* Rebased Neptune changes based on significant rework done
* Updated the README documentation
* Fixed linting and formatting
* Update README.md
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Update graphiti_core/driver/neptune_driver.py
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Update README.md
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Addressed feedback from code review
* Updated the README documentation for clarity
* Updated the README and neptune_driver based on PR feedback
* Update node_db_queries.py
* bug: Fixed issue with missing call to create indicies for Neptune and added quickstart example
* chore: added pyright to ignore the attribute not in GrapHDriver
* Fixed quickstart with feedback from automated PR
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Preston Rasmussen <109292228+prasmussen15@users.noreply.github.com>
* gpt-5-mini and gpt-5-nano default
* bump version
* remove unused imports
* linter
* update
* disable neptune errors while we get a fixture in place
* update pyright
* revert non-structured completions
* fix typo
fix: respect search_methods configuration in edge_search and node_search
The search functions were ignoring the configured search_methods and
always executing all three methods (BM25, cosine similarity, and BFS).
This was causing unnecessary performance overhead - running 3x the
required computations when users only wanted specific search methods.
Now the functions build search tasks dynamically based on what's
actually configured in search_methods, only executing the requested
search algorithms.
This should significantly improve performance when users need only
specific search methods. Would appreciate your review on this approach\!
Fixes#788
* Add support for non-ASCII characters in LLM prompts
- Add ensure_ascii parameter to Graphiti class (default: True)
- Create to_prompt_json helper function for consistent JSON serialization
- Update all prompt files to use new helper function
- Preserve Korean/Japanese/Chinese characters when ensure_ascii=False
- Maintain backward compatibility with existing behavior
Fixes issue where non-ASCII characters were escaped as unicode sequences
in prompts, making them unreadable in LLM logs and potentially affecting
model understanding.
* Remove unused json imports after replacing with to_prompt_json helper
- Fix ruff lint errors (F401) for unused json imports
- All prompt files now use to_prompt_json helper instead of json.dumps
- Maintains clean code style and passes lint checks
* Fix ensure_ascii propagation to all LLM calls
- Add ensure_ascii parameter to maintenance operation functions that were missing it
- Update function signatures in node_operations, community_operations, temporal_operations, and edge_operations
- Ensure all llm_client.generate_response calls receive proper ensure_ascii context
- Fix hardcoded ensure_ascii: True values that prevented non-ASCII character preservation
- Maintain backward compatibility with default ensure_ascii=True
- Complete the fix for issue #804 ensuring Korean/Japanese/Chinese characters are properly handled in LLM prompts
* Prepare code
* Fix tests
* As -> AS, remove trailing spaces
* Enable more tests for FalkorDB
* Fix more cypher queries
* Return all created nodes and edges
* Add Neo4j service to unit tests workflow
- Introduced Neo4j as a service in the GitHub Actions workflow for unit tests.
- Configured Neo4j with appropriate ports, authentication, and health checks.
- Updated test steps to include waiting for Neo4j and running integration tests against it.
- Set environment variables for Neo4j connection in both non-integration and integration test steps.
* Update Neo4j authentication in unit tests workflow
- Changed Neo4j authentication password from 'test' to 'testpass' in the GitHub Actions workflow.
- Updated health check command to reflect the new password.
- Ensured consistency across all test steps that utilize Neo4j credentials.
* fix health check
* Fix Neo4j integration tests in CI workflow
Remove reference to non-existent test_neo4j_driver.py file from test command.
Integration tests now run via parametrized tests using the drivers list.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add OPENAI_API_KEY to Neo4j integration tests
Neo4j integration tests require OpenAI API access for LLM functionality.
Add the secret environment variable to enable these tests to run properly.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix Neo4j Cypher syntax error in BFS search queries
Replace parameter substitution in relationship pattern ranges (*1..$depth)
with direct string interpolation (*1..{bfs_max_depth}). Neo4j doesn't allow
parameter maps in MATCH pattern ranges - they must be literal values.
Fixed in both node_bfs_search and edge_bfs_search functions.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix variable name mismatch in edge_bfs_search query
Change relationship variable from 'r' to 'e' to match ENTITY_EDGE_RETURN
constant expectations. The ENTITY_EDGE_RETURN constant references variable
'e' for relationships, but the query was using 'r', causing "Variable e
not defined" errors.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Isolate database tests in CI workflow
- FalkorDB tests: Add DISABLE_NEO4J=1 and remove Neo4j env vars
- Neo4j tests: Keep current setup without DISABLE_NEO4J flag
This ensures proper test isolation where each test suite only runs
against its intended database backend.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Siddhartha Sahu <sid@kuzudb.com>
Co-authored-by: Claude <noreply@anthropic.com>
* graphiti-graph-name
* fix-lint
* fix-unittest
* clone-update
* groupid-none
* groupid-def-fulltext
* lint
* Remove redundant function definition for fulltext_query in search_utils.py
* Refactor get_default_group_id function and remove redundant code in falkordb_driver and search_utils. Added import statement in driver.py.
* Refactor test cases in test_falkordb_driver.py for improved readability by consolidating multi-line assertions into single lines. No functional changes made.
* Refactor fulltext_query function in search_utils.py to use double quotes for group_id in the filter list, enhancing consistency in query syntax.
* Remove duplicate assignment of fuzzy_query in episode_fulltext_search function in search_utils.py to eliminate redundancy.
* Remove duplicate assignment of fuzzy_query in community_fulltext_search function in search_utils.py to streamline code.
---------
Co-authored-by: Gal Shubeli <galshubeli93@gmail.com>
* feat: enhance GeminiClient with max tokens management
- Introduced a mapping for maximum output tokens for various Gemini models.
- Added methods to resolve max tokens based on precedence rules, allowing for more flexible token management.
- Updated tests to verify max tokens behavior, ensuring explicit parameters take precedence and fallback mechanisms work correctly.
This change improves the handling of token limits for different models, enhancing the client’s configurability and usability.
* refactor: streamline max tokens retrieval in GeminiClient
- Removed the fallback to DEFAULT_MAX_TOKENS in favor of directly using model-specific maximum tokens.
- Simplified the logic for determining max tokens, enhancing code clarity and maintainability.
This change improves the efficiency of token management within the GeminiClient.
* feat(gemini): embedding batch size & lite default
The new `gemini-embedding-001` model only allows one embedding input per batch
(instance), but has other impressive statistics:
https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/text-embeddings-api
The -DEFAULT_SMALL_MODEL must not have the 'models/' prefix.
* Refactor: Improve Gemini Client Error Handling and Reliability
This commit introduces several improvements to the Gemini client to enhance its robustness and reliability.
- Implemented more specific error handling for various Gemini API responses, including rate limits and safety blocks.
- Added a JSON salvaging mechanism to gracefully handle incomplete or malformed JSON responses from the API.
- Introduced detailed logging for failed LLM generations to simplify debugging and troubleshooting.
- Refined the Gemini embedder to better handle empty or invalid embedding responses.
- Updated and corrected tests to align with the improved error handling and reliability features.
* fix: cleanup in _log_failed_generation()
* fix: cleanup in _log_failed_generation()
* Fix ruff B904 error in gemini_client.py
* fix(gemini): correct retry logic and enhance error logging
Updated the retry mechanism in the GeminiClient to ensure it retries the maximum number of times specified. Improved error logging to provide clearer insights when all retries are exhausted, including detailed information about the last error encountered.
* fix(gemini): enhance error handling for safety blocks and update tests
Refined error handling in the GeminiClient to improve detection of safety block conditions. Updated test cases to reflect changes in exception messages and ensure proper retry logic is enforced. Enhanced mock responses in tests to better simulate real-world scenarios, including handling of invalid JSON responses.
* revert default gemini to text-embedding-001
---------
Co-authored-by: Daniel Chalef <131175+danielchalef@users.noreply.github.com>
* fix: remove global DEFAULT_DATABASE usage in favor of driver-specific
config
Fixes bugs introduced in PR #607. This removes reliance on the global
DEFAULT_DATABASE environment variable. It specifies the database within
each driver. PR #607 introduced a Neo4j compatability, as the database
names are different when attempting to support FalkorDB.
This refactor improves compatability across database types and ensures
future reliance by isolating the configuraiton to the driver level.
* fix: make falkordb support optional
This ensures that the the optional dependency and subsequent import is compliant with the graphiti-core project dependencies.
* chore: fmt code
* chore: undo changes to uv.lock
* fix: undo potentially breaking changes to drive interface
* fix: ensure a default database of "None" is provided - falling back to internal default
* chore: ensure default value exists for session and delete_all_indexes
* chore: fix typos and grammar
* chore: update package versions and dependencies in uv.lock and bulk_utils.py
* docs: update database configuration instructions for Neo4j and FalkorDB
Clarified default database names and how to override them in driver constructors. Updated testing requirements to include specific commands for running integration and unit tests.
* fix: ensure params defaults to an empty dictionary in Neo4jDriver
Updated the execute_query method to initialize params as an empty dictionary if not provided, ensuring compatibility with the database configuration.
---------
Co-authored-by: Urmzd <urmzd@dal.ca>
The cross_encoder for Gemini already supported passing in a custom client.
I replicated the same input pattern to embedder and llm_client.
The value is, you can support custom API endpoints and other options like below:
cross_encoder=GeminiRerankerClient(
client=genai.Client(
api_key=os.environ.get('GOOGLE_GENAI_API_KEY'),
http_options=types.HttpOptions(api_version='v1alpha')),
config=LLMConfig(
model="gemini-2.5-flash-lite-preview-06-17"
)
))
* add support for Gemini 2.5 model thinking budget
* allow adding thinking config to support current and future gemini models
* merge
* improve client; add reranker
* refactor: change type hint for gemini_messages to Any for flexibility
* refactor: update GeminiRerankerClient to use direct relevance scoring and improve ranking logic. Add tests
* fix fixtures
---------
Co-authored-by: realugbun <github.disorder751@passmail.net>
