> ## Documentation Index > Fetch the complete documentation index at: https://docs.hellotars.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Agent from PDF Knowledge > Build AI Agents that answer questions using PDF document knowledge bases Create powerful AI Agents that can answer questions and provide information based on PDF documents. This process automatically processes and trains your PDF content to build a smart assistant. ### What you can do with this * **Build customer support agents** that answer questions using your help documentation * **Create internal knowledge assistants** to help employees find information quickly * **Develop product information bots** that provide detailed specs and features * **Design training assistants** for interactive learning experiences * **Ensure compliance** with accurate information delivery for regulatory requirements ### What you get **Knowledge-powered intelligence** * **Instant expertise**: Your Agent immediately knows your content and can answer related questions * **Contextual responses**: Provides accurate answers based on your specific information * **Content updates**: Automatically stays current as you update your Knowledge Base * **Source citations**: Can reference specific documents or sections when answering * **Domain expertise**: Specialized knowledge in your specific field or industry ### Step-by-step creation process Navigate to the Create Agent page and click on the **Create from Knowledge** card to begin the process. Create Agent page showing the Create from Knowledge card option This opens a modal dialog where you can configure your knowledge-powered Agent. In the modal, select **PDF** as the data source for training your Agent's Knowledge Base and customize the Agent's appearance: Data source selection and agent customization options **Customization options:** * **Data Source**: Choose **PDF** to train from document files * **Agent Icon**: Select or change the icon representing your Agent You can choose from various data sources and customize your Agent's icon. Additional data source options will be introduced in future updates. Once you have clicked on the `Documents (PDF)` card, your Knowledge Base configuration modal will open. Create Knowledge Base page showing Documents PDF card selection Set up the fundamental information for your Knowledge Base and upload your PDF documents. Knowledge base configuration showing name field and file upload area **Required configuration:** - **Knowledge Base Name**: Enter a descriptive name for your Knowledge Base - **File Upload**: Drag and drop PDF files or browse to select documents The system will process your PDF documents to extract text content, tables, and structured information for Knowledge Base creation. Click the `Upload` button to upload your selected PDF files to the cloud for processing. Upload button to process PDF files to cloud storage Files are securely uploaded to cloud storage(aws-s3) Your PDF files are successfully uploaded and ready for content extraction and processing. After successful upload, choose to add more files or proceed with content fetching. Options to add more files or fetch content from uploaded PDFs **Available options:** - **Add more files**: Click to upload additional PDF documents to the same Knowledge Base - **Fetch content**: Begin content extraction from uploaded PDF files - **File management**: View and manage uploaded documents **Multiple Documents**: You can add multiple PDF files to create a comprehensive Knowledge Base from various document sources. Click the `Fetch Content` button to begin extracting text and structured data from your PDF documents. Active content fetching process showing PDF text extraction progress The system extracts and processes text, tables, and document structures from your uploaded PDF files stored in cloud storage, preparing the content for the subsequent training phase. **Processing Time**: Content extraction may take several minutes depending on document size and complexity. Monitor the progress for detailed status updates. After content extraction completes,initiate training after removing the unwanted documents. Post-fetch state showing extracted content ready for training **Content training:** - **Train button**: Click to begin Knowledge Base training process All content has been successfully extracted from your PDF documents and is ready for the training phase. Watch the real-time training progress as your PDF content is processed and indexed. Active training process showing real-time PDF content training progress **Training process:** - **Index optimization**: Creates efficient search and retrieval system - **Quality validation**: Ensures Knowledge Base accuracy and completeness Training converts your PDF content into searchable knowledge embeddings that power AI responses. After the training process is completed, click the `Create Agent` button to start building your AI Agent with the pre-configured PDF Knowledge Base. Post-training state with Create Agent button enabled Agent creation loading process with Knowledge Base integration **Agent creation process:** - **Agent initialization**: Begins creating the AI Agent with the Knowledge Base connection - **Gambit configuration**: Automatically connects the Knowledge Base gambit - **System integration**: Sets up the Agent to use PDF content for responses - **Deployment preparation**: Prepares the Agent for immediate use The Agent is being created with your PDF Knowledge Base pre-configured for immediate interaction. Your AI Agent is now ready, and you can interact with it using the chat interface. Completed Agent creation showing chat interface ready for interaction **Agent capabilities:** - **PDF knowledge integration**: Agent can answer questions based on your PDF content - **Interactive chat**: Use the chat interface to test Agent responses - **Knowledge base connection**: Agent automatically references your PDF documents - **Ready for deployment**: Agent can be deployed to various channels **Immediate Use**: Your Agent is immediately functional and can answer questions based on the content extracted from your PDF documents. **Content Quality**: The effectiveness of your Agent depends on the quality and organization of your source content. Ensure your PDF documents are well-structured and comprehensive. **Content Updates**: If your source PDF documents change significantly, you may need to retrain your Knowledge Base to ensure the Agent has access to the latest information.