ce9ef3ca79
* 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
24 lines
795 B
Python
24 lines
795 B
Python
import json
|
|
from typing import Any
|
|
|
|
DO_NOT_ESCAPE_UNICODE = '\nDo not escape unicode characters.\n'
|
|
|
|
|
|
def to_prompt_json(data: Any, ensure_ascii: bool = True, indent: int = 2) -> str:
|
|
"""
|
|
Serialize data to JSON for use in prompts.
|
|
|
|
Args:
|
|
data: The data to serialize
|
|
ensure_ascii: If True, escape non-ASCII characters. If False, preserve them.
|
|
indent: Number of spaces for indentation
|
|
|
|
Returns:
|
|
JSON string representation of the data
|
|
|
|
Notes:
|
|
When ensure_ascii=False, non-ASCII characters (e.g., Korean, Japanese, Chinese)
|
|
are preserved in their original form in the prompt, making them readable
|
|
in LLM logs and improving model understanding.
|
|
"""
|
|
return json.dumps(data, ensure_ascii=ensure_ascii, indent=indent)
|