While xpander.ai offers a serverless solution where you can use AI agents without managing LLM infrastructure, you might want to use your own LLM deployment for:

• Running models locally for lower latency
• Using specific model versions or custom fine-tuned models
• Implementing local function calling
• Maintaining full control over your LLM stack
• Handling sensitive data locally

This guide shows how to integrate your LLM with xpander’s tools and local functions.

​

Choose Your LLM Provider

To integrate your LLM with xpander’s tools and local functions, you’ll need to select one LLM provider and model combination. The integration is done by configuring your agent object with the chosen provider and model.

​

Provider and Model Selection

You can specify your chosen LLM provider and model using either enums from the SDK or string values:

from xpander_sdk import (
    LLMProvider,  # Enum for supported LLM providers
    OpenAISupportedModels,  # Enum for Function calling LLMs
    NvidiaNIMSupportedModels,
    OllamaSupportedModels,
    AmazonBedrockSupportedModels
)

​

Get Tools to the LLM

​

Run Tools for the LLM

​

Available Providers and Models

Here are all the supported LLM providers and their corresponding models. Choose the combination that best fits your needs:

​

Tool Response

The tool_response object represents the output from a tool invoked by an AI Agent. It contains key attributes that provide information about the tool invocation’s execution and results. This data is used to build the AI Agent’s memory and guide further interactions.

​

Tool Response Object Structure

​

Full example

​

Best Practices

1. Error Handling: Implement robust error handling for both LLM and tool calls
2. Memory Management: Properly manage conversation context
3. Security: Validate all inputs and file operations
4. Monitoring: Log LLM and tool performance metrics
5. Testing: Test with different prompts and tool combinations

Need help? Visit our Discord community or documentation.