mem0ai
Support Direct Import in the open source lib
Description
Support Direct Import in the open source lib Add infer parameter to control memory inference behavior
Added a new optional boolean parameter 'infer' to the add() method that allows controlling whether inference should be used when adding memories. When infer=False, the method will directly embed and store the raw messages without performing any inference or deduction, providing a faster and simpler memory storage option. This gives users more flexibility in how memories are processed and stored.
The default value is True to maintain backward compatibility.
Another change: to make the UT could run locally, I have to fix the test_proxy.py
Type of change
- [x] New feature (non-breaking change which adds functionality)
How Has This Been Tested?
Replaced the high-level mocking of _add_to_vector_store with detailed component-level mocks to provide better test coverage and validation of internal behaviors.
- [x] Unit Test
Checklist:
- [x] My code follows the style guidelines of this project
- [x] I have performed a self-review of my own code
- [x] I have commented my code, particularly in hard-to-understand areas
- [x] My changes generate no new warnings
- [x] I have added tests that prove my fix is effective or that my feature works
- [x] New and existing unit tests pass locally with my changes
- [x] Any dependent changes have been merged and published in downstream modules
- [x] I have checked my code and corrected any misspellings
Maintainer Checklist
- [ ] closes #2103
- [ ] Made sure Checks passed
