Changes to `to_prompt_json()` helper to default to minified JSON (no indentation) instead of 2-space indentation. This reduces token consumption in LLM prompts while maintaining all necessary information.
- Changed default `indent` parameter from `2` to `None` in `prompt_helpers.py`
- Updated all prompt modules to remove explicit `indent=2` arguments
- Minor code formatting fixes in LLM clients
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* Add OpenTelemetry distributed tracing support
- Add tracer abstraction with no-op and OpenTelemetry implementations
- Instrument add_episode and add_episode_bulk with tracing spans
- Instrument LLM client with cache-aware tracing
- Add configurable span name prefix support
- Refactor add_episode methods to improve code quality
- Add OTEL_TRACING.md documentation
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix linting errors in tracing implementation
- Remove unused episodes_by_uuid variable
- Fix tracer type annotations for context manager support
- Replace isinstance tuple with union syntax
- Use contextlib.suppress for exception handling
- Fix import ordering and use AbstractContextManager
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Address PR review feedback on tracing implementation
Critical fixes:
- Remove flawed error span creation in graphiti.py that created orphaned spans
- Restructure LLM client tracing to create span once at start, eliminating code duplication
- Initialize LLM client tracer to NoOpTracer by default to fix type checking
Enhancements:
- Add comprehensive span attributes to add_episode: reference_time, entity/edge type counts, previous episodes count, invalidated edge count, community count
- Optimize isinstance check for better performance
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Add prompt name tracking to OpenTelemetry tracing spans
Add prompt_name parameter to all LLM client generate_response() methods
and set it as a span attribute in the llm.generate span. This enables
better observability by identifying which prompt template was used for
each LLM call.
Changes:
- Add prompt_name parameter to LLMClient.generate_response() base method
- Add prompt_name parameter and tracing to OpenAIBaseClient,
AnthropicClient, GeminiClient, and OpenAIGenericClient
- Update all 14 LLM call sites across maintenance operations to include
prompt_name:
- edge_operations.py: 4 calls
- node_operations.py: 6 calls (note: 7 listed but only 6 unique)
- temporal_operations.py: 2 calls
- community_operations.py: 2 calls
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix exception handling in add_episode to record errors in OpenTelemetry span
Moved try-except block inside the OpenTelemetry span context and added
proper error recording with span.set_status() and span.record_exception().
This ensures exceptions are captured in the distributed trace, matching
the pattern used in add_episode_bulk.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* Add group_id parameter to get_extraction_language_instruction
Enable consumers to provide group-specific language extraction
instructions by passing group_id through the call chain.
Changes:
- Add optional group_id parameter to get_extraction_language_instruction()
- Add group_id parameter to all LLMClient.generate_response() methods
- Pass group_id through to language instruction function
- Maintain backward compatibility with default None value
Users can now customize extraction per group:
```python
def custom_instruction(group_id: str | None = None) -> str:
if group_id == 'spanish-users':
return '\n\nExtract in Spanish.'
return '\n\nExtract in original language.'
client.get_extraction_language_instruction = custom_instruction
```
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Pass group_id to generate_response in extraction operations
Thread group_id parameter through all extraction-related generate_response()
calls where it's naturally available (via episode.group_id or node.group_id).
This enables consumers to override get_extraction_language_instruction() with
group-specific language preferences.
Changes:
- edge_operations.py: Pass group_id in extract_edges()
- node_operations.py: Pass episode.group_id in extract_nodes() and
node.group_id in extract_attributes_from_node()
- node_operations.py: Add group_id parameter to extract_nodes_reflexion()
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Fix type inconsistency in extract_nodes_reflexion parameter
Change group_id parameter from str = '' to str | None = None to match
the pattern used throughout the codebase and align with the optional
nature of group_id in generate_response().
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Remove ensure_ascii parameter and uv.lock file
* Reset uv.lock to main branch version
---------
Co-authored-by: Claude <noreply@anthropic.com>
Replace MULTILINGUAL_EXTRACTION_RESPONSES constant with configurable
get_extraction_language_instruction() function to improve determinism
and allow customization.
Changes:
- Replace constant with function in client.py
- Update all LLM client implementations to use new function
- Maintain backward compatibility with same default behavior
- Enable users to override function for custom language requirements
Users can now customize extraction behavior by monkey-patching:
```python
import graphiti_core.llm_client.client as client
client.get_extraction_language_instruction = lambda: "Custom instruction"
```
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.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
* 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>
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>
* Refactor group_id handling and update dependencies
- Changed default behavior for `group_id` to 'default' instead of generating a UUID.
- Updated README to reflect the new default behavior for `--group-id`.
- Reformatted LLMConfig initialization for better readability.
- Bumped versions of several dependencies including `azure-core`, `azure-identity`, `certifi`, `charset-normalizer`, `sse-starlette`, and `typing-inspection`.
- Added `python-multipart` as a new dependency.
This update improves usability and ensures compatibility with the latest library versions.
* Update Graphiti MCP server instructions and refactor method names for clarity
- Revised the welcome message to enhance clarity about Graphiti's functionality.
- Renamed methods for better understanding: `add_episode` to `add_memory`, `search_nodes` to `search_memory_nodes`, `search_facts` to `search_memory_facts`, and updated related docstrings to reflect these changes.
- Updated references to "knowledge graph" to "graph memory" for consistency throughout the codebase.
* Update README for Graphiti MCP server configuration and integration with Claude Desktop
- Changed server name from "graphiti" to "graphiti-memory" in configuration examples for clarity.
- Added instructions for running the Graphiti MCP server using Docker.
- Included detailed steps for integrating Claude Desktop with the Graphiti MCP server, including optional installation of `mcp-remote`.
- Enhanced overall documentation to improve user experience and understanding of the setup process.
* Enhance error handling in GeminiEmbedder and GeminiClient
- Added checks to raise exceptions when no embeddings or response text are returned, improving robustness.
- Included type ignore comments for mypy compatibility in embed_content calls.
* Update graphiti_core/embedder/gemini.py
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* Update graphiti_core/llm_client/gemini_client.py
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
* remove temporary debug logging
* add anthropic api to .env.example
* move anthropic int tests to llm_client dir to better match existing test structure
* update `TestLLMClient` to `MockLLMClient` to eliminate pytest warning
* Fix: use self.max_tokens when max_token isnt specified
* Fix: use self.max_tokens in OpenAI clients
* Fix: use self.max_tokens in Anthropic client
* Fix: use self.max_tokens in Gemini client
* update Anthropic client to use tool calling and add tests
* fix linting errors before creating pull request by making literal types for anthropic models
* Bump version from 0.9.0 to 0.9.1 in pyproject.toml and update google-genai dependency to >=0.1.0
* Bump version from 0.9.1 to 0.9.2 in pyproject.toml
* Update google-genai dependency version to >=0.8.0 in pyproject.toml
* loc file
* Update pyproject.toml to version 0.9.3, restructure dependencies, and modify author format. Remove outdated Google API key note from README.md.
* upgrade poetry and ruff
* first cut
* Update dependencies and enhance README for optional LLM providers
- Bump aiohttp version from 3.11.14 to 3.11.16
- Update yarl version from 1.18.3 to 1.19.0
- Modify pyproject.toml to include optional extras for Anthropic, Groq, and Google Gemini
- Revise README.md to reflect new optional LLM provider installation instructions and clarify API key requirements
* Remove deprecated packages from poetry.lock and update content hash
- Removed cachetools, google-auth, google-genai, pyasn1, pyasn1-modules, rsa, and websockets from the lock file.
- Added new extras for anthropic, google-genai, and groq.
- Updated content hash to reflect changes.
* Refactor import paths for GeminiClient in README and __init__.py
- Updated import statement in README.md to reflect the new module structure for GeminiClient.
- Removed GeminiClient from the __all__ list in __init__.py as it is no longer directly imported.
* Refactor import paths for GeminiEmbedder in README and __init__.py
- Updated import statement in README.md to reflect the new module structure for GeminiEmbedder.
- Removed GeminiEmbedder and GeminiEmbedderConfig from the __all__ list in __init__.py as they are no longer directly imported.
* implement so
* bug fixes and typing
* inject schema for non-openai clients
* correct datetime format
* remove List keyword
* Refactor node_operations.py to use updated prompt_library functions
* update example
* node distance and group_ids fixed
* get all with no group_id passed
* push
* push
* remove comments
* mypy
* mypy ids
* please mypy
* trust
* last one
* Override default max tokens for Anthropic and Groq clients
* Override default max tokens for Anthropic and Groq clients
* Override default max tokens for Anthropic and Groq clients
The code changes refactor the `OpenAIClient` initialization to accept an optional `client` parameter. This allows the client to be passed in from outside, providing more flexibility and enabling easier testing.
* Add get_nodes_by_query method to Graphiti class
Add a method to the Graphiti class that wraps `get_relevant_nodes` and returns a list of nodes given a query.
* Add `get_nodes_by_query` method to the `Graphiti` class in `graphiti_core/graphiti.py`.
* Import `generate_embedding` from `graphiti_core/llm_client/utils.py`.
* Use `generate_embedding` to generate an embedding for the query.
* Call `get_relevant_nodes` with the generated embedding and return the relevant nodes.
Add an embedding function to `llm_client/utils.py`.
* Add `generate_embedding` function to `graphiti_core/llm_client/utils.py`.
* Accept an embedder and model_id as parameters.
* Generate an embedding for the given text and return it.
---
For more details, open the [Copilot Workspace session](https://copilot-workspace.githubnext.com/getzep/graphiti?shareId=XXXX-XXXX-XXXX-XXXX).
* address comments left by @danielchalef on #49 (Add get_nodes_by_query method to Graphiti class);
* fix ellipsis name in cla config
* feat: Add get_nodes_by_query method to Graphiti class
* chore: Cleanup unused files, add hybrid node search, add tests
---------
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: paulpaliychuk <pavlo.paliychuk.ca@gmail.com>
