v2.0.14

semaphoreui/semaphorev2.0.14Jul 25, 2026by kartik-mem0

AI Summary

The Python SDK gains support for Oracle AI Vector Search and fixes bugs related to OpenSearch wildcard filtering and Milvus schema requirements.

Key Highlights

Added Oracle AI Vector Search provider (`oracledb`) with connection pooling and multiple distance metrics
Fixed OpenSearch wildcard filter to correctly translate `*` into existence queries
Fixed OpenSearch error handling to surface configuration issues instead of returning empty results
Fixed Milvus update operations to respect BM25 schema checks

New Features

Oracle AI Vector Search provider

Full Release Notes

**New Features:**
- **Vector Stores:** Add an Oracle AI Vector Search provider (`oracledb`) with connection pooling, `HNSW`/`IVF` indexes, JSON metadata filtering, and six selectable distance metrics ([#5358](https://github.com/mem0ai/mem0/pull/5358))

**Bug Fixes:**
- **Vector Stores:** Translate a `"*"` filter value in OpenSearch into an `exists` query for every key, not just identity keys. It was previously ignored or matched literally against the string `"*"`, so a wildcard filter returned nothing ([#6522](https://github.com/mem0ai/mem0/pull/6522))
- **Vector Stores:** Re-raise errors from OpenSearch `search()` instead of returning `[]`, so a transport, auth, or index misconfiguration surfaces instead of looking like zero matches. `keyword_search()` still degrades on failure, since it is a best-effort BM25 signal ([#6519](https://github.com/mem0ai/mem0/pull/6519))
- **Vector Stores:** Guard the `text` field in Milvus `update()` behind the `_has_bm25_schema` check, matching `insert()`, so updating a memory in a collection without the BM25 `text`/`sparse` schema no longer fails ([#5705](https://github.com/mem0ai/mem0/pull/5705))