Documentation
Using Tools

Using Tools

This article lists the capabilities of the Jan platform and guides you through using RAG to chat with PDF documents, web, and desktop searches.

⚠️

To access this feature, please enable Experimental mode in the Advanced Settings.

Retrieval

To chat with PDFs using RAG in Jan, follow these steps:

  1. Create a new thread.
  2. Click the Tools dropdown menu.
  3. Ensure that Retrieval is toggled on.
  4. Adjust the Retrieval settings as needed. These settings include the following:
FeatureDescription
RetrievalUtilizes information from uploaded files, automatically retrieving content relevant to your queries for enhanced interaction.
Embedding ModelConverts text into numerical representations for machine understanding. Selection depends on your specific requirements and available resources.
Vector DatabaseFacilitates quick searches through stored numerical text representations to find relevant information efficiently.
Top KDetermines the number of top-ranked documents to retrieve, allowing control over search result relevance.
Chunk SizeSets the maximum number of tokens per data chunk, which is crucial for managing processing load and maintaining performance.
Chunk OverlapSpecifies the overlap in tokens between adjacent chunks to ensure continuous context in split text segments.
Retrieval TemplateDefines the query structure using variables like {CONTEXT} and {QUESTION} to tailor searches to specific needs.
  1. Click on the 📎 icon in the chat input field.
  2. Upload your PDF.
  3. Chat with your PDF.