- Add extract_keywords() to LLMService with conversation context support,
using process_stream + start_log/end_log for logging consistency
- Add expand_with_terminology() to expand keywords with synonym matching
- Add fusion scoring in calc_table_embedding(): α * vec_score + (1-α) * keyword_score
- Add calc_keyword_score() with multi-level matching:
table name exact (1.0), comment exact (0.9), comment substring (0.7),
table name partial (0.25-0.5), field comment exact (0.5),
field comment substring (0.4), field name partial (0.3)
- Scoring considers keyword coverage rate to differentiate tables
with different numbers of matched keywords
- Extracted keywords persisted to ChatRecord for reuse across endpoints
- get_terminology_template() supports comma-separated keyword input
with per-keyword matching for higher precision
- Add TABLE_EMBEDDING_ALPHA and TABLE_EMBEDDING_KEYWORD_ENABLED config
Security hardening:
- Add SQLBOT_ALLOW_METADATA_QUERIES config option, disable SHOW/DESCRIBE/EXPLAIN by default
- Add table whitelist check, use sqlglot to parse actual SQL table names and compare with authorized table list
- Add dangerous function check, block LOAD_FILE, INTO OUTFILE, EXEC etc. by database type
- Improve check_sql_read to return specific error reasons for better debugging
1.Add parameter: GENERATE_SQL_QUERY_LIMIT_ENABLED (default value is True to control data return Limit 1000 rows)
2.Use different SQL example templates based on different data sources.
ulleo