PDF Table, Datasheet & RAG Markdown Extractor avatar

PDF Table, Datasheet & RAG Markdown Extractor

Pricing

from $2.00 / 1,000 pdf page processeds

Go to Apify Store
PDF Table, Datasheet & RAG Markdown Extractor

PDF Table, Datasheet & RAG Markdown Extractor

Extract structured JSON/CSV tables, engineering specs with units, compliance tags (RoHS/ISO/CE/UL), and RAG-ready Markdown chunks from any public PDF URL — zero LLM API keys required.

Pricing

from $2.00 / 1,000 pdf page processeds

Rating

0.0

(0)

Developer

Riccardo Viola

Riccardo Viola

Maintained by Community

Actor stats

0

Bookmarked

2

Total users

1

Monthly active users

5 hours ago

Last modified

Categories

Features

Limited permissions

Share

PDF Table, Engineering Datasheet & RAG Markdown Extractor

Turn any public PDF URL (engineering datasheets, BOMs, technical manuals, RFPs, financial statements, or research reports) into clean JSON/CSV tables, structured engineering specifications with physical units, compliance standards tags, and RAG-ready chunked Markdown — with zero external LLM API keys required.

Built for AI agents (MCP), n8n / Make workflows, hardware & procurement teams, and RAG data pipelines.


What You Get (Sample Output)

{
"url": "https://www.ti.com/lit/ds/symlink/ne555.pdf",
"status": "ok",
"title": "xx555 Precision Timers datasheet (Rev. K)",
"totalPages": 39,
"pagesProcessed": 6,
"wordCount": 2650,
"approxTokens": 4420,
"isLikelyScanned": false,
"tableCount": 8,
"specCount": 24,
"chunkCount": 18,
"tables": [
{
"page": 5,
"tableIndex": 0,
"headers": ["Parameter", "Test Conditions", "Min", "Typ", "Max", "Unit"],
"records": [
{ "Parameter": "Supply voltage (VCC)", "Test Conditions": "NE555", "Min": "4.5", "Typ": "", "Max": "16", "Unit": "V" }
],
"markdown": "| Parameter | Test Conditions | Min | Typ | Max | Unit |\n| --- | --- | --- | --- | --- | --- |\n| Supply voltage (VCC) | NE555 | 4.5 | | 16 | V |"
}
],
"technicalSpecs": [
{ "parameter": "NE555 T", "value": "0°C to 70°C", "page": 1, "source": "text" },
{ "parameter": "High-level output voltage", "value": "15V, I = -200mA 12.5 V", "page": 6, "source": "text" }
],
"ragChunks": [
{
"chunkIndex": 0,
"pageStart": 1,
"pageEnd": 1,
"charCount": 1820,
"approxTokens": 455,
"text": "## Page 1\n\n..."
}
]
}

Why Use This Instead of Basic PDF-to-Text Dumpers?

FeatureBasic PDF-to-Text ScrapersThis Actor
Structured table detection (headers, rows, records[], Markdown)NoYes
Engineering spec & physical unit mining (V, mA, MHz, °C, mm, MPa, etc.)NoYes
Automatic compliance tag detection (RoHS, REACH, CE, UL, FCC, ISO, IEC, IEEE, ASTM, IP)NoYes
Token-estimated overlapping RAG chunks with page numbersNoYes
3 export modes (per_document, per_table for Excel/Sheets, per_chunk for Vector DBs)NoYes
Scanned-PDF warning flag (isLikelyScanned)RareYes
Zero LLM API keys, zero proxies, deterministic speed—Yes

Output Modes

  • per_document (default): One comprehensive JSON object per PDF URL containing metadata, all tables, technical specs, compliance tags, full Markdown, and RAG chunks.
  • per_table: Flattens every detected table into its own dataset row — perfect for exporting directly to CSV, Excel, Airtable, or Google Sheets.
  • per_chunk: Flattens every RAG Markdown chunk into its own dataset row with url, title, pageStart, pageEnd, and approxTokens — ready to upsert straight into Pinecone, Qdrant, Chroma, or pgvector via n8n/Make.

Pricing (Pay-Per-Event)

Transparent, predictable event billing — set a hard spending limit on any run:

  • Actor Start (actor-start): charged once per run.
  • Per Page Processed (pdf-page-processed): charged per PDF page actually parsed (capped by your maxPagesPerPdf setting).

Limitations

  • Works on publicly accessible PDF URLs (http:// / https://) up to maxPdfSizeMb (default 25 MB).
  • Uses deterministic text & layout extraction (no OCR). Image-only scanned PDFs are automatically flagged with "isLikelyScanned": true so downstream pipelines can route them to OCR only when needed.