> ## Documentation Index > Fetch the complete documentation index at: https://www.bolna.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Choose and Configure LLM Models for Voice AI > Select and configure the language model for your Bolna Voice AI agent. Choose from OpenAI, Azure, Anthropic, connect knowledge bases, and set up guardrails. ## What is the LLM Tab? The LLM Tab is where you select and configure the intelligence behind your voice AI agent. Choose your language model provider, adjust response parameters, and connect knowledge bases for enhanced conversations. LLM Tab showing model selection, parameters, and knowledge base options *** ## Configuration Options ### Choose LLM Model Select your AI provider and model for conversation intelligence. Choose LLM model with Azure provider and gpt-4.1-mini cluster selected Choose from Azure, OpenAI, Anthropic, Groq, and more Pick the specific model (e.g., `gpt-4.1-mini cluster`) Connect your own provider keys in [Providers](/getting-started/providers) to reduce costs and access more models. *** ### Model Parameters Fine-tune how your agent generates responses. Model Parameters section showing Tokens and Temperature sliders with Knowledge Base dropdown | Parameter | Description | Recommended | | -------------------- | ------------------------------ | ------------------------------ | | **Tokens Generated** | Max tokens per LLM output | 300-500 for concise responses | | **Temperature** | Controls creativity/randomness | 0.3-0.5 for balanced responses | **Keep temperature low** (0.3-0.5) if you want consistent, controlled responses. Higher temperature increases creativity but may cause deviation from your prompt instructions. *** ### Add Knowledge Base Connect your knowledge bases to give your agent accurate, contextual information. Knowledge base dropdown showing connected URLs and PDFs with Add new knowledgebase option Open the **"Select knowledge bases"** multi-select dropdown. Check one or more knowledge bases (PDFs, URLs) to connect. Click **"Add new knowledgebase"** to create and upload new content. Knowledge bases enable your agent to answer questions with accurate, up-to-date information from your documents and URLs. Connect multiple knowledge bases for comprehensive coverage. Create knowledge bases in the [Knowledge Base](/getting-started/knowledge-base) section by uploading PDFs or adding URLs. *** ### Add FAQs & Guardrails Create structured responses and safety controls for your agent. Add FAQs and Guardrails section with button to add new blocks Pre-defined answers to common questions that bypass LLM generation for faster, consistent responses Safety rules that control inappropriate content and maintain professional boundaries Click **"Add a new block for FAQs & Guardrails"** to open the configuration modal: Modal for adding FAQs and Guardrails with Name, Response, Threshold, and Utterances fields Give a descriptive name (e.g., "Pricing Questions", "Off-Topic Deflection"). Define the forced response when this rule triggers. Set matching sensitivity (0.9 = strict, lower = more matches but may trigger unintentionally). Add up to 20 example phrases that should trigger this response. **Lower thresholds** increase matching likelihood but may cause false triggers. Start with 0.8-0.9 and adjust based on testing. **[Learn more about Guardrails →](/guardrails)** to understand how to maintain professionalism, ensure compliance, and protect your brand during AI conversations. *** ## Next Steps Create and manage knowledge bases Learn guardrails best practices Configure prompts and welcome message Connect your own LLM provider Built with [Mintlify](https://mintlify.com).