory vectors. This change allows for more precise handling of memory storage across different tiers (STM, IM, LTM), improving the flexibility and maintainability of the vector storage process.
…ted results This commit modifies the SimilaritySearchTestSuite by adjusting the expected memory IDs, minimum score thresholds, and result limits for various tests. The changes enhance the accuracy of the similarity search validations, ensuring that the tests reflect the latest updates in the memory vector storage logic.
This commit updates the VectorStore class to include content data in the metadata for improved filtering capabilities. It also refines the SimilaritySearchTestSuite by adjusting expected memory IDs and minimum score thresholds, ensuring better alignment with the latest changes in vector storage logic and enhancing the accuracy of similarity search validations.
…ng, content structure, and memory states in SimilaritySearchTestSuite This commit expands the SimilaritySearchTestSuite by introducing new test methods to cover various scenarios, including memory tier transitions, complex metadata filtering, different content structures, and varying memory states. These additions enhance the test coverage and ensure more robust validation of the similarity search functionality.
Similarity search validation
This commit updates the validation documentation for the AttributeSearchStrategy by removing the performance testing section and streamlining the content. The focus is now on functional and edge case validations, ensuring clarity and conciseness in the validation approach.
…earch tests This commit simplifies the vector storage process in the VectorStore class by consolidating the storage logic and improving error handling. It also updates the SimilaritySearchTestSuite to refine metadata filters and expected results, ensuring better alignment with the latest changes in vector storage and enhancing the accuracy of similarity search validations.
…ing obsolete tests This commit refines the SimilaritySearchTestSuite by updating the metadata filter structure to use 'importance_score' instead of 'importance', and adjusting the minimum score threshold for tests. Additionally, it removes several outdated tests related to memory state and content structure, streamlining the test suite for better clarity and focus on relevant scenarios.
This commit introduces a new validation document for the SimilaritySearchStrategy, outlining the comprehensive validation approach, including functional testing, edge case testing, and memory tier testing. The document details the validation methodology, test results, and confirms the robustness of the implementation across various scenarios, ensuring clarity and thoroughness in the validation process.
Similarity search validation
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.
This pull request introduces several updates to the memory vector storage logic, search strategies, and validation test suites. Key changes include refactoring the vector storage method, improving test coverage for similarity search, and simplifying the validation documentation. Below is a breakdown of the most important changes:
Memory Vector Storage Refactor:
store_memory_vectorsmethod by removing the nestedstore_vectorfunction and directly handling vector storage operations for each memory tier (stm,im,ltm). Added error handling for invalid tiers.load_memory_system_from_jsonto explicitly callstore_memory_vectorswith the appropriate tier for each memory entry.Search Strategy Improvements:
searchand_generate_query_vectormethods to improve readability. [1] [2] [3] [4]similarity.py.Validation Documentation Updates:
validation.mdfile, focusing solely on functional and edge case validation. [1] [2] [3]Similarity Search Test Suite Enhancements:
similarity_test_suite.pyto refine expected results, thresholds, and metadata filters. [1] [2] F93fb09bL156R157, [3] [4] [5]run_all_testsmethod to execute all test suites and display a summary.Code Cleanup:
similarity_test_suite.pyto streamline the code.