pdf-extraction

Pure javascript cross-platform module to extract text from PDFs.

v1.0.2 URL: https://unpkg.com/pdf-extraction@1.0.2/index.js

Open Browse Files

pdf-parse pdf-crawler xpdf pdf.js pdfreader pdf-extractor pdf2json j-pdfjson pdf-extraction pdf-parse pdf-parser pdf-extract pdf-extractor pdf-to-text pdf-text-extract pdfjs server side PDF parsing pdf metadata

@aidalinfo/pdf-processor

Powerful PDF data extraction library powered by AI vision models. Transform PDFs into structured, validated data using TypeScript, Zod, and AI providers like Scaleway and Ollama.

v1.0.18 URL: https://unpkg.com/@aidalinfo/pdf-processor@1.0.18/dist/index.js

Open Browse Files

pdf pdf-extraction vision-llm ai-sdk document-processing invoice-extraction data-extraction ocr-alternative zod sharp scaleway ollama structured-extraction typescript bun

n8n-nodes-unstract

n8n nodes for Unstract services including LLMWhisperer and Unstract API

v0.4.2 URL: https://unpkg.com/n8n-nodes-unstract@0.4.2/index.js

Open Browse Files

n8n-community-node-package unstract llmwhisperer n8n n8n-node document-processing text-extraction ocr optical-character-recognition pdf-extraction image-to-text document-ocr text-recognition pdf-to-text scan-to-text

poppler-ts

Native Node.js binding for Poppler PDF library

v0.3.0 URL: https://unpkg.com/poppler-ts@0.3.0/dist/index.js

Open Browse Files

poppler pdf native binding typescript pdf-parser pdf-extraction pdf-rendering

vecpdf

CLI tool to process PDFs and create local vector databases using ChromaDB

v0.0.1 URL: https://unpkg.com/vecpdf@0.0.1/index.js

Open Browse Files

cli pdf vector chroma chromadb embeddings pdf-extraction text-extraction semantic-search local-vector-db offline rag nlp document-search pymupdf tiktoken