Merge branch 'dev' into feature/cog-3254-add-multifile-ontology-handling

2025-10-28 09:58:17 +01:00 · 2025-10-28 09:58:17 +01:00 · 65003a0a0b
commit 65003a0a0b
parent d224864e57 5684024d8c
8 changed files with 4166 additions and 4163 deletions
--- a/cognee/modules/pipelines/operations/run_tasks_base.py
+++ b/cognee/modules/pipelines/operations/run_tasks_base.py
@ -27,6 +27,7 @@ async def handle_task(
        additional_properties={
            "task_name": running_task.executable.__name__,
            "cognee_version": cognee_version,
+            "tenant_id": str(user.tenant_id) if user.tenant_id else "Single User Tenant",
        },
    )

@ -49,6 +50,7 @@ async def handle_task(
            additional_properties={
                "task_name": running_task.executable.__name__,
                "cognee_version": cognee_version,
+                "tenant_id": str(user.tenant_id) if user.tenant_id else "Single User Tenant",
            },
        )
    except Exception as error:
@ -62,6 +64,7 @@ async def handle_task(
            additional_properties={
                "task_name": running_task.executable.__name__,
                "cognee_version": cognee_version,
+                "tenant_id": str(user.tenant_id) if user.tenant_id else "Single User Tenant",
            },
        )
        raise error
--- a/cognee/modules/pipelines/operations/run_tasks_with_telemetry.py
+++ b/cognee/modules/pipelines/operations/run_tasks_with_telemetry.py
@ -28,6 +28,7 @@ async def run_tasks_with_telemetry(
            additional_properties={
                "pipeline_name": str(pipeline_name),
                "cognee_version": cognee_version,
+                "tenant_id": str(user.tenant_id) if user.tenant_id else "Single User Tenant",
            }
            | config,
        )
@ -42,6 +43,7 @@ async def run_tasks_with_telemetry(
            additional_properties={
                "pipeline_name": str(pipeline_name),
                "cognee_version": cognee_version,
+                "tenant_id": str(user.tenant_id) if user.tenant_id else "Single User Tenant",
            }
            | config,
        )
@ -58,6 +60,7 @@ async def run_tasks_with_telemetry(
            additional_properties={
                "pipeline_name": str(pipeline_name),
                "cognee_version": cognee_version,
+                "tenant_id": str(user.tenant_id) if user.tenant_id else "Single User Tenant",
            }
            | config,
        )
--- a/cognee/modules/search/methods/search.py
+++ b/cognee/modules/search/methods/search.py
@ -67,7 +67,10 @@ async def search(
    send_telemetry(
        "cognee.search EXECUTION STARTED",
        user.id,
-        additional_properties={"cognee_version": cognee_version},
+        additional_properties={
+            "cognee_version": cognee_version,
+            "tenant_id": str(user.tenant_id) if user.tenant_id else "Single User Tenant",
+        },
    )

    # Use search function filtered by permissions if access control is enabled
@ -108,7 +111,10 @@ async def search(
    send_telemetry(
        "cognee.search EXECUTION COMPLETED",
        user.id,
-        additional_properties={"cognee_version": cognee_version},
+        additional_properties={
+            "cognee_version": cognee_version,
+            "tenant_id": str(user.tenant_id) if user.tenant_id else "Single User Tenant",
+        },
    )

    await log_result(
--- a/cognee/shared/logging_utils.py
+++ b/cognee/shared/logging_utils.py
@ -430,6 +430,15 @@ def setup_logging(log_level=None, name=None):
    stream_handler.setFormatter(console_formatter)
    stream_handler.setLevel(log_level)

+    root_logger = logging.getLogger()
+    if root_logger.hasHandlers():
+        root_logger.handlers.clear()
+    root_logger.addHandler(stream_handler)
+
+    # Note: root logger needs to be set at NOTSET to allow all messages through and specific stream and file handlers
+    # can define their own levels.
+    root_logger.setLevel(logging.NOTSET)
+
    # Check if we already have a log file path from the environment
    # NOTE: environment variable must be used here as it allows us to
    # log to a single file with a name based on a timestamp in a multiprocess setting.
@ -441,17 +450,15 @@ def setup_logging(log_level=None, name=None):
        log_file_path = os.path.join(LOGS_DIR, f"{start_time}.log")
        os.environ["LOG_FILE_NAME"] = log_file_path

-    # Create a file handler that uses our custom PlainFileHandler
-    file_handler = PlainFileHandler(log_file_path, encoding="utf-8")
-    file_handler.setLevel(DEBUG)
-
-    # Configure root logger
-    root_logger = logging.getLogger()
-    if root_logger.hasHandlers():
-        root_logger.handlers.clear()
-    root_logger.addHandler(stream_handler)
-    root_logger.addHandler(file_handler)
-    root_logger.setLevel(log_level)
+    try:
+        # Create a file handler that uses our custom PlainFileHandler
+        file_handler = PlainFileHandler(log_file_path, encoding="utf-8")
+        file_handler.setLevel(DEBUG)
+        root_logger.addHandler(file_handler)
+    except Exception as e:
+        # Note: Exceptions happen in case of read only file systems or log file path poiting to location where it does
+        # not have write permission. Logging to file is not mandatory so we just log a warning to console.
+        root_logger.warning(f"Warning: Could not create log file handler at {log_file_path}: {e}")

    if log_level > logging.DEBUG:
        import warnings
--- a/cognee/tasks/ingestion/migrate_relational_database.py
+++ b/cognee/tasks/ingestion/migrate_relational_database.py
@ -239,7 +239,7 @@ async def complete_database_ingestion(schema, migrate_column_data):
                            id=uuid5(NAMESPACE_OID, name=column_node_id),
                            name=column_node_id,
                            properties=f"{key} {value} {table_name}",
-                            description=f"column from relational database table={table_name}. Column name={key} and value={value}. The value of the column is related to the following row with this id: {row_node.id}. This column has the following ID: {column_node_id}",
+                            description=f"column from relational database table={table_name}. Column name={key} and value={value}. This column has the following ID: {column_node_id}",
                        )
                        node_mapping[column_node_id] = column_node

--- a/poetry.lock
+++ b/poetry.lock
@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 2.1.2 and should not be changed by hand.
+# This file is automatically @generated by Poetry 2.1.3 and should not be changed by hand.

 [[package]]
 name = "accelerate"
@ -2543,7 +2543,6 @@ files = [
    {file = "fastuuid-0.12.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b9b31dd488d0778c36f8279b306dc92a42f16904cba54acca71e107d65b60b0c"},
    {file = "fastuuid-0.12.0-cp313-cp313-manylinux_2_34_x86_64.whl", hash = "sha256:b19361ee649365eefc717ec08005972d3d1eb9ee39908022d98e3bfa9da59e37"},
    {file = "fastuuid-0.12.0-cp313-cp313-win_amd64.whl", hash = "sha256:8fc66b11423e6f3e1937385f655bedd67aebe56a3dcec0cb835351cfe7d358c9"},
-    {file = "fastuuid-0.12.0-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:2925f67b88d47cb16aa3eb1ab20fdcf21b94d74490e0818c91ea41434b987493"},
    {file = "fastuuid-0.12.0-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:7b15c54d300279ab20a9cc0579ada9c9f80d1bc92997fc61fb7bf3103d7cb26b"},
    {file = "fastuuid-0.12.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:458f1bc3ebbd76fdb89ad83e6b81ccd3b2a99fa6707cd3650b27606745cfb170"},
    {file = "fastuuid-0.12.0-cp38-cp38-manylinux_2_34_x86_64.whl", hash = "sha256:a8f0f83fbba6dc44271a11b22e15838641b8c45612cdf541b4822a5930f6893c"},
@ -4170,8 +4169,6 @@ groups = ["main"]
 markers = "extra == \"dlt\""
 files = [
    {file = "jsonpath-ng-1.7.0.tar.gz", hash = "sha256:f6f5f7fd4e5ff79c785f1573b394043b39849fb2bb47bcead935d12b00beab3c"},
-    {file = "jsonpath_ng-1.7.0-py2-none-any.whl", hash = "sha256:898c93fc173f0c336784a3fa63d7434297544b7198124a68f9a3ef9597b0ae6e"},
-    {file = "jsonpath_ng-1.7.0-py3-none-any.whl", hash = "sha256:f3d7f9e848cba1b6da28c55b1c26ff915dc9e0b1ba7e752a53d6da8d5cbd00b6"},
 ]

 [package.dependencies]
@ -8593,7 +8590,6 @@ files = [
    {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:bb89f0a835bcfc1d42ccd5f41f04870c1b936d8507c6df12b7737febc40f0909"},
    {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:f0c2d907a1e102526dd2986df638343388b94c33860ff3bbe1384130828714b1"},
    {file = "psycopg2_binary-2.9.10-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f8157bed2f51db683f31306aa497311b560f2265998122abe1dce6428bd86567"},
-    {file = "psycopg2_binary-2.9.10-cp313-cp313-win_amd64.whl", hash = "sha256:27422aa5f11fbcd9b18da48373eb67081243662f9b46e6fd07c3eb46e4535142"},
    {file = "psycopg2_binary-2.9.10-cp38-cp38-macosx_12_0_x86_64.whl", hash = "sha256:eb09aa7f9cecb45027683bb55aebaaf45a0df8bf6de68801a6afdc7947bb09d4"},
    {file = "psycopg2_binary-2.9.10-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:b73d6d7f0ccdad7bc43e6d34273f70d587ef62f824d7261c4ae9b8b1b6af90e8"},
    {file = "psycopg2_binary-2.9.10-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ce5ab4bf46a211a8e924d307c1b1fcda82368586a19d0a24f8ae166f5c784864"},
--- a/pyproject.toml
+++ b/pyproject.toml
@ -1,7 +1,7 @@
 [project]
 name = "cognee"

-version = "0.3.7"
+version = "0.3.7.dev1"
 description = "Cognee - is a library for enriching LLM context with a semantic layer for better understanding and reasoning."
 authors = [
    { name = "Vasilije Markovic" },
--- a/uv.lock
+++ b/uv.lock