# FAQs ### Can I search the contents of a PDF file with Dexter? Yes! If you enable the `includeFullText` config setting Dexter will read the contents of .pdf, .doc, .csv, .txt, and .md files, cleanup the text, and add it to the `__fullText` property of an entry being indexed, thus making it searchable. You can also limit indexing the first N pages or words of a document. Check out the [configuration](/dexter/docs/configuration.md) settings for details on how to do this. ### Can Dexter generate descriptions of images for me? Yes! If you add OpenAI credentials and add the FileDescribePipeline to your settings, it will read the image (as long as it is publicly available) and generate a description and optionally categories. ### Do I have to use OpenAI with Dexter? No, you don't. OpenAI is only used with the enhanced search option, and for generating image descriptions and text document summaries. You can still use Dexter to fully index content into Meilisearch or Algolia, and use it as a full-text, keyword, and faceted search engine. --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.boldminded.com/faqs.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.