run-llama/llama_index · error · ValueError

include_tables {missing_tables} not found in database

Error message

include_tables {missing_tables} not found in database

What it means

When include_tables is given, SQLWrapper verifies every requested table actually exists in the database (tables plus views if view_support=True). Any table in include_tables that the inspector cannot find raises ValueError listing the missing names, protecting downstream text-to-SQL from hallucinating over nonexistent tables.

Source

Thrown at llama-index-core/llama_index/core/utilities/sql_wrapper.py:75

        self._engine = engine
        self._schema = schema
        if include_tables and ignore_tables:
            raise ValueError("Cannot specify both include_tables and ignore_tables")

        self._inspector = inspect(self._engine)

        # including view support by adding the views as well as tables to the all
        # tables list if view_support is True
        self._all_tables = set(
            self._inspector.get_table_names(schema=schema)
            + (self._inspector.get_view_names(schema=schema) if view_support else [])
        )

        self._include_tables = set(include_tables) if include_tables else set()
        if self._include_tables:
            missing_tables = self._include_tables - self._all_tables
            if missing_tables:
                raise ValueError(
                    f"include_tables {missing_tables} not found in database"
                )
        self._ignore_tables = set(ignore_tables) if ignore_tables else set()
        if self._ignore_tables:
            missing_tables = self._ignore_tables - self._all_tables
            if missing_tables:
                raise ValueError(
                    f"ignore_tables {missing_tables} not found in database"
                )
        usable_tables = self.get_usable_table_names()
        self._usable_tables = set(usable_tables) if usable_tables else self._all_tables

        if not isinstance(sample_rows_in_table_info, int):
            raise TypeError("sample_rows_in_table_info must be an integer")

        self._sample_rows_in_table_info = sample_rows_in_table_info
        self._indexes_in_table_info = indexes_in_table_info

View on GitHub (pinned to afd0fef371)

Solutions

1. List the real tables first: print(db.get_usable_table_names()) or insp.get_table_names(), then copy exact names into include_tables.
2. Pass schema='my_schema' if tables live outside the default schema, and view_support=True if you need views.
3. Match identifier case exactly on backends like Postgres (quoted identifiers) or Snowflake.

Example fix

# before
 db = SQLDatabase(engine, include_tables=['users', 'acounts'])  # typo -> ValueError

# after
 print(SQLDatabase(engine).get_usable_table_names())  # ['users', 'accounts', ...]
 db = SQLDatabase(engine, include_tables=['users', 'accounts'])

from sqlalchemy import inspect

def filter_include_tables(engine, include_tables, schema=None, view_support=False):
    insp = inspect(engine)
    existing = set(insp.get_table_names(schema=schema))
    if view_support:
        existing |= set(insp.get_view_names(schema=schema))
    missing = set(include_tables or []) - existing
    if missing:
        raise ValueError(f'These tables do not exist: {sorted(missing)}. '
                         f'Available: {sorted(existing)}')
    return list(existing & set(include_tables))

def include_tables_exist(engine, include_tables, schema=None) -> bool:
    existing = set(inspect(engine).get_table_names(schema=schema))
    return set(include_tables) <= existing

try:
    db = SQLDatabase(engine, include_tables=tables)
except ValueError as e:
    if 'include_tables' in str(e) and 'not found' in str(e):
        available = SQLDatabase(engine).get_usable_table_names()
        tables = [t for t in tables if t in available]
        db = SQLDatabase(engine, include_tables=tables)
    else:
        raise

When it happens

Trigger: SQLDatabase(engine, include_tables=['users', 'acounts']) where 'acounts' is a typo; referencing tables in a non-default schema without passing schema=; listing views while view_support=False (views are then not in _all_tables); case-mismatched table names on case-sensitive backends.

Common situations: Typos or stale table lists after a schema migration renamed/dropped tables; pointing the engine at the wrong database or schema; environments (dev vs prod) with divergent schemas.

Related errors

• ignore_tables {missing_tables} not found in database
• Invalid context table names: {context_keys - set(self.sql_da
• Cannot specify both include_tables and ignore_tables
• Statement {command!r} is invalid SQL.\nError: {exc.orig}
• sql_database must be provided.

AI-assisted analysis of run-llama/llama_index@afd0fef371 (2026-08-15). Data as JSON: /api/errors/aaa9fc1a92b34d41. Report an issue: GitHub.