MindsDB 25.2.3.0__py3-none-any.whl → 25.2.4.0__py3-none-any.whl

mindsdb/interfaces/agents/langchain_agent.py

@@ -400,7 +400,7 @@ class LangchainAgent:
                 "max_iterations", args.get("max_iterations", DEFAULT_MAX_ITERATIONS)
             ),
             memory=memory,
-            verbose=args.get("verbose", args.get("verbose", True)),
+            verbose=args.get("verbose", args.get("verbose", False))
         )
         return agent_executor
 
@@ -435,7 +435,7 @@ class LangchainAgent:
         all_callbacks = []
 
         if self.log_callback_handler is None:
-            self.log_callback_handler = LogCallbackHandler(logger)
+            self.log_callback_handler = LogCallbackHandler(logger, verbose=args.get("verbose", True))
 
         all_callbacks.append(self.log_callback_handler)
 
@@ -599,7 +599,9 @@ AI: {response}"""
                 agent_executor_finished_event.set()
 
         # Enqueue Langchain agent streaming chunks in a separate thread to not block event chunks.
-        executor_stream_thread = threading.Thread(target=stream_worker, daemon=True, args=(ctx.dump(),))
+        executor_stream_thread = threading.Thread(
+            target=stream_worker, daemon=True, args=(ctx.dump(),), name='LangchainAgent.stream_worker'
+        )
         executor_stream_thread.start()
 
         while not agent_executor_finished_event.is_set():

mindsdb/interfaces/database/database.py

@@ -106,7 +106,7 @@ class DatabaseController:
                 }
 
     def exists(self, db_name: str) -> bool:
-        return db_name in self.get_dict()
+        return db_name.lower() in self.get_dict()
 
     def get_project(self, name: str):
         return self.project_controller.get(name=name)

mindsdb/interfaces/database/integrations.py

@@ -64,7 +64,7 @@ class HandlersCache:
         ):
             return
         self._stop_event.clear()
-        self.cleaner_thread = threading.Thread(target=self._clean)
+        self.cleaner_thread = threading.Thread(target=self._clean, name='HandlersCache.clean')
         self.cleaner_thread.daemon = True
         self.cleaner_thread.start()
 

mindsdb/interfaces/jobs/scheduler.py

@@ -44,7 +44,7 @@ class Scheduler:
         self.q_in = queue.Queue()
         self.q_out = queue.Queue()
         self.work_thread = threading.Thread(
-            target=execute_async, args=(self.q_in, self.q_out)
+            target=execute_async, args=(self.q_in, self.q_out), name='Scheduler.execute_async'
         )
         self.work_thread.start()
 

mindsdb/interfaces/knowledge_base/preprocessing/constants.py

@@ -6,8 +6,8 @@ DEFAULT_MARKDOWN_HEADERS = [
 ]
 
 # Limits for web crawling
-DEFAULT_CRAWL_DEPTH = 1
-DEFAULT_WEB_CRAWL_LIMIT = 100
+DEFAULT_CRAWL_DEPTH = None
+DEFAULT_WEB_CRAWL_LIMIT = 1
 DEFAULT_WEB_FILTERS = []
 
 DEFAULT_CONTEXT_DOCUMENT_LIMIT = 50

mindsdb/interfaces/skills/skills_controller.py

@@ -1,7 +1,7 @@
 import datetime
 from typing import Dict, List, Optional
 
-from sqlalchemy import null
+from sqlalchemy import null, func
 from sqlalchemy.orm.attributes import flag_modified
 
 from mindsdb.interfaces.storage import db
@@ -33,7 +33,7 @@ class SkillsController:
 
         project = self.project_controller.get(name=project_name)
         return db.Skills.query.filter(
-            db.Skills.name == skill_name,
+            func.lower(db.Skills.name) == func.lower(skill_name),
             db.Skills.project_id == project.id,
             db.Skills.deleted_at == null()
         ).first()

mindsdb/interfaces/skills/sql_agent.py

@@ -287,6 +287,7 @@ class SQLAgent:
         return info
 
     def _get_sample_rows(self, table: str, fields: List[str]) -> str:
+        logger.info(f'_get_sample_rows: table={table} fields={fields}')
         command = f"select {', '.join(fields)} from {table} limit {self._sample_rows_in_table_info};"
         try:
             ret = self._call_engine(command)
@@ -300,7 +301,7 @@ class SQLAgent:
                 map(lambda row: [truncate_value(value) for value in row], sample_rows))
             sample_rows_str = "\n" + list_to_csv_str([fields] + sample_rows)
         except Exception as e:
-            logger.warning(e)
+            logger.info(f'_get_sample_rows error: {e}')
             sample_rows_str = "\n" + "\t [error] Couldn't retrieve sample rows!"
 
         return sample_rows_str
@@ -347,14 +348,18 @@ class SQLAgent:
 
     def get_table_info_safe(self, table_names: Optional[List[str]] = None) -> str:
         try:
+            logger.info(f'get_table_info_safe: {table_names}')
             return self.get_table_info(table_names)
         except Exception as e:
+            logger.info(f'get_table_info_safe error: {e}')
             return f"Error: {e}"
 
     def query_safe(self, command: str, fetch: str = "all") -> str:
         try:
+            logger.info(f'query_safe (fetch={fetch}): {command}')
             return self.query(command, fetch)
         except Exception as e:
+            logger.info(f'query_safe error: {e}')
             msg = f"Error: {e}"
             if 'does not exist' in msg and ' relation ' in msg:
                 msg += '\nAvailable tables: ' + ', '.join(self.get_usable_table_names())

mindsdb/interfaces/storage/db.py

@@ -218,18 +218,6 @@ class Project(Base):
     )
 
 
-class Log(Base):
-    __tablename__ = "log"
-
-    id = Column(Integer, primary_key=True)
-    created_at = Column(DateTime, default=datetime.datetime.now)
-    log_type = Column(String)  # log, info, warning, traceback etc
-    source = Column(String)  # file + line
-    company_id = Column(Integer)
-    payload = Column(String)
-    created_at_index = Index("some_index", "created_at_index")
-
-
 class Integration(Base):
     __tablename__ = "integration"
     id = Column(Integer, primary_key=True)

mindsdb/migrations/versions/2025-02-10_6ab9903fc59a_del_log_table.py

@@ -0,0 +1,33 @@
+"""del_log_table
+
+Revision ID: 6ab9903fc59a
+Revises: 4943359e354a
+Create Date: 2025-02-10 16:50:27.186697
+
+"""
+from alembic import op
+import sqlalchemy as sa
+import mindsdb.interfaces.storage.db  # noqa
+
+# revision identifiers, used by Alembic.
+revision = '6ab9903fc59a'
+down_revision = '4943359e354a'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    op.drop_table('log')
+
+
+def downgrade():
+    op.create_table(
+        'log',
+        sa.Column('id', sa.INTEGER(), nullable=False),
+        sa.Column('created_at', sa.DATETIME(), nullable=True),
+        sa.Column('log_type', sa.VARCHAR(), nullable=True),
+        sa.Column('source', sa.VARCHAR(), nullable=True),
+        sa.Column('company_id', sa.INTEGER(), nullable=True),
+        sa.Column('payload', sa.VARCHAR(), nullable=True),
+        sa.PrimaryKeyConstraint('id')
+    )

mindsdb/utilities/config.py

@@ -149,6 +149,7 @@ class Config:
                 "handlers": {
                     "console": {
                         "enabled": True,
+                        "formatter": "default",
                         "level": "INFO"     # MINDSDB_CONSOLE_LOG_LEVEL or MINDSDB_LOG_LEVEL (obsolete)
                     },
                     "file": {

mindsdb/utilities/log.py

@@ -1,3 +1,4 @@
+import json
 import logging
 from logging.config import dictConfig
 
@@ -7,6 +8,19 @@ from mindsdb.utilities.config import config as app_config
 logging_initialized = False
 
 
+class JsonFormatter(logging.Formatter):
+    def format(self, record):
+        record_message = super().format(record)
+        log_record = {
+            'process_name': record.processName,
+            'name': record.name,
+            'message': record_message,
+            'level': record.levelname,
+            'time': record.created
+        }
+        return json.dumps(log_record)
+
+
 class ColorFormatter(logging.Formatter):
     green = "\x1b[32;20m"
     default = "\x1b[39;20m"
@@ -53,7 +67,7 @@ def configure_logging():
     if console_handler_config['enabled'] is True:
         handlers_config['console'] = {
             "class": "logging.StreamHandler",
-            "formatter": "f",
+            "formatter": console_handler_config.get('formatter', 'default'),
             "level": console_handler_config_level
         }
 
@@ -74,7 +88,8 @@ def configure_logging():
     logging_config = dict(
         version=1,
         formatters={
-            "f": {"()": ColorFormatter},
+            "default": {"()": ColorFormatter},
+            "json": {"()": JsonFormatter},
             "file": {
                 "format": "%(asctime)s %(processName)15s %(levelname)-8s %(name)s: %(message)s"
             }

mindsdb/utilities/ml_task_queue/consumer.py

@@ -74,7 +74,9 @@ class MLTaskConsumer(BaseRedisQueue):
 
         # region collect cpu usage statistic
         self.cpu_stat = [0] * 10
-        self._collect_cpu_stat_thread = threading.Thread(target=self._collect_cpu_stat)
+        self._collect_cpu_stat_thread = threading.Thread(
+            target=self._collect_cpu_stat, name='MLTaskConsumer._collect_cpu_stat'
+        )
         self._collect_cpu_stat_thread.start()
         # endregion
 
@@ -221,7 +223,7 @@ class MLTaskConsumer(BaseRedisQueue):
             if self._ready_event.is_set() is False:
                 continue
             self._ready_event.clear()
-            threading.Thread(target=self._listen).start()
+            threading.Thread(target=self._listen, name='MLTaskConsumer._listen').start()
         self.stop()
 
     def stop(self) -> None:

mindsdb/utilities/render/sqlalchemy_render.py

@@ -63,6 +63,10 @@ class AttributedStr(str):
         obj.is_quoted = is_quoted
         return obj
 
+    def replace(self, *args):
+        obj = super().replace(*args)
+        return AttributedStr(obj, self.is_quoted)
+
 
 def get_is_quoted(identifier: ast.Identifier):
     quoted = getattr(identifier, 'is_quoted', [])

mindsdb/utilities/log_controller.py

@@ -1,39 +0,0 @@
-from mindsdb.interfaces.storage import db
-from mindsdb.utilities.context import context as ctx
-
-
-def fmt_log_record(log_record):
-    return {
-        'log_from': 'mindsdb',
-        'level': log_record.log_type,
-        'context': 'unknown',
-        'text': log_record.payload,
-        'created_at': str(log_record.created_at).split('.')[0]
-    }
-
-
-def get_logs(min_timestamp, max_timestamp, context, level, log_from, limit):
-    logs = db.session.query(db.Log).filter(
-        db.Log.company_id == ctx.company_id,
-        db.Log.created_at > min_timestamp
-    )
-
-    if max_timestamp is not None:
-        logs = logs.filter(db.Log.created_at < max_timestamp)
-
-    if context is not None:
-        # e.g. datasource/predictor and assoicated id
-        pass
-
-    if level is not None:
-        logs = logs.filter(db.Log.log_type == level)
-
-    if log_from is not None:
-        # mindsdb/native/lightwood/all
-        pass
-
-    if limit is not None:
-        logs = logs.limit(limit)
-
-    logs = [fmt_log_record(x) for x in logs]
-    return logs

mindsdb/utilities/telemetry.py

@@ -1,44 +0,0 @@
-import os
-from pathlib import Path
-
-TELEMETRY_FILE = 'telemetry.lock'
-
-
-def enable_telemetry(storage_dir):
-    os.environ['CHECK_FOR_UPDATES'] = '1'
-    path = os.path.join(storage_dir, TELEMETRY_FILE)
-    if os.path.exists(path):
-        os.remove(path)
-
-
-def disable_telemetry(storage_dir):
-    os.environ['CHECK_FOR_UPDATES'] = '0'
-    path = os.path.join(storage_dir, TELEMETRY_FILE)
-    with open(path, 'w') as _:
-        pass
-
-
-def telemetry_file_exists(storage_dir):
-    path = os.path.join(storage_dir, TELEMETRY_FILE)
-    return os.path.exists(path)
-
-
-def inject_telemetry_to_static(static_folder):
-    TEXT = '<script>localStorage.isTestUser = true;</script>'
-    index = Path(static_folder).joinpath('index.html')
-    disable_telemetry = os.getenv('CHECK_FOR_UPDATES', '1').lower() in ['0', 'false', 'False']
-    if index.is_file():
-        with open(str(index), 'rt') as f:
-            content = f.read()
-        script_index = content.find('<script>')
-        need_update = True
-        if TEXT not in content and disable_telemetry:
-            content = content[:script_index] + TEXT + content[script_index:]
-        elif not disable_telemetry and TEXT in content:
-            content = content.replace(TEXT, '')
-        else:
-            need_update = False
-
-        if need_update:
-            with open(str(index), 'wt') as f:
-                f.write(content)