Commit 73964f39 authored by Jan Reimes's avatar Jan Reimes
Browse files

refactor(logging): replace logging with custom logger across modules 

* Updated logging implementation to use `get_logger` from tdoc_crawler.
* Refactored migration.py, pg0_manager.py, processor.py, rag.py, shared_storage.py, seeder.py, classify.py, extraction.py, figure_descriptor.py, llm_client.py, summarize.py, workspace_registry.py, and workspaces.py.
* Improved consistency in logging practices across the codebase.
parent 7ee219bd

packages/3gpp-ai/threegpp_ai/lightrag/migration.py

+2 −2
Original line number Diff line number Diff line
@@ -15,15 +15,15 @@ Usage: 
from __future__ import annotations



import json

import logging

from pathlib import Path

from typing import Any



from lightrag.utils import compute_mdhash_id

from tdoc_crawler.logging import get_logger



from .shared_storage import SharedNanoVectorDBStorage, WorkspaceIndex



logger = logging.getLogger(__name__)

logger = get_logger(__name__)





async def migrate_to_shared_storage(

packages/3gpp-ai/threegpp_ai/lightrag/pg0_manager.py

+3 −2
Original line number Diff line number Diff line
@@ -4,16 +4,17 @@ This module manages pg0 lifecycle for PostgreSQL-backed LightRAG storage. 
pg0 is a zero-config embedded PostgreSQL with pgvector extension.

"""



import logging

from collections.abc import Generator

from contextlib import contextmanager



from tdoc_crawler.logging import get_logger



try:

    from pg0 import Pg0 as _Pg0

except ImportError:

    _Pg0 = None



logger = logging.getLogger(__name__)

logger = get_logger(__name__)





class Pg0Manager:

packages/3gpp-ai/threegpp_ai/lightrag/processor.py

+3 −2
Original line number Diff line number Diff line
@@ -6,12 +6,13 @@ for text extraction and artifact handling. 


from __future__ import annotations



import logging

from dataclasses import dataclass

from enum import StrEnum

from pathlib import Path

from typing import Any



from tdoc_crawler.logging import get_logger



from threegpp_ai.models import ConversionError, ExtractionError

from threegpp_ai.operations.conversion import OFFICE_FORMATS

from threegpp_ai.operations.extraction import extract_document_structured
@@ -20,7 +21,7 @@ from .config import LightRAGConfig 
from .metadata import RAGMetadata, enrich_text

from .rag import TDocRAG



logger = logging.getLogger(__name__)

logger = get_logger(__name__)



# All supported formats (re-exported from conversion module for convenience)

SUPPORTED_FORMATS = {".pdf", ".txt", ".md"} | OFFICE_FORMATS

packages/3gpp-ai/threegpp_ai/lightrag/rag.py

+2 −2
Original line number Diff line number Diff line
@@ -8,7 +8,6 @@ This module provides a thin wrapper around LightRAG with: 


from __future__ import annotations



import logging

from collections.abc import Callable

from dataclasses import dataclass

from functools import wraps
@@ -27,6 +26,7 @@ from lightrag.llm.openai import openai_complete, openai_embed 
from lightrag.llm.zhipu import zhipu_complete, zhipu_embedding

from lightrag.utils import EmbeddingFunc

from tdoc_crawler.config import resolve_cache_manager

from tdoc_crawler.logging import get_logger



from .config import LightRAGConfig, QueryMode, StorageBackend

from .pg0_manager import Pg0Manager
@@ -87,7 +87,7 @@ zhipu_module.zhipu_complete_if_cache = patched_zhipu_complete_if_cache 
zhipu_module.zhipu_embedding = patched_zhipu_embedding



STORAGES["SharedNanoVectorDBStorage"] = "threegpp_ai.lightrag.shared_storage"

logger = logging.getLogger(__name__)

logger = get_logger(__name__)





@dataclass(frozen=True)

packages/3gpp-ai/threegpp_ai/lightrag/seeder.py

+2 −2
Original line number Diff line number Diff line
@@ -6,17 +6,17 @@ into the LightRAG knowledge graph after document indexing. 


from __future__ import annotations



import logging

from dataclasses import dataclass

from enum import StrEnum

from typing import Any



from tdoc_crawler.logging import get_logger

from tdoc_crawler.tdocs.utils import normalize_tdoc_id



from .metadata import normalize_release_label

from .rag import TDocRAG



logger = logging.getLogger(__name__)

logger = get_logger(__name__)





class EntityType(StrEnum):