graphiti/graphiti_core/search
Daniel Chalef 196eb2f077
Remove JSON indentation from prompts to reduce token usage (#985)
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>
2025-10-06 16:08:43 -07:00
..
__init__.py chore: Fix packaging (#38) 2024-08-25 10:07:50 -07:00
search.py cleanup (#894) 2025-09-05 11:30:46 -04:00
search_config.py cleanup (#894) 2025-09-05 11:30:46 -04:00
search_config_recipes.py add episode scope to search (#362) 2025-04-15 19:27:56 -04:00
search_filters.py OpenSearch updates (#906) 2025-09-14 01:43:37 -04:00
search_helpers.py Remove JSON indentation from prompts to reduce token usage (#985) 2025-10-06 16:08:43 -07:00
search_utils.py fix-fulltext-syntax-error (#914) 2025-09-23 10:52:44 -04:00