Llm Adapters - Copilotkit

import { Callout } from "fumadocs-ui/components/callout"; import { TailoredContent, TailoredContentOption, } from "@/components/react/tailored-content.tsx"; import SelfHostingCopilotRuntimeCreateEndpoint from "@/snippets/self-hosting-copilot-runtime-create-endpoint.mdx"; import { FaCloud, FaServer } from "react-icons/fa"; import FindYourCopilotRuntime from "@/snippets/find-your-copilot-runtime.mdx";

LLM Adapters are responsible for executing the request with the LLM and standardizing the request/response format in a way that the Copilot Runtime can understand.

Currently, we support the following LLM adapters natively:

<Callout type="info"> You can use the [LangChain Adapter](/reference/v1/classes/llm-adapters/LangChainAdapter) to use any LLM provider we don't yet natively support! </Callout> <Callout type="info"> It's not too hard to write your own LLM adapter from scratch -- see the existing adapters for inspiration. And of course, we would love a contribution! ⭐️ </Callout> <TailoredContent id="hosting"> <TailoredContentOption id="copilot-cloud" title="Copilot Cloud (Recommended)" description="Use our hosted backend endpoint to get started quickly." icon={<FaCloud />} > Configure the used LLM adapter [on your Copilot Cloud dashboard](https://cloud.copilotkit.ai/)! </TailoredContentOption>

<TailoredContentOption id="self-hosted" title="Self-hosting" description="Learn to host CopilotKit's runtime yourself with your own backend." icon={<FaServer />}

<Steps> <Step> ## Find your CopilotRuntime instance <FindYourCopilotRuntime components={props.components} />

</Step>

<Step>
## Modify the used LLM Adapter

Use the example code below to tailor your CopilotRuntime instantiation to your desired llm adapter.

<SelfHostingCopilotRuntimeCreateEndpoint components={props.components} />
</Step>

<Step>
## Make further customizations
See the reference documentation linked above for further customization parameters.
</Step>

</Steps> </TailoredContentOption> </TailoredContent>