Commit Graph
313 Commits
Author SHA1 Message Date
kartik-mem0andClaude Opus 4.6 b38f2ef45c fix(qdrant): deduplicate $or/$not keys and add icontains debug warning
Memory._process_metadata_filters() renames OR→$or and NOT→$not, but
effective_filters also retains the original OR/NOT keys from the
deepcopy of input_filters. Without dedup, the same sub-conditions were
evaluated twice in the Qdrant filter.

Normalize the filter dict upfront so $or/$not/$and map to OR/NOT/AND
and only the first occurrence is kept. Also replace the fragile
value.get("contains") or value.get("icontains") pattern with explicit
key lookup, and add a logger.debug for icontains explaining that Qdrant
MatchText case sensitivity depends on full-text index configuration.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 19:04:42 +05:30
kartik-mem0andClaude Opus 4.6 b1dbd08c63 fix(qdrant): handle $or/$not keys injected by Memory middleware
Memory._process_metadata_filters() renames OR→$or and NOT→$not before
passing filters to the vector store. Without this fix, $or/$not keys
with list values hit _build_field_condition and crash with
ValidationError (MatchValue rejects lists).

Normalize $or→OR, $not→NOT, $and→AND at the start of _create_filter
so both naming conventions work.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-21 18:32:57 +05:30
kartik-mem0andClaude Sonnet 4.6 269d784c0f test(qdrant): add edge-case tests for enhanced metadata filtering
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-21 18:08:31 +05:30
kartik-mem0andClaude Sonnet 4.6 72c2a7f322 fix(qdrant): fix MatchText comment and validate logical operator inputs
Corrects the MatchText comment to accurately describe Qdrant behavior
(tokenized match with a full-text index; exact substring without one),
and adds ValueError validation when AND/OR/NOT filter values are not
lists, replacing unhelpful AttributeError crashes.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-21 18:07:07 +05:30
kartik-mem0andClaude Sonnet 4.6 a930603c12 fix(qdrant): add wildcard * support and update type hints
Wildcard '*' values now return None from _build_field_condition (match any /
field exists semantics), and _create_filter skips None conditions so a
filter containing only wildcards returns None. Updated return type annotations
to Optional[FieldCondition] and Optional[Filter] accordingly.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-21 18:05:48 +05:30
kartik-mem0andClaude Sonnet 4.6 b53507efd3 fix(qdrant): reject mixed range and non-range filter operators
Raise ValueError when a filter dict for a single field combines range
operators (gt/gte/lt/lte) with non-range operators (eq/ne/in/nin/etc),
preventing silent data loss where the non-range conditions were dropped.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-21 18:04:10 +05:30
kartik-mem0andClaude Sonnet 4.6 fb430b1a32 fix(qdrant): raise ValueError for unsupported filter operators
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-21 18:02:54 +05:30
Longwei Liu 7e0968bbc8 fix(qdrant): implement enhanced metadata filtering operators
The Qdrant vector store's _create_filter only handled simple equality
and a single gte+lte range case, causing ValidationError for all other
operators documented at docs.mem0.ai/open-source/features/metadata-filtering.

Add _build_field_condition to translate the universal filter syntax into
Qdrant-native models:
- Comparison: eq, ne, gt, gte, lt, lte  → MatchValue / MatchExcept / Range
- List:       in, nin                    → MatchAny / MatchExcept
- String:     contains, icontains        → MatchText
- Logical:    AND, OR, NOT              → Filter(must/should/must_not), recursive

Existing simple equality and gte+lte range filters continue to work
unchanged (backward compatible).

Closes #3975
2026-02-25 00:01:24 +08:00
Saket AryanandGitHub 27e5db5831 (fix): mongodb distribution name, azure ai search, and workflow trigger (#3900) 2026-01-13 12:52:49 +05:30
Parth SharmaandGitHub 84687fc3d2 [fix] list' object has no attribute 'id' - Id fault with chroma pinecone and other providers (#3693) 2025-10-31 16:46:10 +05:30
eb2f8a3738 fix: Prevent Mock object issues in graph memory tests (#3627)
Co-authored-by: parshvadaftari <daftariparshva@gmail.com>
2025-10-22 03:53:12 +05:30
Faizan HabibandGitHub 9ef644b95e Add Apache Cassandra vector store support (#3578) 2025-10-17 23:48:49 +05:30
Tarun JainandGitHub 1090784302 [feat add]FastEmbed embedding for local embeddings (#3552) 2025-10-16 22:52:22 +05:30
Parshva DaftariandGitHub 394203d1b5 Mem0 1.0.0 (#3545) 2025-10-16 15:50:20 +05:30
Parshva DaftariandGitHub 41cfb3ab1a [Update] Default LLM (#3587) 2025-10-15 11:19:52 -07:00
Vedant ThakkarandGitHub ea22e8d9cd feat: Allow custom model and params with huggingface_base_url (#3574) 2025-10-14 17:33:18 +05:30
Alex KondratevandGitHub ce8a285003 Validate embedding_dims in kuzu, fix #3556 (#3558) 2025-10-11 03:55:03 +05:30
Parshva DaftariandGitHub 4559623501 [fix] milvus db bug and added tests (#3566) 2025-10-11 02:21:35 +05:30
Vishaal LSandGitHub 9000576173 fix: handle non-serializable objects in config deepcopy (#3464) (#3544) 2025-10-09 19:35:08 +05:30
Josh HayesandGitHub 922471f43b fix: Databricks Vector Store (#3546) 2025-10-09 19:19:07 +05:30
Alex KondratevandGitHub ee0202764b Tool call support for LangchainLLM (#3542) 2025-10-06 00:03:44 +05:30
dog-lastandGitHub 51ce6f1347 Bug fix of thinking llm in vllm (#3510) 2025-10-03 19:13:08 +05:30
Parshva DaftariandGitHub 346d89d244 Added azure mysql for mem0 (#3531) 2025-10-02 21:41:03 +05:30
Vishaal LSandGitHub 58cc44ff38 fix: handle missing 'data' key in memory payload during search operations (#3524) 2025-09-30 15:10:43 -07:00
Karthikeya KolluandGitHub dc883b0f9e [test] Add comprehensive test suite for SQLiteManager (#3494) 2025-09-25 22:30:03 +05:30
Abdullah IrfanandGitHub 9df392b26a Fixed s3 vectors memory initialization issue from configuration (#3481) 2025-09-20 12:43:18 +05:30
Parshva DaftariandGitHub ead210ffe4 Added weaviate db test (#3483) 2025-09-18 14:40:44 -07:00
a015e2ff4a Add Neptune-DB graph store with vector store (#3443)
Signed-off-by: Andrew Carbonetto <andrew.carbonetto@improving.com>
Co-authored-by: Siddhartha Sahu <dev@sdht.in>
2025-09-19 02:54:33 +05:30
Andy KwokandGitHub 6b5582f474 Feat: Mem0 vector store backend integration for Neptune Analytics (#3453)
Signed-off-by: Andy Kwok <andy.kwok@improving.com>
2025-09-17 19:26:03 +05:30
Parshva DaftariandGitHub d48b1832c7 Fixes ollama and updates openai dependency (#3452) 2025-09-12 01:39:39 +05:30
Swarnaprakash UdayakumarandGitHub e3f0277cb9 feat(vector-store): Add Valkey vector store support (#3272) 2025-09-10 04:01:53 +05:30
Josh HayesandGitHub 9477184582 databricks bug fixes (#3416) 2025-09-05 16:22:09 +05:30
Srishti GurejaandGitHub cc15a22bf9 support store for openai (#3399) 2025-09-02 21:23:59 +05:30
John LockwoodandGitHub 97fd320bbf Fix/new mem mistaken for current fixing #2875 (#2876) 2025-09-01 19:46:01 +05:30
Sheharyar AhmadandGitHub 3d0ece1bcf Refactor PGVector to Use Internal Connection Pools and Context Managers (#3373) 2025-08-29 19:06:39 +05:30
Padarn WilsonandGitHub 3b2d0ad0eb Fix missing commas in Kuzu graph INSERT queries (#3358) 2025-08-24 12:33:51 +05:30
Enzo BiondoandGitHub c72bfc3285 Add Amazon S3 Vectors Support (#3237) 2025-08-23 16:44:42 +05:30
David A. TorresandGitHub 4487785cec feature: add Azure Identity for Azure OpenAI and Azure AI Search authentication (#3262) 2025-08-21 02:00:27 +05:30
e4c5582808 fix-migration-collection-override (#3100)
Co-authored-by: parshvadaftari <daftariparshva@gmail.com>
2025-08-21 00:11:28 +05:30
AkisAyaandGitHub 346b913ace feat: add es headers config (#3088) 2025-08-19 01:15:23 +05:30
Josh HayesandGitHub 3a1eff425b feat(vector-store): Add Databricks Mosaic AI vector store support (#3325) 2025-08-18 22:20:33 +05:30
Siddhartha SahuandGitHub a6a3928091 Add support for graph memory using Kuzu (#2934) 2025-08-16 02:22:31 +05:30
Parshva DaftariandGitHub b60a208c2f Fixes n_embeddings use and error for memgraph (#3296) 2025-08-11 12:57:29 -05:00
John LockwoodandGitHub 4c748423fc Feat/llm monitoring callback (#2877) 2025-08-08 14:26:51 -07:00
26732771eb Fix Neo4j Cypher syntax error with agent_id filtering (#3158)
Co-authored-by: parshvadaftari <daftariparshva@gmail.com>
2025-08-08 09:08:13 -07:00
Parshva DaftariandGitHub 148bbf0a5c Add sslmode pgvector (#3265) 2025-08-06 10:28:02 -07:00
Parshva DaftariandGitHub 6e8c6c1cb7 Refactored base class config for llms (#3241) 2025-08-05 15:42:06 -07:00
Parshva DaftariandGitHub 42e60d6724 Added mulit id filters support for all vectorstores (#3269) 2025-08-04 14:52:57 -07:00
Parshva DaftariandGitHub 57a16aeb4b Updated psycopg -> 3 (#3271) 2025-08-04 14:46:44 -07:00
Enam BiswasandGitHub 907328aafe feat (pinecone): Add namespace support and improve type safety (#3216) 2025-08-01 11:53:34 -07:00