Skip to main content
The Semantic search API helps you build AI systems that use data from documents. With the API, you can search for texts with similar semantic meaning, unlike the search where you search for keywords, and find relevant texts written in other languages. The Semantic search API calculates Vector Embeddings for all PDF documents uploaded to Cognite Data Fusion (CDF). You can read more about embeddings and AIs multitool vector embeddings. Vector embeddings are created as part of the built-in Retrieval Augmented Generation (RAG) pipeline. All PDF documents you upload to CDF are parsed and OCRed, and the extracted text is divided into suitably sized passages that are indexed into a vector store. This article explains how to upload a PDF and use the Semantic search API to find relevant passages for a user question.
1

Upload PDF

You can upload a PDF file to CDF one of the following ways:
  • Go to CDF > Industrial tools > Canvas and drag your PDF file to the canvas or upload existing files by selecting + Add data.
  • Go to CDF > Industrial tools > Data explorer > Files and select Upload.
  • Use the Python code.
2

Processing

Once you’ve uploaded the file, wait for it to pass through the RAG pipeline. You can use the Document status API to poll the status.
3

Search

Once the document is fully indexed, search for the relevant passages with the Python code.
See the response for the test file.
The response is a list of matching passages from the given documents. In addition to the relevant text, they contain the page numbers and bounding boxes where you can find the text. The response returns the passages in the order of relevance, where the top passage is the most relevant.
Last modified on July 7, 2026