v2.0.14

mem0ai/mem0v2.0.14Jul 25, 2026by kartik-mem0

AI Summary

This release adds Oracle AI Vector Search provider and fixes various vector store filter and error handling issues.

Key Highlights

Add Oracle AI Vector Search provider with connection pooling, HNSW/IVF indexes, and JSON metadata filtering
Fix wildcard filter value in OpenSearch by converting to exists query
Re-raise errors from OpenSearch search() instead of returning empty array
Guard text field in Milvus update() behind _has_bm25_schema check

New Features

Oracle AI Vector Search provider (oracledb) with six selectable distance metrics

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))