Understanding how your content is indexed is crucial for optimizing your documents. Indexing refers to organizing and categorizing information by search engines and AI systems to access and retrieve it quickly. When content is indexed, it is analyzed and stored in a way that allows for rapid information retrieval, meaning that when you search for specific terms or phrases, the indexing system can quickly find relevant documents. In the context of our AI assistant, effective indexing ensures that it can efficiently engage with the information your users need, allowing for more accurate and timely responses. Properly indexed content enhances findability and improves overall user experience, as you can locate necessary information without unnecessary delays or complexity.
Indexed Content
PDF Documents
The AI assistant indexes PDFs, making the text searchable and accessible.
Word Documents (.doc, .docx)
Word files are fully supported, allowing the assistant to index and analyze text.
Plain Text Files (.txt)
All content in plain text files is searchable.
CSV Files
The assistant indexes CSV files, making their text data easy to search and retrieve.
Non-Indexed Content
iFrame Embeds
The AI assistant cannot access or search content embedded via iFrames.
Google Docs
Direct indexing of Google Docs isn’t supported. Export them as PDF or Word to make them searchable.
Videos
Videos aren’t indexed, but transcriptions in a supported text format can be.
Images
Images aren’t indexed. You should extract any text within images into a text format document for indexing.