AI & RAG PDF Table to Markdown/JSON Extractor
Extracts clean Markdown, structured tables, metadata, and token-aware overlapping chunks from PDF URLs for LLM RAG pipelines (LangChain, LlamaIndex, OpenAI, Anthropic, Gemini).
33%
users
Apify builder
Ulrich Sofner Cervatti Data & GPU Compute Engineer | High-Scale Web Scraping, Brazil Gov/B2B APIs, Docling PDF OCR & DuckDB Pipelines
Leaderboard position
out of 10,354
New actors
#1,657
Total actors
#3,805
↓ -657
Monthly users
#4,201
↓ -635
Total users
#5,787
↓ -712
Monthly runs
#5,161
↑ +2,749
Total runs
#8,226
↑ +547
Portfolio stats
New actors
3
Total actors
3
+0
Monthly users
3
+0
Total users
6
+0
Monthly runs
48
↑ +45
Total runs
52
↑ +45
New actors
Each bar shows one day in the last 30 days.
Portfolio concentration
3 of 3 actors cover 80%+ of monthly users.
Extracts clean Markdown, structured tables, metadata, and token-aware overlapping chunks from PDF URLs for LLM RAG pipelines (LangChain, LlamaIndex, OpenAI, Anthropic, Gemini).
33%
users
Enriches Brazilian company registration numbers (CNPJ) in batch via BrasilAPI & ReceitaWS with automatic failover. Normalizes QSA (corporate partners), primary/secondary CNAEs, share capital (Capital Social), Simples Nacional/MEI status, address, phones, and emails.
33%
users
Scrapes and filters official Brazilian Government Procurement & Tenders from Portal Nacional de Contratações Públicas (PNCP API) by date range, state (UF), modality, and keywords. Outputs structured high-value government contracts, buyer CNPJ, estimated values, and edital links.
33%
users
ActorHunt MCP
ActorHunt gives paid members MCP access to keyword data, actor evidence, and Store movement for deciding what to build next.