feat(platform): simplify file tools — auto RAG indexing, remove parse/template ops

packages/tale_knowledge/src/tale_knowledge/extraction/__init__.py

@@ -1,5 +1,5 @@
 """File text extraction modules."""
 
-from .router import extract_text
+from .router import ProgressCallback, extract_text
 
-__all__ = ["extract_text"]
+__all__ = ["ProgressCallback", "extract_text"]

packages/tale_knowledge/src/tale_knowledge/extraction/pdf.py

@@ -8,6 +8,7 @@
 from __future__ import annotations
 
 import asyncio
+from collections.abc import Callable
 from functools import partial
 from typing import TYPE_CHECKING
 
@@ -19,6 +20,8 @@
 if TYPE_CHECKING:
     from tale_knowledge.vision.client import VisionClient
 
+ProgressCallback = Callable[[int, int], None]  # (pages_done, total_pages)
+
 LARGE_IMAGE_RATIO = 0.5
 MAX_PAGES = 2000
 DEFAULT_PAGE_CONCURRENCY = 8
@@ -139,6 +142,7 @@ async def extract_text_from_pdf_bytes(
     vision_client: VisionClient | None = None,
     process_images: bool = True,
     max_pages: int = MAX_PAGES,
+    on_progress: ProgressCallback | None = None,
 ) -> tuple[str, bool]:
     """Extract text from PDF bytes.
 
@@ -148,6 +152,8 @@ async def extract_text_from_pdf_bytes(
         vision_client: Optional VisionClient for OCR/image description.
         process_images: Whether to extract and describe embedded images.
         max_pages: Maximum number of pages to process.
+        on_progress: Optional callback ``(pages_done, total_pages)`` invoked
+            after each page completes.  Safe to call from concurrent tasks.
 
     Returns:
         Tuple of (extracted_text, vision_was_used).
@@ -182,7 +188,10 @@ async def extract_text_from_pdf_bytes(
     finally:
         doc.close()
 
+    pages_done = 0
+
     async def process_page(page_num: int, page_bytes: bytes) -> tuple[int, str, bool]:
+        nonlocal pages_done
         async with page_semaphore:
             content, vis_used = await _extract_page_with_layout(
                 page_bytes,
@@ -191,6 +200,9 @@ async def process_page(page_num: int, page_bytes: bytes) -> tuple[int, str, bool
                 vision_client,
                 process_images,
             )
+            pages_done += 1
+            if on_progress is not None:
+                on_progress(pages_done, pages_to_process)
             return page_num, f"--- Page {page_num + 1} ---\n{content}", vis_used
 
     tasks = [process_page(pn, pb) for pn, pb in page_data]

packages/tale_knowledge/src/tale_knowledge/extraction/router.py

@@ -2,6 +2,7 @@
 
 from __future__ import annotations
 
+from collections.abc import Callable
 from pathlib import Path
 from typing import TYPE_CHECKING
 
@@ -33,12 +34,16 @@ def is_supported(filename: str) -> bool:
     return Path(filename).suffix.lower() in ALL_SUPPORTED_EXTENSIONS
 
 
+ProgressCallback = Callable[[int, int], None]
+
+
 async def extract_text(
     file_bytes: bytes,
     filename: str,
     *,
     vision_client: VisionClient | None = None,
     process_images: bool = True,
+    on_progress: ProgressCallback | None = None,
 ) -> tuple[str, bool]:
     """Extract text from file bytes, routing to the correct extractor.
 
@@ -47,6 +52,8 @@ async def extract_text(
         filename: Original filename (used to determine file type).
         vision_client: Optional VisionClient for OCR/image description.
         process_images: Whether to extract and describe embedded images.
+        on_progress: Optional callback ``(done, total)`` for page-level progress
+            (currently only used by PDF extraction).
 
     Returns:
         Tuple of (extracted_text, vision_was_used).
@@ -65,6 +72,7 @@ async def extract_text(
             filename,
             vision_client=vision_client,
             process_images=process_images,
+            on_progress=on_progress,
         )
 
     if suffix in DOCX_EXTENSIONS:

services/crawler/app/models.py

@@ -207,6 +207,18 @@ class HtmlToDocxRequest(BaseModel):
 # ==================== PPTX Models ====================
 
 
+class MarkdownToPptxRequest(BaseModel):
+    """Request to convert Markdown to PPTX."""
+
+    content: str = Field(..., description="Markdown content to convert")
+
+
+class HtmlToPptxRequest(BaseModel):
+    """Request to convert HTML to PPTX."""
+
+    html: str = Field(..., description="HTML content to convert")
+
+
 class TableData(BaseModel):
     """Table data for PPTX generation."""
 

services/crawler/app/routers/pptx.py

@@ -6,11 +6,14 @@
 import json
 
 from fastapi import APIRouter, File, Form, HTTPException, UploadFile, status
+from fastapi.responses import Response
 from loguru import logger
 
 from app.models import (
     FileMetadataResponse,
     GeneratePptxResponse,
+    HtmlToPptxRequest,
+    MarkdownToPptxRequest,
     ParseFileResponse,
 )
 from app.services.file_parser_service import get_file_parser_service
@@ -133,6 +136,88 @@ async def generate_pptx_from_json(
         )
 
 
+_PPTX_CONTENT_TYPE = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
+
+
+@router.post("/from-markdown")
+async def convert_markdown_to_pptx(request: MarkdownToPptxRequest):
+    """
+    Convert Markdown content to PPTX.
+
+    Parses markdown into HTML, then extracts slide structure (headings become
+    slide titles, lists become bullet points, etc.) and generates a PowerPoint.
+
+    Args:
+        request: Markdown content
+
+    Returns:
+        PPTX file as binary response
+    """
+    try:
+        from app.services.base_converter import BaseConverterService
+        from app.services.html_to_pptx_converter import html_to_slides
+
+        converter = BaseConverterService()
+        html = await converter.markdown_to_html(request.content)
+        slides_content = html_to_slides(html)
+
+        template_service = get_template_service()
+        pptx_bytes = await template_service.generate_pptx_from_content(
+            slides_content=slides_content,
+        )
+
+        return Response(
+            content=pptx_bytes,
+            media_type=_PPTX_CONTENT_TYPE,
+            headers={"Content-Disposition": "attachment; filename=presentation.pptx"},
+        )
+
+    except Exception:
+        logger.exception("Error converting markdown to PPTX")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail="Failed to convert markdown to PPTX",
+        ) from None
+
+
+@router.post("/from-html")
+async def convert_html_to_pptx(request: HtmlToPptxRequest):
+    """
+    Convert HTML content to PPTX.
+
+    Parses HTML to extract slide structure (h1/h2 headings become slide titles,
+    lists become bullet points, tables preserved) and generates a PowerPoint.
+
+    Args:
+        request: HTML content
+
+    Returns:
+        PPTX file as binary response
+    """
+    try:
+        from app.services.html_to_pptx_converter import html_to_slides
+
+        slides_content = html_to_slides(request.html)
+
+        template_service = get_template_service()
+        pptx_bytes = await template_service.generate_pptx_from_content(
+            slides_content=slides_content,
+        )
+
+        return Response(
+            content=pptx_bytes,
+            media_type=_PPTX_CONTENT_TYPE,
+            headers={"Content-Disposition": "attachment; filename=presentation.pptx"},
+        )
+
+    except Exception:
+        logger.exception("Error converting HTML to PPTX")
+        raise HTTPException(
+            status_code=status.HTTP_500_INTERNAL_SERVER_ERROR,
+            detail="Failed to convert HTML to PPTX",
+        ) from None
+
+
 @router.post("/parse", response_model=ParseFileResponse)
 async def parse_pptx_file(
     file: UploadFile = _FILE_UPLOAD,