feat: implement LLM keyword extraction and fusion scoring for table matching

- 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

backend/alembic/env.py

@@ -24,14 +24,14 @@ config = context.config
 
 # from apps.system.models.user import SQLModel  # noqa
 # from apps.settings.models.setting_models import SQLModel
-#from apps.chat.models.chat_model import SQLModel
-from apps.terminology.models.terminology_model import SQLModel
-from sqlbot_xpack.custom_prompt.models.custom_prompt_model import SQLModel
+from apps.chat.models.chat_model import SQLModel
+#from apps.terminology.models.terminology_model import SQLModel
+#from sqlbot_xpack.custom_prompt.models.custom_prompt_model import SQLModel
 #from apps.data_training.models.data_training_model import SQLModel
 # from apps.dashboard.models.dashboard_model import SQLModel
 from common.core.config import settings # noqa
 #from apps.datasource.models.datasource import SQLModel
-from apps.system.models.system_model import SQLModel
+#from apps.system.models.system_model import SQLModel
 
 target_metadata = SQLModel.metadata
 

backend/alembic/versions/072_chat_record.py

@@ -0,0 +1,31 @@
+"""072_chat_record
+
+Revision ID: f898322341a5
+Revises: a2e2ecfa5a9c
+Create Date: 2026-09-14 15:54:47.921806
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel.sql.sqltypes
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision = 'f898322341a5'
+down_revision = 'a2e2ecfa5a9c'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('chat_record', sa.Column('extracted_keywords', sa.Text(), nullable=True, comment='关键词'))
+    op.add_column('chat_record', sa.Column('expanded_keywords', sa.Text(), nullable=True, comment='扩展后的关键词'))
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column('chat_record', 'extracted_keywords')
+    op.drop_column('chat_record', 'expanded_keywords')
+    # ### end Alembic commands ###