Docs to Markdown for RAG (PDF, Word, PowerPoint, Excel)
Pricing
$4.00 / 1,000 page converteds
Docs to Markdown for RAG (PDF, Word, PowerPoint, Excel)
Turn PDF, Word, PowerPoint, Excel, CSV and HTML files into clean Markdown with real tables, then split it into token-counted chunks with heading paths, ready for embeddings, RAG and AI agents.
Pricing
$4.00 / 1,000 page converteds
Rating
0.0
(0)
Developer
Kapil sarma
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 hours ago
Last modified
Categories
Share
Docs to Markdown for RAG: PDF, Word, PowerPoint, Excel
Turn documents into clean Markdown that AI models read well, then split it into token-counted chunks ready for embeddings. Paste file links; get Markdown with real tables and chunks that keep their headings.
What you get
- Seven formats, one output: PDF, Word (DOCX), PowerPoint (PPTX), Excel (XLSX), CSV, HTML, Markdown and plain text.
- Real tables. Word, Excel, CSV and HTML tables become Markdown tables, not jumbled text.
- Readable PDFs. Lines that a PDF wrapped are joined back into paragraphs, words split with a hyphen are rejoined, and bullets become lists. Optional
<!-- page N -->markers let you cite page numbers. - Slides with notes. Each slide becomes a section with its title, bullet points and speaker notes.
- Chunks for RAG. Split by headings, then paragraphs, then sentences, up to your token limit, with overlap. Each chunk carries its heading path (for example
Guide > Install > Linux) and its token count, using the cl100k tokenizer used by OpenAI embedding models. - Two output shapes. One row per document, or one row per chunk, ready to load into Pinecone, Qdrant, Weaviate, pgvector or any vector database.
Input
| Field | Example |
|---|---|
| File URLs | https://arxiv.org/pdf/1706.03762, a Dropbox or S3 link, any direct download link |
| Split into chunks | on |
| Chunk size (tokens) | 512 |
| Chunk overlap (tokens) | 50 |
| Output | One row per document, or one row per chunk |
| Add page markers to PDFs | off |
Output (one row per chunk)
Files that fail (a broken link, an unsupported type) get a row with an error field, so you can see exactly which ones to fix.
Pricing
You pay per page converted. A page is a PDF page or a slide. For formats without pages (Word, Excel, CSV, HTML, text), every 3,000 characters of output count as one page. A file is only charged if it converts.
Good to know
- Scanned PDFs (images of text) have no text layer, and this Actor does not run OCR. They come back with a warning saying so.
- Links must download the file directly. A Google Drive share link usually opens a preview page instead; use a direct download link.
- PDF headings are kept as their own paragraphs but are not marked as Markdown headings, because PDFs don't store which lines are headings. Word and HTML headings become real Markdown headings.
- Files up to 50 MB by default; raise "Max file size" for larger ones.
