How to use it with pdf files ?

[Dpaste20]

same as title

[Cuiyus]

A typical PDF RAG pipeline with zvec: PDF -> OCR → Parser -> Chunking → Embedding → zvec.

• feat: support ai extension #88 will expose ai-extension APIs to call local/remote embedding services.
• For full PDF support, we're planning to integrate open-source RAG tools or provide best-practice examples.

If you've built PDF processing pipelines or have favorite tools (e.g., PaddleOCR, MinerU, LlamaIndex), we'd love your help to:

• Propose integration designs
• Contribute adapters/connectors
• Share real-world usage patterns

Let's build this together — feel free to open a PR or continue the discussion here! 😊