Chat with Anthropic (Claude) API on New Records Returned by CloudWatch Logs Insights Query from AWS API

Pipedream makes it easy to connect APIs for Anthropic (Claude), AWS and 2,200+ other apps remarkably fast.

Trigger workflow on

New Records Returned by CloudWatch Logs Insights Query from the AWS API

Next, do this

Chat with the Anthropic (Claude) API

No credit card required

▶

Watch us build a workflow

8 min

Watch now ➜

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

Getting Started#

This integration creates a workflow with a AWS trigger and Anthropic (Claude) action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Records Returned by CloudWatch Logs Insights Query trigger
1. Connect your AWS account
2. Select a AWS Region
3. Select one or more CloudWatch Log Groups
4. Configure Logs Insights Query
5. Optional- Configure Emit query results as a single event
6. Configure Polling schedule
Configure the Chat action
1. Connect your Anthropic (Claude) account
2. Select a Model
3. Configure User Message
4. Optional- Configure Prior Message History
5. Optional- Configure Temperature
6. Optional- Configure Top K
7. Optional- Configure Top P
8. Configure Maximum Tokens To Sample
Deploy the workflow
Send a test event to validate your setup
Turn on the trigger

Details#

This integration uses pre-built, source-available components from Pipedream's GitHub repo. These components are developed by Pipedream and the community, and verified and maintained by Pipedream.

To contribute an update to an existing component or create a new component, create a PR on GitHub. If you're new to Pipedream component development, you can start with quickstarts for trigger span and action development, and then review the component API reference.

Trigger#

New Records Returned by CloudWatch Logs Insights Query on AWS

Description:Executes a CloudWatch Logs Insights query on a schedule, and emits the records as invidual events (default) or in batch

Version:0.2.2

Key:aws-new-records-returned-by-cloudwatch-logs-insights-query

View on GitHub

AWS Overview#

The AWS API unlocks endless possibilities for automation with Pipedream. With this powerful combo, you can manage your AWS services and resources, automate deployment workflows, process data, and react to events across your AWS infrastructure. Pipedream offers a serverless platform for creating workflows triggered by various events that can execute AWS SDK functions, making it an efficient tool to integrate, automate, and orchestrate tasks across AWS services and other apps.

Trigger Code#

import common from "../../common/common-cloudwatch-logs.mjs";
import { DEFAULT_POLLING_SOURCE_TIMER_INTERVAL } from "@pipedream/platform";

export default {
  ...common,
  key: "aws-new-records-returned-by-cloudwatch-logs-insights-query",
  name: "New Records Returned by CloudWatch Logs Insights Query",
  // eslint-disable-next-line pipedream/source-description
  description: "Executes a CloudWatch Logs Insights query on a schedule, and emits the records as invidual events (default) or in batch",
  version: "0.2.2",
  type: "source",
  props: {
    aws: common.props.aws,
    region: common.props.region,
    db: "$.service.db",
    // eslint-disable-next-line pipedream/props-label
    logGroupNames: {
      ...common.props.logGroupName,
      type: "string[]",
      description: "The log groups you'd like to query",
    },
    queryString: {
      label: "Logs Insights Query",
      description: "The query you'd like to run. See [this AWS doc](https://docs.aws.amazon.com/AmazonCloudWatch/latest/logs/CWL_QuerySyntax.html) for help with query syntax",
      type: "string",
    },
    emitResultsInBatch: {
      type: "boolean",
      label: "Emit query results as a single event",
      description: "If `true`, all events are emitted as an array, within a single Pipedream event. If `false`, each row of results is emitted as its own event. Defaults to `true`",
      optional: true,
      default: true,
    },
    timer: {
      label: "Polling schedule",
      description: "How often you want to query CloudWatch Logs Insights for results",
      type: "$.interface.timer",
      default: {
        intervalSeconds: DEFAULT_POLLING_SOURCE_TIMER_INTERVAL,
      },
    },
  },
  async run() {
    const now = +new Date();
    const startTime = this.db.get("startTime") || now - 1000 * 60 * 60;

    // First, start the query
    const params = {
      queryString: this.queryString,
      startTime,
      endTime: now,
      logGroupNames: this.logGroupNames,
    };

    const { queryId } = await this.startQuery(params);

    // Then poll for its status, emitting each record as its own event when completed
    async function sleep(ms) {
      return new Promise((r) => setTimeout(r, ms));
    }

    let result, res;
    do {
      await sleep(1000);
      res = await this.getQueryResults({
        queryId,
      });
      result = res.status;
    } while (result === "Running" || result === "Scheduled");

    if (result !== "Complete") {
      throw new Error(`Query ${queryId} failed with status ${result}`);
    }

    console.log(JSON.stringify(res, null, 2));
    const { results } = res;

    if (!results || !results.length) {
      console.log("No results, exiting");
      this.db.set("startTime", now);
      return;
    }

    if (this.emitResultsInBatch === true) {
      this.$emit(results, {
        summary: JSON.stringify(results),
      });
    } else {
      for (const item of results) {
        this.$emit(item, {
          summary: JSON.stringify(item),
        });
      }
    }

    // The next time this source runs, query for data starting now
    this.db.set("startTime", now);
  },
};

Trigger Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI and CLI.

Label	Prop	Type	Description
AWS	`aws`	`app`	This component uses the AWS app.
AWS Region	`region`	`string`	Select a value from the drop down menu.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
CloudWatch Log Groups	`logGroupNames`	`string[]`	Select a value from the drop down menu.
Logs Insights Query	`queryString`	`string`	The query you'd like to run. See this AWS doc for help with query syntax
Emit query results as a single event	`emitResultsInBatch`	`boolean`	If `true`, all events are emitted as an array, within a single Pipedream event. If `false`, each row of results is emitted as its own event. Defaults to `true`
Polling schedule	`timer`	`$.interface.timer`	How often you want to query CloudWatch Logs Insights for results

Trigger Authentication#

AWS uses API keys for authentication. When you connect your AWS account, Pipedream securely stores the keys so you can easily authenticate to AWS APIs in both code and no-code steps.

Follow the AWS Instructions for creating an IAM user with an associated access and secret key.

As a best practice, attach the minimum set of IAM permissions necessary to perform the specific task in Pipedream. If your workflow only needs to perform a single API call, you should create a user and associate an IAM group / policy with permission to do only that task. You can create as many linked AWS accounts in Pipedream as you'd like.

Enter your access and secret key below.

About AWS#

Amazon Web Services (AWS) offers reliable, scalable, and inexpensive cloud computing services.

Action#

Chat on Anthropic (Claude)

Description:The Chat API. [See the documentation](https://docs.anthropic.com/claude/reference/messages_post)

Version:0.0.9

Key:anthropic-chat

View on GitHub

Anthropic (Claude) Overview#

The Anthropic (Claude) API offers a conversational AI that can be leveraged for a variety of applications, ranging from answering questions to generating content or providing customer support. In Pipedream, you can create powerful workflows that utilize the capabilities of Claude to automate responses, analyze text, or enhance data with AI-generated insights. Pipedream's serverless platform simplifies integrating Claude into your processes with other apps and services for seamless automation.

Action Code#

import anthropic from "../../anthropic.app.mjs";
import constants from "../common/constants.mjs";

export default {
  name: "Chat",
  version: "0.0.9",
  key: "anthropic-chat",
  description: "The Chat API. [See the documentation](https://docs.anthropic.com/claude/reference/messages_post)",
  type: "action",
  props: {
    anthropic,
    model: {
      label: "Model",
      description: "Select the model to use for your query. Defaults to the `claude-3-opus-20240229` model, which Anthropic describes as the \"Most powerful model for highly complex tasks\".",
      type: "string",
      options: constants.MESSAGE_MODELS,
      default: constants.MESSAGE_MODELS[0],
    },
    userMessage: {
      label: "User Message",
      type: "string",
      description: "The user messages provide instructions to the assistant",
    },
    messages: {
      label: "Prior Message History",
      type: "string[]",
      description: "All relevant information must be supplied via the conversation. You can provide an array of messages from prior conversations here always beginning with the human message.",
      optional: true,
    },
    temperature: {
      label: "Temperature",
      description: "**Optional**. Amount of randomness injected into the response. Ranges from 0 to 1. Use temp closer to 0 for analytical / multiple choice, and temp closer to 1 for creative and generative tasks.",
      type: "string",
      optional: true,
    },
    topK: {
      label: "Top K",
      description: "Only sample from the top K options for each subsequent token. Used to remove `long tail` low probability responses.",
      type: "integer",
      optional: true,
    },
    topP: {
      label: "Top P",
      description: "Does nucleus sampling, in which we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified.",
      type: "string",
      optional: true,
    },
    maxTokensToSample: {
      label: "Maximum Tokens To Sample",
      description: "A maximum number of tokens to generate before stopping.",
      type: "integer",
    },
  },
  async run({ $ }) {
    const messages = [];

    const priorMessages = typeof this.messages === "string"
      ? JSON.parse(this.messages)
      : this.messages;

    if (priorMessages?.length) {
      let isUserMessage = true;

      for (const message of priorMessages) {
        messages.push({
          role: isUserMessage
            ? "user"
            : "assistant",
          content: message,
        });

        isUserMessage = !isUserMessage;
      }
    }

    messages.push({
      role: "user",
      content: this.userMessage,
    });

    const response = await this.anthropic.createMessage({
      $,
      data: {
        messages,
        model: this.model,
        max_tokens: this.maxTokensToSample,
        temperature: this.temperature
          ? parseFloat(this.temperature)
          : undefined,
        top_p: this.topP
          ? parseFloat(this.topP)
          : undefined,
        top_k: this.topK,
      },
    });

    if (response) {
      $.export("$summary", `Successfully sent message with ID ${response.id}`);
    }

    const originalMessages = messages.map(({ content }) => content);
    return {
      original_messages: originalMessages,
      original_messages_with_assistant_response: originalMessages.concat(response.content[0].text),
      ...response,
    };
  },
};

Action Configuration#

This component may be configured based on the props defined in the component code. Pipedream automatically prompts for input values in the UI.

Label	Prop	Type	Description
Anthropic (Claude)	`anthropic`	`app`	This component uses the Anthropic (Claude) app.
Model	`model`	`string`	Select a value from the drop down menu:`claude-3-5-sonnet-20241022claude-3-5-sonnet-20240620claude-3-opus-20240229claude-3-sonnet-20240229claude-3-haiku-20240307claude-2.1claude-2.0claude-instant-1.2`
User Message	`userMessage`	`string`	The user messages provide instructions to the assistant
Prior Message History	`messages`	`string[]`	All relevant information must be supplied via the conversation. You can provide an array of messages from prior conversations here always beginning with the human message.
Temperature	`temperature`	`string`	Optional. Amount of randomness injected into the response. Ranges from 0 to 1. Use temp closer to 0 for analytical / multiple choice, and temp closer to 1 for creative and generative tasks.
Top K	`topK`	`integer`	Only sample from the top K options for each subsequent token. Used to remove `long tail` low probability responses.
Top P	`topP`	`string`	Does nucleus sampling, in which we compute the cumulative distribution over all the options for each subsequent token in decreasing probability order and cut it off once it reaches a particular probability specified.
Maximum Tokens To Sample	`maxTokensToSample`	`integer`	A maximum number of tokens to generate before stopping.

Action Authentication#

Anthropic (Claude) uses API keys for authentication. When you connect your Anthropic (Claude) account, Pipedream securely stores the keys so you can easily authenticate to Anthropic (Claude) APIs in both code and no-code steps.

About Anthropic (Claude)#

AI research and products that put safety at the frontier. Introducing Claude, a next-generation AI assistant for your tasks, no matter the scale.

More Ways to Connect Anthropic (Claude) + AWS#

Other Popular Integrations#

Chat with Anthropic (Claude) API on New DynamoDB Stream Event from AWS API

AWS + Anthropic (Claude)

Chat with Anthropic (Claude) API on New Records Returned by CloudWatch Logs Insights Query from AWS API

Pipedream makes it easy to connect APIs for Anthropic (Claude), AWS and 2,200+ other apps remarkably fast.

Trusted by 1,000,000+ developers from startups to Fortune 500 companies

Developers ♥ Pipedream

1-24of2,200+apps by most popular

1
-
24
of
2,200+
apps by most popular