Commit e1f50943 authored by Jan Reimes's avatar Jan Reimes
Browse files

refactor: resolve codebase concerns 

- Fix SpecSource Protocol to use proper '...' syntax instead of NotImplementedError
- Consolidate normalization functions to tdoc_crawler.utils.normalization
  - Add normalize_tdoc_id(), normalize_tdoc_ids(), normalize_portal_meeting_name()
  - Re-export from tdocs/utils.py and meetings/utils.py for backward compatibility
- Improve workspace error handling
  - Add WorkspaceNotFoundError exception
  - List members and process commands now clearly distinguish workspace not found
  - Export WorkspaceNotFoundError from threegpp_ai package
- Update migration module documentation
  - Remove misleading TODO comment
  - Document module's role in shared storage consolidation
parent 25ce4f5a

packages/3gpp-ai/threegpp_ai/__init__.py

+2 −1
Original line number Diff line number Diff line
@@ -27,7 +27,7 @@ from threegpp_ai.lightrag import ( 
    create_metadata_from_dict,

    enrich_text,

)

from threegpp_ai.models import SourceKind, SummarizeResult

from threegpp_ai.models import SourceKind, SummarizeResult, WorkspaceNotFoundError

from threegpp_ai.operations.convert import convert_tdoc as convert_document

from threegpp_ai.operations.convert import convert_tdoc_to_markdown

from threegpp_ai.operations.summarize import summarize_tdoc as summarize_document
@@ -81,6 +81,7 @@ __all__ = [ 
    "SummarizeResult",

    "TDocProcessor",

    "TDocRAG",

    "WorkspaceNotFoundError",

    "WorkspaceRegistry",

    "add_workspace_members",

    "checkout_spec_to_workspace",

packages/3gpp-ai/threegpp_ai/cli.py

+14 −2
Original line number Diff line number Diff line
@@ -83,6 +83,7 @@ from threegpp_ai.lightrag.config import LightRAGConfig 
from threegpp_ai.lightrag.metadata import RAGMetadata

from threegpp_ai.lightrag.processor import DocumentProcessor

from threegpp_ai.lightrag.rag import PROVIDER_ALIASES, PROVIDERS

from threegpp_ai.models import WorkspaceNotFoundError

from threegpp_ai.operations.classify import pick_main_document

from threegpp_ai.operations.conversion import OFFICE_FORMATS, convert_to_pdf

from threegpp_ai.operations.convert import convert_document_to_markdown
@@ -802,7 +803,12 @@ def workspace_list_members( 
    json_output: JsonOutputOption = False,

) -> None:

    workspace_name = _resolve_workspace_name(workspace)



    try:

        members = list_workspace_members(workspace_name, include_inactive=include_inactive)

    except WorkspaceNotFoundError:

        console.print(f"[red]Workspace '{workspace_name}' not found[/red]")

        raise typer.Exit(1)



    if json_output:

        typer.echo(
@@ -839,7 +845,13 @@ def workspace_process( 
    json_output: JsonOutputOption = False,

) -> None:

    workspace_name = _resolve_workspace_name(workspace)



    try:

        members = list_workspace_members(workspace_name, include_inactive=False)

    except WorkspaceNotFoundError:

        console.print(f"[red]Workspace '{workspace_name}' not found[/red]")

        raise typer.Exit(1)



    if limit is not None and limit > 0:

        members = members[:limit]

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

+3 −3
Original line number Diff line number Diff line
@@ -8,9 +8,9 @@ Usage: 
    >>> await migrate_to_shared_storage(working_dir, embedding_model)

"""



# TODO: Is this module needed at all? No need for legacy migration if we just switch

# to shared storage for all new workspaces. Maybe just keep the consolidation function

# for users who want to merge existing workspaces into shared storage?

# This module provides essential functionality for migrating existing workspace

# embeddings to shared storage format, eliminating duplicates and improving efficiency.

# Used by the `tdoc-crawler ai rag migrate` command.



from __future__ import annotations

packages/3gpp-ai/threegpp_ai/models.py

+4 −0
Original line number Diff line number Diff line
@@ -75,6 +75,10 @@ class EmbeddingDimensionError(AiError): 
    """Embedding model dimension mismatch with stored vectors."""





class WorkspaceNotFoundError(AiError):

    """Workspace does not exist in registry."""





class Workspace(BaseModel):

    """Logical workspace boundary for AI processing."""

packages/3gpp-ai/threegpp_ai/operations/workspaces.py

+5 −1
Original line number Diff line number Diff line
@@ -22,6 +22,7 @@ from tdoc_crawler.tdocs.sources.whatthespec import resolve_via_whatthespec 
from tdoc_crawler.tdocs.utils import normalize_tdoc_id

from tdoc_crawler.utils.normalization import normalize_spec_number, resolve_release_to_full_version



from threegpp_ai.models import WorkspaceNotFoundError

from threegpp_ai.operations.workspace_names import DEFAULT_WORKSPACE, is_default_workspace, normalize_workspace_name

from threegpp_ai.operations.workspace_registry import (

    WorkspaceMember,
@@ -250,13 +251,16 @@ def list_workspace_members( 


    Returns:

        List of WorkspaceMember.



    Raises:

        WorkspaceNotFoundError: If workspace does not exist.

    """

    normalized_workspace = normalize_workspace_name(workspace)

    registry = _get_registry()



    metadata = registry.get_workspace(normalized_workspace)

    if metadata is None:

        return []

        raise WorkspaceNotFoundError(f"Workspace '{normalized_workspace}' not found")



    return metadata.list_members(include_inactive=include_inactive)