Commit f14be17c authored by Jan Reimes's avatar Jan Reimes
Browse files

🔧 chore(ai): remove unused imports and consolidate options

parent 27d0f6de

src/tdoc_crawler/cli/ai.py

+16 −33
Original line number Diff line number Diff line
@@ -8,10 +8,8 @@ import platform 
from datetime import UTC, datetime

from functools import cache

from pathlib import Path

from typing import Annotated



import typer

from rich.console import Console

from rich.progress import BarColumn, Progress, SpinnerColumn, TaskProgressColumn, TextColumn, TimeRemainingColumn

from rich.table import Table

from tdoc_ai import (
@@ -53,19 +51,18 @@ from tdoc_crawler.cli.args import ( 
    EmbeddingTopKOption,

    EndDateOption,

    GraphQueryArgument,

    GraphQueryOption,

    JsonOutputOption,

    ProcessAllOption,

    ProcessForceOption,

    ProcessLimitOption,

    ProcessNewOnlyOption,

    QueryArgument,

    QueryOption,

    QueryMaxWordsOption,

    SourcePatternExcludeOption,

    SourcePatternOption,

    StartDateOption,

    StatusTDocIdOption,

    SummarizeDocumentArgument,

    SummarizeFormatOption,

    SummarizeWordsOption,

    TitlePatternExcludeOption,

    TitlePatternOption,
@@ -86,12 +83,13 @@ from tdoc_crawler.cli.args import ( 
)

from tdoc_crawler.config import CacheManager, resolve_cache_manager

from tdoc_crawler.database import TDocDatabase

from tdoc_crawler.logging import get_console

from tdoc_crawler.tdocs.models import TDocQueryConfig

from tdoc_crawler.utils.date_parser import parse_partial_date

from tdoc_crawler.utils.normalization import resolve_release_to_full_version



ai_app = typer.Typer(help="AI document processing commands")

console = Console()

console = get_console()

_logger = logging.getLogger(__name__)
@@ -120,25 +118,14 @@ def resolve_workspace(workspace: str | None) -> str: 
@ai_app.command("summarize")

def ai_summarize(

    document_id: SummarizeDocumentArgument,

    words: SummarizeWordsOption = 200,

    output_format: SummarizeFormatOption = "markdown",

    json_output: Annotated[bool, typer.Option("--json", help="Output as JSON (overrides --format)")] = False,

    max_words: SummarizeWordsOption = 200,

) -> None:

    """Summarize a single document with specified word count."""

    try:

        result = summarize_document(document_id=document_id, words=words, fetch_remote=True)



        if json_output or output_format == "json":

            typer.echo(result.to_json())

        elif output_format == "yaml":

            typer.echo(result.to_yaml())

        else:

        result = summarize_document(document_id=document_id, max_words=max_words, fetch_remote=True)

        console.print(f"## Summary for {document_id}")

        console.print(result.summary)

    except Exception as exc:

        if json_output:

            typer.echo(json.dumps({"error": str(exc)}), err=True)

        else:

        console.print(f"[red]Error: {exc}[/red]")

        raise typer.Exit(1) from exc
@@ -173,18 +160,16 @@ def ai_convert( 


@ai_app.command("query")

def ai_query(

    query_arg: QueryArgument = None,

    query: QueryOption = None,

    query_text: QueryArgument,

    workspace: WorkspaceNameOption = None,

    top_k: EmbeddingTopKOption = 5,

    words: int = typer.Option(300, "--words", help="Target word count for LLM answer (default: 300)"),

    top_k: EmbeddingTopKOption = 8,

    max_words: QueryMaxWordsOption = 300,

    json_output: JsonOutputOption = False,

) -> None:

    """Search TDocs using semantic embeddings and knowledge graph (RAG + GraphRAG).



    Uses LLM to synthesize an answer from embedding and graph context.

    """

    query_text = query or query_arg

    if not query_text:

        console.print("[red]Error: query is required (positional or --query).[/red]")

        raise typer.Exit(1)
@@ -200,7 +185,7 @@ def ai_query( 
        query_text,

        workspace=resolved_workspace,

        embedding_chunks=embedding_results,

        max_words=words,

        max_words=max_words,

        query_level="advanced",  # Always use LLM synthesis

    )
@@ -249,7 +234,7 @@ def ai_process( 
    force: ProcessForceOption = False,

    accelerate: EmbeddingBackendOption = "torch",

    json_output: JsonOutputOption = False,

    limit: int | None = typer.Option(None, "--limit", "-l", help="Limit number of documents to process (for testing)"),

    limit: ProcessLimitOption = None,

) -> None:

    """Process all documents in a workspace through the AI pipeline.
@@ -340,13 +325,11 @@ def ai_status( 


@ai_app.command("graph")

def ai_graph(

    query_arg: GraphQueryArgument = None,

    query: GraphQueryOption = None,

    query_text: GraphQueryArgument = None,

    workspace: WorkspaceNameOption = None,

    json_output: JsonOutputOption = False,

) -> None:

    """Query the knowledge graph for a workspace."""

    query_text = query or query_arg

    if not query_text:

        console.print("[red]Error: query is required (positional or --query).[/red]")

        raise typer.Exit(1)
@@ -721,7 +704,7 @@ def workspace_process( 
    new_only: WorkspaceProcessNewOnlyOption = True,

    force_rerun: WorkspaceProcessForceOption = False,

    json_output: JsonOutputOption = False,

    limit: int | None = typer.Option(None, "--limit", "-l", help="Limit number of documents to process (for testing)"),

    limit: ProcessLimitOption = None,

) -> None:

    """Process all active document members in a workspace through the AI pipeline.

src/tdoc_crawler/cli/args.py

+3 −4
Original line number Diff line number Diff line
@@ -152,8 +152,7 @@ NoProgressOption = Annotated[ 


# Options - AI

SummarizeDocumentArgument = Annotated[str, typer.Argument(help="Document ID to summarize")]

SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target word count (default: 200)")]

SummarizeFormatOption = Annotated[str, typer.Option("--format", "-f", help="Output format (markdown, json, yaml)")]

SummarizeWordsOption = Annotated[int, typer.Option("--words", "-w", help="Target/Maximum word count (default: 200)")]

JsonOutputOption = Annotated[bool, typer.Option("--json", help="Output as JSON")]



ConvertDocumentArgument = Annotated[str, typer.Argument(help="Document ID to convert")]
@@ -163,9 +162,9 @@ ConvertOutputOption = Annotated[ 
]



QueryArgument = Annotated[str | None, typer.Argument(help="Semantic search query")]

QueryOption = Annotated[str | None, typer.Option("--query", help="Semantic search query")]

WorkspaceNameOption = Annotated[str | None, typer.Option("--workspace", "-w", help="Workspace name")]

EmbeddingTopKOption = Annotated[int, typer.Option("--top-k", "-k", help="Number of embedding results to return")]

QueryMaxWordsOption = Annotated[int, typer.Option("--words", help="Maximum word count for LLM answer (default: 300)")]



_ = Annotated[str | None, typer.Option("--tdoc-id", "-t", help="TDoc ID to process")]

EmbeddingBackendOption = Annotated[
@@ -182,11 +181,11 @@ CheckoutBaseOption = Annotated[str | None, typer.Option("--checkout-base", help= 
ProcessAllOption = Annotated[bool, typer.Option("--all", help="Process all documents in workspace")]

ProcessNewOnlyOption = Annotated[bool, typer.Option("--new-only", help="Process only new documents")]

ProcessForceOption = Annotated[bool, typer.Option("--force", help="Force reprocessing")]

ProcessLimitOption = Annotated[int | None, typer.Option("--limit", "-l", help="Limit number of documents to process (for testing)")]



StatusTDocIdOption = Annotated[str | None, typer.Option("--tdoc-id", "-t", help="TDoc ID to check status for")]



GraphQueryArgument = Annotated[str | None, typer.Argument(help="Graph query string")]

GraphQueryOption = Annotated[str | None, typer.Option("--query", help="Graph query string")]



WorkspaceNameArgument = Annotated[str, typer.Argument(help="Workspace name")]

WorkspaceActivateArgument = Annotated[str, typer.Argument(help="Workspace name to activate")]