PDF Citation Chunker

OCR Citation Chunker

skilled_glee/ocr-citation-chunker

Convert scanned or image-based PDFs into page-aware, citation-ready JSON chunks with OCR confidence for RAG, search, and agent workflows.

PDF to RAG-Ready Dataset

utilityforgelab/pdf-to-rag-ready-dataset

Convert public text-based PDFs into clean, token-aware RAG chunks with Markdown, page references, metadata, stable document IDs, and ready-to-use Apify Dataset output.

PDF Evidence Graph API

axetl_industries/my-actor

Turn public text-layer PDFs into deterministic, citation-ready JSON for AI agents, RAG pipelines, APIs, and developer workflows. Extract page-level evidence spans, stable citation IDs, document/page hashes, outlines, and internal/outbound link graphs. No OCR, authentication, or private documents.

Convert PDFs into token-bounded Markdown chunks for RAG, embeddings, and vector databases (Pinecone, Chroma, Weaviate, Qdrant). Set maxTokens + overlap; get clean chunks with page number, token count, and SHA-256 content hash for dedup. JSON dataset ready for any LLM pipeline.

Chunk tender text for RAG/embeddings with stable ids and metadata.

RAG-Ready Markdown Converter & Chunker

foxpink/apify-rag-markdown-chunker

Convert raw HTML/text into clean Markdown and split into ready-to-ingest chunks for RAG pipelines, Vector DBs, and LLM fine-tuning workflows.

Source Receipt Extractor

z3n_m4nt1s/source-receipt-extractor

Extract clean public-page text with timestamped SHA-256 source receipts for AI, RAG, research, and audit workflows.

PDF Text Extractor & Change Monitor

produkdigitalali/pdf-text-extractor-change-monitor

Extract text, page content, metadata, and RAG-ready chunks from PDFs. Monitor content, page, and metadata changes across runs.

Convert news and announcements into RAG-ready Markdown chunks. Clean JSON for PR, media-monitoring teams and AI agents.

Rag Content Chunker

labrat011/rag-content-chunker

Turn raw text, Markdown, or Apify datasets into token-perfect RAG chunks with deterministic IDs, source metadata, and a billing-ready summary—ready for embeddings or vector DBs without extra glue code.