Skip to content

Release 0.5.0 #73

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

Merged
merged 5 commits into from
Jul 25, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,27 @@

## Next

## 0.5.0

### Added

- Added support for specifying custom database names in `Neo4jChatMessageHistory` (not limited to the default `"neo4j"`).
- Introduced an optional `mmr` dependency group for maximal marginal relevance search dependencies.
- Included `numpy` in the `mmr` dependency group.

### Changed

- Bumped `neo4j-graphrag` dependency version from `^1.5.0` to `^1.9.0`.

### Fixed

- Prevented infinite loops in `CypherQueryCorrector.extract_paths` whenever there was a repeated path in a Cypher query.
- Replaced direct `result["text"]` indexing with `result.get("text")` in `Neo4jVector.similarity_search_with_score_by_vector`, so missing text fields are handled gracefully instead of raising errors.
- Changed an empty-list check in `CypherQueryCorrector.detect_node_variables` so that nodes without an explicit variable are properly skipped instead of misclassifying all labels under an empty variable.
- Stopped `Neo4jChatMessageHistory` from creating duplicate session nodes.
- Schema bug in `Neo4jGraph` when `enhance_schema=True` where relationships with boolean properties triggered a malformed `RETURN {} AS output` Cypher query and prevented graph initialization.
- Ensured custom DB names are passed through to `retrieve_vector_index_info` and `retrieve_existing_fts_index` in `Neo4jVector`.

## 0.4.0

### Changed
Expand Down
2 changes: 2 additions & 0 deletions libs/neo4j/langchain_neo4j/vectorstores/neo4j_vector.py
Original file line number Diff line number Diff line change
Expand Up @@ -382,6 +382,7 @@ def retrieve_existing_index(self) -> Optional[Tuple[Optional[int], str]]:
index_name=self.index_name,
label_or_type=self.node_label,
embedding_property=self.embedding_node_property,
neo4j_database=self._database,
)
if index_information:
try:
Expand Down Expand Up @@ -417,6 +418,7 @@ def retrieve_existing_fts_index(
index_name=self.keyword_index_name,
label_or_type=self.node_label,
text_properties=text_node_properties or [self.text_node_property],
neo4j_database=self._database,
)
else:
raise ValueError("keyword_index_name is not set.")
Expand Down
Loading