Show HN: Multimodal PDF extraction using Sonnet 3.5/GPT-4o

1 point

2 years ago

Using the new graphlit-ingest CLI, you can ingest any document, audio/video, image or web page, and extract Markdown text or structured JSON. Also, supports summarization and auto-generated transcript chapters, bullet points, social media posts and more.

Supports Anthropic Sonnet 3.5 and OpenAI GPT-4o for multimodal PDF extraction.

Free to use, up to 1GB data.

Built with our new cross-platform .NET SDK.

Signup: https://portal.graphlit.dev Code: https://github.com/graphlit/graphlit-samples/tree/main/dotne...