Skip to main content

List Slack Channels

Use OpenAI, NextJS, and the Auth0-AI SDKs to list your Slack channels.

note

We value your feedback! To ask questions, report issues, or request new frameworks and providers, connect with us on GitHub.

language

Prerequisites

Before using this example, make sure you:

Pick Your Tech Stack

1. Configure Auth0 AI​

First, you must install the SDK:

npm install @auth0/ai-vercel
ctrl+C

Then, you need to initialize Auth0 AI and set up the connection to request access tokens with the required Slack scopes.

./src/lib/auth0-ai.ts
ctrl+C
import { Auth0AI } from "@auth0/ai-vercel";
import { auth0 } from "@/lib/auth0";

const auth0AI = new Auth0AI();

export const withSlack = auth0AI.withTokenForConnection({
  connection: "sign-in-with-slack",
  scopes: ["channels:read", "groups:read"],
  refreshToken: async () => {
    const session = await auth0.getSession();
    const refreshToken = session?.tokenSet.refreshToken as string;

    return refreshToken;
  },
});
info

Here, the property auth0 is an instance of @auth0/nextjs-auth0 to handle the application auth flows.
You can check different authentication options for Next.js with Auth0 at the official documentation.

2. Integrate your tool with Slack​

Wrap your tool using the Auth0 AI SDK to obtain an access token for the Slack API.

./src/lib/tools/listChannels.ts
ctrl+C
import { ErrorCode, WebClient } from "@slack/web-api";
import { getAccessTokenForConnection } from "@auth0/ai-vercel";
import { FederatedConnectionError } from "@auth0/ai/interrupts";
import { withSlack } from "@/lib/auth0-ai";
import { tool } from "ai";
import { z } from "zod";

export const listChannels = withSlack(
  tool({
    description: "List channels for the current user on Slack",
    parameters: z.object({}),
    execute: async () => {
      // Get the access token from Auth0 AI
      const credentials = getAccessTokenForConnection();

      // Slack SDK
      try {
        const web = new WebClient(credentials?.accessToken);

        const result = await web.conversations.list({
          exclude_archived: true,
          types: "public_channel,private_channel",
          limit: 10,
        });

        return result.channels?.map((channel) => channel.name);
      } catch (error) {
        if (error && typeof error === "object" && "code" in error) {
          if (error.code === ErrorCode.HTTPError) {
            throw new FederatedConnectionError(
              `Authorization required to access the Federated Connection`
            );
          }
        }

        throw error;
      }
    },
  })
);

3. Handle authentication redirects​

Interrupts are a way for the system to pause execution and prompt the user to take an action—such as authenticating or granting API access—before resuming the interaction. This ensures that any required access is granted dynamically and securely during the chat experience. In this context, Auth0-AI SDK manages authentication redirects in the Vercel AI SDK via these interrupts.

Server Side​

On the server-side code of your Next.js App, you need to set up the tool invocation and handle the interruption messaging via the errorSerializer. The setAIContext function is used to set the async-context for the Auth0 AI SDK.

./src/app/api/chat/route.ts
ctrl+C
import { createDataStreamResponse, generateId, Message, streamText } from "ai";
import { openai } from "@ai-sdk/openai";
import { setAIContext } from "@auth0/ai-vercel";
import { errorSerializer, invokeTools } from "@auth0/ai-vercel/interrupts";
import { listChannels } from "@/lib/tools/listChannels";

export const maxDuration = 30;

export async function POST(request: Request) {
  const { id, messages} = await request.json();

  setAIContext({ threadID: id });

  return createDataStreamResponse({
    execute: async (dataStream) => {
      await invokeTools({
        messages,
        tools: { listChannels },
      });

      const result = streamText({
        model: openai("gpt-4o-mini"),
        system: "You are a friendly assistant! Keep your responses concise and helpful.",
        messages,
        maxSteps: 5,
        tools: { listChannels },
        experimental_activeTools: ["listChannels"],
        experimental_generateMessageId: generateId,
      });

      result.mergeIntoDataStream(dataStream, {
        sendReasoning: true,
      });
    },
    onError: errorSerializer((err) => {
      return "Oops, an error occured!";
    }),
  });
}

Client Side​

On this example we utilize the EnsureAPIAccessPopup component to show a popup that allows the user to authenticate with Slack and grant access with the requested scopes. You'll first need to install the @auth0/ai-components package:

npx @auth0/ai-components add FederatedConnections
ctrl+C

Then, you can integrate the authentication popup in your chat component, using the interruptions helper from the SDK:

./src/components/chat.tsx
ctrl+C
"use client";

import { generateId } from "ai";
import { useChat } from "@ai-sdk/react";
import { useInterruptions } from "@auth0/ai-vercel/react";
import { FederatedConnectionInterrupt } from "@auth0/ai/interrupts";
import { EnsureAPIAccessPopup } from "@/components/auth0-ai/FederatedConnections/popup";

export default function Chat() {
  const { messages, handleSubmit, input, setInput, toolInterrupt } =
    useInterruptions((handler) =>
      useChat({
        experimental_throttle: 100,
        sendExtraMessageFields: true,
        generateId,
        onError: handler((error) => console.error("Chat error:", error)),
      })
    );

  return (
    <div>
      {messages.map((message) => (
        <div key={message.id}>
          {message.role === "user" ? "User: " : "AI: "}
          {message.content}
          {message.parts && message.parts.length > 0 && (
            <div>
              {message.parts
                .filter((p) => p.type === "tool-invocation")
                .map((part) => {
                  const { toolInvocation: { toolCallId, state } } = part;

                  if (state === "call" && FederatedConnectionInterrupt.isInterrupt(toolInterrupt)) {
                    return (
                      <EnsureAPIAccessPopup
                        key={toolCallId}
                        onFinish={toolInterrupt.resume}
                        connection={toolInterrupt.connection}
                        scopes={toolInterrupt.requiredScopes}
                        connectWidget={{
                          title: "List Slack channels",
                          description:"description ...",
                          action: { label: "Check" },
                        }}
                      />
                    );
                  }
                })}
            </div>
          )}
        </div>
      ))}

      <form onSubmit={handleSubmit}>
        <input value={input} placeholder="Say something..." onChange={(e) => setInput(e.target.value)} />
      </form>
    </div>
  );
}

1. Configure Auth0 AI​

First, you must install the SDK:

npm install @auth0/ai-langchain
ctrl+C

Then, you need to initialize Auth0 AI and set up the connection to request access tokens with the required Slack scopes.

./src/lib/auth0-ai.ts
ctrl+C
import { Auth0AI } from "@auth0/ai-langchain";

const auth0AI = new Auth0AI();

export const withSlack = auth0AI.withTokenForConnection({
  connection: "sign-in-with-slack",
  scopes: ["channels:read", "groups:read"],
  // Optional: By default, the SDK will expect the refresh token from
  // the LangChain RunnableConfig (`config.configurable._credentials.refreshToken`)
  // If you want to use a different store for refresh token you can set up a getter here
  // refreshToken: async () => await getRefreshToken(),
});

2. Integrate your tool with Slack​

Wrap your tool using the Auth0 AI SDK to obtain an access token for the Slack API.

./src/lib/tools/listChannels.ts
ctrl+C
import { ErrorCode, WebClient } from "@slack/web-api";
import { getAccessTokenForConnection } from "@auth0/ai-langchain";
import { FederatedConnectionError } from "@auth0/ai/interrupts";
import { withSlack } from "@/lib/auth0-ai";
import { tool } from "@langchain/core/tools";
import { z } from "zod";

export const listChannels = withSlack(
  tool(async ({ date }) => {
    // Get the access token from Auth0 AI
    const credentials = getAccessTokenForConnection();

    // Slack SDK
    try {
      const web = new WebClient(credentials?.accessToken);

      const result = await web.conversations.list({
        exclude_archived: true,
        types: "public_channel,private_channel",
        limit: 10,
      });

      return result.channels?.map((channel) => channel.name);
    } catch (error) {
      if (error && typeof error === "object" && "code" in error) {
        if (error.code === ErrorCode.HTTPError) {
          throw new FederatedConnectionError(
            `Authorization required to access the Federated Connection`
          );
        }
      }

      throw error;
    }
  },
  {
    name: "list_slack_channels",
    description: "List channels for the current user on Slack",
    schema: z.object({
      date: z.coerce.date(),
    }),
  })
);

Now that the tool is protected, you can pass it your LangGraph agent as part of a ToolNode. The agent will automatically request the access token when the tool is called.

./src/lib/agent.ts
ctrl+C
import { AIMessage } from "@langchain/core/messages";
import { RunnableLike } from "@langchain/core/runnables";
import { END, InMemoryStore, MemorySaver, MessagesAnnotation, START, StateGraph } from "@langchain/langgraph";
import { ToolNode } from "@langchain/langgraph/prebuilt";
import { ChatOpenAI } from "@langchain/openai";

import { listChannels } from "@/lib/tools/listChannels";

const model = new ChatOpenAI({ model: "gpt-4o", }).bindTools([
  listChannels,
]);

const callLLM = async (state: typeof MessagesAnnotation.State) => {
  const response = await model.invoke(state.messages);
  return { messages: [response] };
};

const routeAfterLLM: RunnableLike = function (state) {
  const lastMessage = state.messages[state.messages.length - 1] as AIMessage;
  if (!lastMessage.tool_calls?.length) {
    return END;
  }
  return "tools";
};

const stateGraph = new StateGraph(MessagesAnnotation)
  .addNode("callLLM", callLLM)
  .addNode(
    "tools",
    new ToolNode(
      [
        // A tool with federated connection access
        listChannels,
        // ... other tools
      ],
      {
        // Error handler should be disabled in order to
        // trigger interruptions from within tools.
        handleToolErrors: false,
      }
    )
  )
  .addEdge(START, "callLLM")
  .addConditionalEdges("callLLM", routeAfterLLM, [END, "tools"])
  .addEdge("tools", "callLLM");

const checkpointer = new MemorySaver();
const store = new InMemoryStore();

export const graph = stateGraph.compile({
  checkpointer,
  store,
});

3. Handle authentication redirects​

Interrupts are a way for the system to pause execution and prompt the user to take an action —such as authenticating or granting API access— before resuming the interaction. This ensures that any required access is granted dynamically and securely during the chat experience. In this context, Auth0-AI SDK manages such authentication redirects integrated with the Langchain SDK.

Server Side​

On the server side of your Next.js application you need to set up a route to handle the Chat API requests. This route will be responsible for forwarding the requests to the LangGraph API. Additionally, you must provide the refreshToken to the Langchain's RunnableConfig from the authenticated user's session.

./src/app/api/langgraph/[..._path]/route.ts
ctrl+C
import { initApiPassthrough } from "langgraph-nextjs-api-passthrough";
import { auth0 } from "@/lib/auth0";

const getRefreshToken = async () => {
  const session = await auth0.getSession();
  const refreshToken = session?.tokenSet.refreshToken as string;
  return refreshToken;
};

export const { GET, POST, PUT, PATCH, DELETE, OPTIONS, runtime } =
  initApiPassthrough({
    apiUrl: process.env.LANGGRAPH_API_URL,
    apiKey: process.env.LANGSMITH_API_KEY,
    runtime: "edge",
    baseRoute: "langgraph/",
    bodyParameters: async (req, body) => {
      if (
        req.nextUrl.pathname.endsWith("/runs/stream") &&
        req.method === "POST"
      ) {
        return {
          ...body,
          config: {
            configurable: {
              _credentials: {
                refreshToken: await getRefreshToken(),
              },
            },
          },
        };
      }

      return body;
    },
  });
info

Here, the property auth0 is an instance of @auth0/nextjs-auth0 to handle the application auth flows.
You can check different authentication options for Next.js with Auth0 at the official documentation.

Client Side​

On this example we utilize the EnsureAPIAccessPopup component to show a popup that allows the user to authenticate with Slack and grant access with the requested scopes. You'll first need to install the @auth0/ai-components package:

npx @auth0/ai-components add FederatedConnections
ctrl+C

Then, you can integrate the authentication popup in your chat component, using the interruptions helper from the SDK:

./src/components/chat.tsx
ctrl+C
import { useStream } from "@langchain/langgraph-sdk/react";
import { FederatedConnectionInterrupt } from "@auth0/ai/interrupts";
import { EnsureAPIAccessPopup } from "@/components/auth0-ai/FederatedConnections/popup";

const useFocus = () => {
  const htmlElRef = useRef<HTMLInputElement>(null);
  const setFocus = () => {
    if (!htmlElRef.current) {
      return;
    }
    htmlElRef.current.focus();
  };
  return [htmlElRef, setFocus] as const;
};

export default function Chat() {
  const [threadId, setThreadId] = useQueryState("threadId");
  const [input, setInput] = useState("");
  const thread = useStream({
    apiUrl: `${process.env.NEXT_PUBLIC_URL}/api/langgraph`,
    assistantId: "agent",
    threadId,
    onThreadId: setThreadId,
    onError: (err) => {
      console.dir(err);
    },
  });

  const [inputRef, setInputFocus] = useFocus();
  useEffect(() => {
    if (thread.isLoading) {
      return;
    }
    setInputFocus();
  }, [thread.isLoading, setInputFocus]);

  const handleSubmit: FormEventHandler<HTMLFormElement> = async (e) => {
    e.preventDefault();
    thread.submit(
      { messages: [{ type: "human", content: input }] },
      {
        optimisticValues: (prev) => ({
          messages: [
            ...((prev?.messages as []) ?? []),
            { type: "human", content: input, id: "temp" },
          ],
        }),
      }
    );
    setInput("");
  };

  return (
    <div>
      {thread.messages.filter((m) => m.content && ["human", "ai"].includes(m.type)).map((message) => (
        <div key={message.id}>
          {message.type === "human" ? "User: " : "AI: "}
          {message.content as string}
        </div>
      ))}

      {thread.interrupt && FederatedConnectionInterrupt.isInterrupt(thread.interrupt.value) ? (
        <div key={thread.interrupt.ns?.join("")}>
          <EnsureAPIAccessPopup
            key={thread.interrupt.ns?.join("")}
            onFinish={() => thread.submit(null)}
            connection={thread.interrupt.value.connection}
            scopes={thread.interrupt.value.requiredScopes}
            connectWidget={{
                title: "List Slack channels",
                description:"description ...",
                action: { label: "Check" },
              }}
          />
        </div>
      ) : null}

      <form onSubmit={handleSubmit}>
        <input ref={inputRef} value={input} placeholder="Say something..." readOnly={thread.isLoading} disabled={thread.isLoading} onChange={(e) => setInput(e.target.value)} />
      </form>
    </div>
  );
}

1. Configure Auth0 AI​

First, you must install the SDK:

npm install @auth0/ai-genkit
ctrl+C

Then, you need to initialize Auth0 AI and set up the connection to request access tokens with the required Slack scopes.

./src/lib/auth0-ai.ts
ctrl+C
import { Auth0AI } from "@auth0/ai-genkit";
import { auth0 } from "@/lib/auth0";

// importing GenKit instance
import { ai } from "./genkit";

const auth0AI = new Auth0AI({
  genkit: ai,
});

export const withSlack = auth0AI.withTokenForConnection({
  connection: "sign-in-with-slack",
  scopes: ["channels:read", "groups:read"],
  refreshToken: async () => {
    const session = await auth0.getSession();
    const refreshToken = session?.tokenSet.refreshToken as string;
    return refreshToken;
  },
});
info

Here, the property auth0 is an instance of @auth0/nextjs-auth0 to handle the application auth flows.
You can check different authentication options for Next.js with Auth0 at the official documentation.

2. Integrate your tool with Slack​

Wrap your tool using the Auth0 AI SDK to obtain an access token for the Slack API.

./src/lib/tools/listChannels.ts
ctrl+C
import { z } from "zod";
import { getAccessTokenForConnection } from "@auth0/ai-genkit";
import { FederatedConnectionError } from "@auth0/ai/interrupts";
import { withSlack } from "@/lib/auth0-ai";
import { ErrorCode, WebClient } from "@slack/web-api";

// importing GenKit instance
import { ai } from "../genkit";

export const listChannels = ai.defineTool(
  ...withSlack(
    {
      description: "List channels for the current user on Slack",
      inputSchema: z.object({}),
      name: "listChannels",
    },
    async () => {
      const credentials = getAccessTokenForConnection();

      try {
        // Slack SDK
        const web = new WebClient(credentials?.accessToken);

        const result = await web.conversations.list({
          exclude_archived: true,
          types: "public_channel,private_channel",
          limit: 10,
        });

        return result.channels?.map((channel) => channel.name);
      } catch (error) {
        if (error && typeof error === "object" && "code" in error) {
          if (error.code === ErrorCode.HTTPError) {
            throw new FederatedConnectionError(
              `Authorization required to access the Federated Connection`
            );
          }
        }

        throw error;
      }
    }
  )
);

3. Handle authentication redirects​

Interrupts are a way for the system to pause execution and prompt the user to take an action—such as authenticating or granting API access—before resuming the interaction. This ensures that any required access is granted dynamically and securely during the chat experience. In this context, Auth0-AI SDK manages authentication redirects in the GenKit SDK via these interrupts.

Server Side​

On the server-side code of your Next.js App, you need to set up the tool invocation and handle the interruption messaging via the errorSerializer. The setAIContext function is used to set the async-context for the Auth0 AI SDK.

./src/app/api/chat/route.ts
ctrl+C
import { ToolRequestPart } from "genkit";
import path from "path";
import { ai } from "@/lib/genkit";
import { listChannels } from "@/lib/tools/list-channels";
import { resumeAuth0Interrupts } from "@auth0/ai-genkit";
import { auth0 } from "@/lib/auth0";

export async function POST(
  request: Request,
  { params }: { params: Promise<{ id: string }> }
) {
  const auth0Session = await auth0.getSession();
  const { id } = await params;
  const {
    message,
    interruptedToolRequest,
    timezone,
  }: {
    message?: string;
    interruptedToolRequest?: ToolRequestPart;
    timezone: { region: string; offset: number };
  } = await request.json();

  let session = await ai.loadSession(id);

  if (!session) {
    session = ai.createSession({
      sessionId: id,
    });
  }

  const tools = [listChannels];

  const chat = session.chat({
    tools: tools,
    system: `You are a helpful assistant.
    The user's timezone is ${timezone.region} with an offset of ${timezone.offset} minutes.
    User's details: ${JSON.stringify(auth0Session?.user, null, 2)}.
    You can use the tools provided to help the user.
    You can also ask the user for more information if needed.
    Chat started at ${new Date().toISOString()}
    `,
  });

  const r = await chat.send({
    prompt: message,
    resume: resumeAuth0Interrupts(tools, interruptedToolRequest),
  });

  return Response.json({ messages: r.messages, interrupts: r.interrupts });
}

export async function GET(
  request: Request,
  { params }: { params: Promise<{ id: string }> }
) {
  const { id } = await params;

  const session = await ai.loadSession(id);

  if (!session) {
    return new Response("Session not found", {
      status: 404,
    });
  }

  const json = session.toJSON();

  if (!json?.threads?.main) {
    return new Response("Session not found", {
      status: 404,
    });
  }

  return Response.json(json.threads.main);
}

Client Side​

On this example we utilize the EnsureAPIAccessPopup component to show a popup that allows the user to authenticate with Google Calendar and grant access with the requested scopes. You'll first need to install the @auth0/ai-components package:

npx @auth0/ai-components add FederatedConnections
ctrl+C

Then, you can integrate the authentication popup in your chat component, using the interruptions helper from the SDK:

./src/components/chat.tsx
ctrl+C
"use client";
import { useQueryState } from "nuqs";
import { FormEventHandler, useEffect, useRef, useState } from "react";
import { FederatedConnectionInterrupt } from "@auth0/ai/interrupts";
import { EnsureAPIAccessPopup } from "@/components/auth0-ai/FederatedConnections/popup";
import Markdown from "react-markdown";

const useFocus = () => {
  const htmlElRef = useRef<HTMLInputElement>(null);
  const setFocus = () => {
    if (!htmlElRef.current) {
      return;
    }
    htmlElRef.current.focus();
  };
  return [htmlElRef, setFocus] as const;
};

export default function Chat() {
  const [threadId, setThreadId] = useQueryState("threadId");
  const [input, setInput] = useState("");
  const [isLoading, setIsLoading] = useState(false);
  const [messages, setMessages] = useState<
    {
      role: "user" | "model";
      content: [{ text?: string; metadata?: { interrupt?: any } }];
    }[]
  >([]);

  useEffect(() => {
    if (!threadId) {
      setThreadId(self.crypto.randomUUID());
    }
  }, [threadId, setThreadId]);

  useEffect(() => {
    if (!threadId) {
      return;
    }

    setIsLoading(true);

    (async () => {
      const messagesResponse = await fetch(`/api/chat/${threadId}`, {
        method: "GET",
        credentials: "include",
      });
      if (!messagesResponse.ok) {
        setMessages([]);
      } else {
        setMessages(await messagesResponse.json());
      }
      setIsLoading(false);
    })();
  }, [threadId]);

  const [inputRef, setInputFocus] = useFocus();
  useEffect(() => {
    if (isLoading) {
      return;
    }
    setInputFocus();
  }, [isLoading, setInputFocus]);

  const submit = async ({
    message,
    interruptedToolRequest,
  }: {
    message?: string;
    interruptedToolRequest?: any;
  }) => {
    setIsLoading(true);
    const timezone = {
      region: Intl.DateTimeFormat().resolvedOptions().timeZone,
      offset: new Date().getTimezoneOffset(),
    };
    const response = await fetch(`/api/chat/${threadId}`, {
      method: "POST",
      credentials: "include",
      headers: {
        "Content-Type": "application/json",
      },
      body: JSON.stringify({ message, interruptedToolRequest, timezone }),
    });
    if (!response.ok) {
      console.error("Error sending message");
    } else {
      const { messages: messagesResponse } = await response.json();
      setMessages(messagesResponse);
    }
    setIsLoading(false);
  };

  // //When the user submits a message, add it to the list of messages and resume the conversation.
  const handleSubmit: FormEventHandler<HTMLFormElement> = async (e) => {
    e.preventDefault();
    setMessages((messages) => [
      ...messages,
      { role: "user", content: [{ text: input }] },
    ]);
    submit({ message: input });
    setInput("");
  };

  return (
    <div>
      {messages
        .filter(
          (m) =>
            ["model", "user", "tool"].includes(m.role) &&
            m.content?.length > 0 &&
            (m.content[0].text || m.content[0].metadata?.interrupt)
        )
        .map((message, index) => (
          <div key={index}>
            <Markdown>
              {(message.role === "user" ? "User: " : "AI: ") +
                (message.content[0].text || "")}
            </Markdown>
            {!isLoading &&
            message.content[0].metadata?.interrupt &&
            FederatedConnectionInterrupt.isInterrupt(
              message.content[0].metadata?.interrupt
            )
              ? (() => {
                  const interrupt: any = message.content[0].metadata?.interrupt;
                  return (
                    <div>
                      <EnsureAPIAccessPopup
                        onFinish={() =>
                          submit({ interruptedToolRequest: message.content[0] })
                        }
                        connection={interrupt.connection}
                        scopes={interrupt.requiredScopes}
                        connectWidget={{
                          title: `Requested by: "${interrupt.toolCall.toolName}"`,
                          description: "Description...",
                          action: { label: "Check" },
                        }}
                      />
                    </div>
                  );
                })()
              : null}
          </div>
        ))}

      <form onSubmit={handleSubmit}>
        <input value={input} ref={inputRef} placeholder="Say something..." readOnly={isLoading} disabled={isLoading} onChange={(e) => setInput(e.target.value)} />
      </form>
    </div>
  );
}

1. Configure Auth0 AI​

First, you must install the SDK:

npm install @auth0/ai-llamaindex
ctrl+C

Then, you need to initialize Auth0 AI and set up the connection to request access tokens with the required GitHub scopes.

./src/lib/auth0-ai.ts
ctrl+C
import { Auth0AI } from "@auth0/ai-llamaindex";
import { auth0 } from "@/lib/auth0";

const auth0AI = new Auth0AI();

export const withSlack = auth0AI.withTokenForConnection({
  connection: "sign-in-with-slack",
  scopes: ["channels:read", "groups:read"],
  refreshToken: async () => {
    const session = await auth0.getSession();
    const refreshToken = session?.tokenSet.refreshToken as string;
    return refreshToken;
  },
});

info

Here, the property auth0 is an instance of @auth0/nextjs-auth0 to handle the application auth flows.
You can check different authentication options for Next.js with Auth0 at the official documentation.

2. Integrate your tool with GitHub​

Wrap your tool using the Auth0 AI SDK to obtain an access token for the GitHub API.

./src/lib/tools/listRepositories.ts
ctrl+C
import { tool } from "llamaindex";
import { z } from "zod";
import { withSlack } from "@/lib/auth0-ai";
import { getAccessTokenForConnection } from "@auth0/ai-llamaindex";
import { FederatedConnectionError } from "@auth0/ai/interrupts";
import { ErrorCode, WebClient } from "@slack/web-api";

export const listChannels = () =>
  withSlack(
    tool(
      async () => {
        // Get the access token from Auth0 AI
        const credentials = getAccessTokenForConnection();

        // Slack SDK
        try {
          const web = new WebClient(credentials?.accessToken);

          const result = await web.conversations.list({
            exclude_archived: true,
            types: "public_channel,private_channel",
            limit: 10,
          });

          return (
            result.channels
              ?.map((channel) => channel.name)
              .filter((name): name is string => name !== undefined) || []
          );
        } catch (error) {
          if (error && typeof error === "object" && "code" in error) {
            if (error.code === ErrorCode.HTTPError) {
              throw new FederatedConnectionError(
                `Authorization required to access the Federated Connection`
              );
            }
          }

          throw error;
        }
      },
      {
        name: "listChannels",
        description: "List channels for the current user on Slack",
        parameters: z.object({}),
      }
    )
  );

3. Handle authentication redirects​

Interrupts are a way for the system to pause execution and prompt the user to take an action —such as authenticating or granting API access— before resuming the interaction. This ensures that any required access is granted dynamically and securely during the chat experience. In this context, Auth0-AI SDK manages authentication redirects in the LlamaIndex SDK via these interrupts.

Server Side​

On the server-side code of your Next.js App, you need to set up the tool invocation and handle the interruption messaging via the errorSerializer. The setAIContext function is used to set the async-context for the Auth0 AI SDK.

./src/app/api/chat/route.ts
ctrl+C
import { createDataStreamResponse, LlamaIndexAdapter, Message, ToolExecutionError } from "ai";
import { listRepositories } from "@/lib/tools/";
import { setAIContext } from "@auth0/ai-llamaindex";
import { withInterruptions } from "@auth0/ai-llamaindex/interrupts";
import { errorSerializer } from "@auth0/ai-vercel/interrupts";
import { OpenAIAgent } from "llamaindex";

export async function POST(request: Request) {
  const { id, messages }: { id: string; messages: Message[] } =
    await request.json();

  setAIContext({ threadID: id });

  return createDataStreamResponse({
    execute: withInterruptions(
      async (dataStream) => {
        const agent = new OpenAIAgent({
          systemPrompt: "You are an AI assistant",
          tools: [listRepositories()],
          verbose: true,
        });

        const stream = await agent.chat({
          message: messages[messages.length - 1].content,
          stream: true,
        });

        LlamaIndexAdapter.mergeIntoDataStream(stream as any, { dataStream });
      },
      {
        messages,
        errorType: ToolExecutionError,
      }
    ),
    onError: errorSerializer((err) => {
      console.log(err);
      return "Oops, an error occured!";
    }),
  });
}

Client Side​

On this example we utilize the EnsureAPIAccessPopup component to show a popup that allows the user to authenticate with GitHub and grant access with the requested scopes. You'll first need to install the @auth0/ai-components package:

npx @auth0/ai-components add FederatedConnections
ctrl+C

Then, you can integrate the authentication popup in your chat component, using the interruptions helper from the SDK:

./src/components/chat.tsx
ctrl+C
"use client";

import { generateId } from "ai";
import { EnsureAPIAccessPopup } from "@/components/auth0-ai/FederatedConnections/popup";
import { useInterruptions } from "@auth0/ai-vercel/react";
import { FederatedConnectionInterrupt } from "@auth0/ai/interrupts";
import { useChat } from "@ai-sdk/react";

export default function Chat() {
  const { messages, handleSubmit, input, setInput, toolInterrupt } =
    useInterruptions((handler) =>
      useChat({
        experimental_throttle: 100,
        sendExtraMessageFields: true,
        generateId,
        onError: handler((error) => console.error("Chat error:", error)),
      })
    );

  return (
    <div>
      {messages.map((message) => (
        <div key={message.id}>
          {message.role === "user" ? "User: " : "AI: "}
          {message.content}
          {message.parts && message.parts.length > 0 && (
            <div>
              {toolInterrupt?.toolCall.id.includes(message.id) &&
                FederatedConnectionInterrupt.isInterrupt(toolInterrupt) && (
                  <EnsureAPIAccessPopup
                    key={toolInterrupt.toolCall.id}
                    onFinish={toolInterrupt.resume}
                    connection={toolInterrupt.connection}
                    scopes={toolInterrupt.requiredScopes}
                    connectWidget={{
                      title: `Requested by: "${toolInterrupt.toolCall.name}"`,
                      description: "Description...",
                      action: { label: "Check" },
                    }}
                  />
                )}
            </div>
          )}
        </div>
      ))}

      <form onSubmit={handleSubmit}>
        <input value={input} placeholder="Say something..." onChange={(e) => setInput(e.target.value)} autoFocus />
      </form>
    </div>
  );
}

Prerequisites

Before using this example, make sure you:

Pick Your Tech Stack

Coming soon!

1. Configure Auth0 AI​

First, you must install the SDK:

pip install auth0-ai-langchain
ctrl+C

Then, you need to initialize Auth0 AI and set up the connection to request access tokens with the required Slack scopes.

./src/lib/auth0-ai.py
ctrl+C
from auth0_ai_langchain.auth0_ai import Auth0AI

auth0_ai = Auth0AI()

with_slack = auth0_ai.with_federated_connection(
    connection="sign-in-with-slack",
    scopes=["channels:read groups:read"],
    # Optional: By default, the SDK will expect the refresh token from
    # the LangChain RunnableConfig (`config.configurable._credentials.refresh_token`)
    # If you want to use a different store for refresh token you can set up a getter here
    # refresh_token=lambda *_args, **_kwargs:session["user"]["refresh_token"],
)

2. Integrate your tool with Slack​

Wrap your tool using the Auth0 AI SDK to obtain an access token for the Slack API.

./src/lib/tools/list_channels.py
ctrl+C
from slack_sdk import WebClient
from slack_sdk.errors import SlackApiError
from pydantic import BaseModel
from langchain_core.tools import StructuredTool
from auth0_ai_langchain.federated_connections import get_access_token_for_connection, FederatedConnectionError
from lib.auth0_ai import with_slack

class EmptySchema(BaseModel):
    pass

def list_channels_tool_function(date: datetime):
    # Get the access token from Auth0 AI
    access_token = get_access_token_for_connection()

    # Slack SDK
    try:
        client = WebClient(token=access_token)
        response = client.conversations_list(
            exclude_archived=True,
            types="public_channel,private_channel",
            limit=10
        )
        channels = response['channels']
        channel_names = [channel['name'] for channel in channels]
        return channel_names
    except SlackApiError as e:
        if e.response['error'] == 'not_authed':
            raise FederatedConnectionError("Authorization required to access the Federated Connection API")

        raise ValueError(f"An error occurred: {e.response['error']}")

list_slack_channels_tool = with_slack(StructuredTool(
    name="list_slack_channels",
    description="List channels for the current user on Slack",
    args_schema=EmptySchema,
    func=list_channels_tool_function,
))

Now that the tool is protected, you can pass it your LangGraph agent as part of a ToolNode. The agent will automatically request the access token when the tool is called.

./src/lib/agent.py
ctrl+C
from typing import Annotated, Sequence, TypedDict
from langchain.storage import InMemoryStore
from langchain_core.messages import AIMessage, BaseMessage
from langchain_openai import ChatOpenAI
from langgraph.checkpoint.memory import MemorySaver
from langgraph.graph import END, START, StateGraph, add_messages
from langgraph.prebuilt import ToolNode
from tools.list_channels import list_slack_channels_tool


class State(TypedDict):
    messages: Annotated[Sequence[BaseMessage], add_messages]

llm = ChatOpenAI(model="gpt-4o")
llm.bind_tools([list_slack_channels_tool])

async def call_llm(state: State):
    response = await llm.ainvoke(state["messages"])
    return {"messages": [response]}

def route_after_llm(state: State):
    messages = state["messages"]
    last_message = messages[-1] if messages else None

    if isinstance(last_message, AIMessage) and last_message.tool_calls:
        return "tools"
    return END

workflow = (
    StateGraph(State)
    .add_node("call_llm", call_llm)
    .add_node(
        "tools",
        ToolNode(
            [
                # a tool with federated connection access
                list_slack_channels_tool,
                # ... other tools
            ],
            # The error handler should be disabled to
            # allow interruptions to be triggered from within tools.
            handle_tool_errors=False
        )
    )
    .add_edge(START, "call_llm")
    .add_edge("tools", "call_llm")
    .add_conditional_edges("call_llm", route_after_llm, [END, "tools"])
)

graph = workflow.compile(checkpointer=MemorySaver(), store=InMemoryStore())

3. Handle authentication redirects​

Interrupts are a way for the system to pause execution and prompt the user to take an action —such as authenticating or granting API access— before resuming the interaction. This ensures that any required access is granted dynamically and securely during the chat experience. In this context, Auth0-AI SDK manages such authentication redirects integrated with the Langchain SDK.

Server Side​

On the server side of your Next.js application you need to set up a route to handle the Chat API requests. This route will be responsible for forwarding the requests to the LangGraph API. Additionally, you must provide the refreshToken to the Langchain's RunnableConfig from the authenticated user's session.

./src/app/api/langgraph/[..._path]/route.ts
ctrl+C
import { initApiPassthrough } from "langgraph-nextjs-api-passthrough";
import { auth0 } from "@/lib/auth0";

const getRefreshToken = async () => {
  const session = await auth0.getSession();
  const refreshToken = session?.tokenSet.refreshToken as string;
  return refreshToken;
};

export const { GET, POST, PUT, PATCH, DELETE, OPTIONS, runtime } =
  initApiPassthrough({
    apiUrl: process.env.LANGGRAPH_API_URL,
    apiKey: process.env.LANGSMITH_API_KEY,
    runtime: "edge",
    baseRoute: "langgraph/",
    bodyParameters: async (req, body) => {
      if (
        req.nextUrl.pathname.endsWith("/runs/stream") &&
        req.method === "POST"
      ) {
        return {
          ...body,
          config: {
            configurable: {
              _credentials: {
                refreshToken: await getRefreshToken(),
              },
            },
          },
        };
      }

      return body;
    },
  });
info

Here, the property auth0 is an instance of @auth0/nextjs-auth0 to handle the application auth flows.
You can check different authentication options for Next.js with Auth0 at the official documentation.

Client Side​

On this example we utilize the EnsureAPIAccessPopup component to show a popup that allows the user to authenticate with Slack and grant access with the requested scopes. You'll first need to install the @auth0/ai-components package:

npx @auth0/ai-components add FederatedConnections
ctrl+C

Then, you can integrate the authentication popup in your chat component, using the interruptions helper from the SDK:

./src/components/chat.tsx
ctrl+C
import { useStream } from "@langchain/langgraph-sdk/react";
import { FederatedConnectionInterrupt } from "@auth0/ai/interrupts";
import { EnsureAPIAccessPopup } from "@/components/auth0-ai/FederatedConnections/popup";

const useFocus = () => {
  const htmlElRef = useRef<HTMLInputElement>(null);
  const setFocus = () => {
    if (!htmlElRef.current) {
      return;
    }
    htmlElRef.current.focus();
  };
  return [htmlElRef, setFocus] as const;
};

export default function Chat() {
  const [threadId, setThreadId] = useQueryState("threadId");
  const [input, setInput] = useState("");
  const thread = useStream({
    apiUrl: `${process.env.NEXT_PUBLIC_URL}/api/langgraph`,
    assistantId: "agent",
    threadId,
    onThreadId: setThreadId,
    onError: (err) => {
      console.dir(err);
    },
  });

  const [inputRef, setInputFocus] = useFocus();
  useEffect(() => {
    if (thread.isLoading) {
      return;
    }
    setInputFocus();
  }, [thread.isLoading, setInputFocus]);

  const handleSubmit: FormEventHandler<HTMLFormElement> = async (e) => {
    e.preventDefault();
    thread.submit(
      { messages: [{ type: "human", content: input }] },
      {
        optimisticValues: (prev) => ({
          messages: [
            ...((prev?.messages as []) ?? []),
            { type: "human", content: input, id: "temp" },
          ],
        }),
      }
    );
    setInput("");
  };

  return (
    <div>
      {thread.messages.filter((m) => m.content && ["human", "ai"].includes(m.type)).map((message) => (
        <div key={message.id}>
          {message.type === "human" ? "User: " : "AI: "}
          {message.content as string}
        </div>
      ))}

      {thread.interrupt && FederatedConnectionInterrupt.isInterrupt(thread.interrupt.value) ? (
        <div key={thread.interrupt.ns?.join("")}>
          <EnsureAPIAccessPopup
            key={thread.interrupt.ns?.join("")}
            onFinish={() => thread.submit(null)}
            connection={thread.interrupt.value.connection}
            scopes={thread.interrupt.value.requiredScopes}
            connectWidget={{
                title: "List GitHub respositories",
                description:"description ...",
                action: { label: "Check" },
              }}
          />
        </div>
      ) : null}

      <form onSubmit={handleSubmit}>
        <input ref={inputRef} value={input} placeholder="Say something..." readOnly={thread.isLoading} disabled={thread.isLoading} onChange={(e) => setInput(e.target.value)} />
      </form>
    </div>
  );
}

1. Configure Auth0 AI​

First, you must install the SDK:

pip install auth0-ai-llamaindex
ctrl+C

Then, you need to initialize Auth0 AI and set up the connection to request access tokens with the required Slack scopes.

./src/lib/auth0-ai.py
ctrl+C
from auth0_ai_llamaindex.auth0_ai import Auth0AI
from flask import session

auth0_ai = Auth0AI()

with_slack = auth0_ai.with_federated_connection(
    connection="sign-in-with-slack",
    scopes=["channels:read groups:read"],
    refresh_token=lambda *_args, **_kwargs:session["user"]["refresh_token"],
)
info

Here, the session is controlled by a Flask application instance. You may utilize any other framework or session store of your preference.

2. Integrate your tool with Slack​

Wrap your tool using the Auth0 AI SDK to obtain an access token for the Slack API.

./src/lib/tools/list_channels.py
ctrl+C
from slack_sdk import WebClient
from slack_sdk.errors import SlackApiError
from llama_index.core.tools import FunctionTool
from auth0_ai_llamaindex.federated_connections import get_access_token_for_connection, FederatedConnectionError
from src.lib.auth0_ai import with_slack

def list_slack_channels_tool_function():
    # Get the access token from Auth0 AI
    access_token = get_access_token_for_connection()

    # Slack SDK
    try:
        client = WebClient(token=access_token)
        response = client.conversations_list(
            exclude_archived=True,
            types="public_channel,private_channel",
            limit=10
        )
        channels = response['channels']
        channel_names = [channel['name'] for channel in channels]
        return channel_names
    except SlackApiError as e:
        if e.response['error'] == 'not_authed':
            raise FederatedConnectionError("Authorization required to access the Federated Connection API")

        raise ValueError(f"An error occurred: {e.response['error']}")

list_slack_channels_tool = with_slack(FunctionTool.from_defaults(
    name="list_slack_channels",
    description="List channels for the current user on Slack",
    fn=list_slack_channels_tool_function,
))

Now that the tool is protected, you can pass it your LlamaIndex agent.

./src/lib/agent.ts
ctrl+C
from datetime import datetime
from llama_index.agent.openai import OpenAIAgent
from src.lib.tools.list_channels import list_slack_channels_tool

system_prompt = f"""You are an assistant designed to answer random user's questions.
**Additional Guidelines**:
- Today’s date for reference: {datetime.now().isoformat()}
"""

agent = OpenAIAgent.from_tools(
    tools=[
        # a tool with federated connection access
        list_slack_channels_tool
        # ... other tools
    ],
    model="gpt-4o",
    system_prompt=system_prompt
    verbose=True,
)

3. Handle authentication redirects​

Interrupts are a way for the system to pause execution and prompt the user to take an action —such as authenticating or granting API access— before resuming the interaction. This ensures that any required access is granted dynamically and securely during the chat experience. In this context, Auth0-AI SDK manages such authentication redirects integrated with the LLamaIndex SDK.

Server side​

On the server side of your Flask application you will need to set up a route to handle the Chat API requests. This route will be responsible for forwarding the requests to the OpenAI API utilizing LlamaIndex's SDK, that has been initialized with Auth0 AI's protection enhancements for tools.

When FederatedConnectionInterrupt error ocurrs, the server side will signal the front-end about the level access restrictions, and the front-end should prompt the user to trigger a new authorization (or login) request with the necessary permissions.

./src/app.py
ctrl+C
from dotenv import load_dotenv
from flask import Flask, request, jsonify, session
from auth0_ai_llamaindex.auth0_ai import Auth0AI
from auth0_ai_llamaindex.federated_connections import FederatedConnectionInterrupt
from src.lib.agent import agent

load_dotenv()
app = Flask(__name__)

@app.route("/chat", methods=["POST"])
async def chat():
    if "user" not in session:
        return jsonify({"error": "unauthorized"}), 401

    try:
        message = request.json.get("message")
        response = agent.achat(message)
        return jsonify({"response": str(response)})
    except FederatedConnectionInterrupt as e:
        return jsonify({"error": str(e.to_json())}), 403
    except Exception as e:
        return jsonify({"error": str(e)}), 500

comming soon

Account linking​

If you're integrating with Google, but user in your app or agent can also sign in using other methods (e.g., a username and password or another social provider), you'll need to link these identities into a single user account. Auth0 refers to this process as account linking.

Account linking logic and handling will vary depending on your app or agent. You can find an example of how to implement it in a Next.js chatbot app here. If you have questions or are looking for best practices, join our Discord and ask in the #auth0-for-gen-ai channel.