Chat with Cohere API on New Record (Instant, of Selectable Type) from Salesforce API

Pipedream makes it easy to connect APIs for Cohere, Salesforce and 2,400+ other apps remarkably fast.

Trigger workflow on

New Record (Instant, of Selectable Type) from the Salesforce API

Next, do this

Chat with the Cohere 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 Salesforce trigger and Cohere action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Record (Instant, of Selectable Type) trigger
1. Connect your Salesforce account
2. Configure timer
3. Select a Object Type
4. Optional- Select one or more Fields to Obtain
Configure the Chat action
1. Connect your Cohere account
2. Configure Message
3. Optional- Select a Model
4. Optional- Configure Temperature
5. Optional- Configure Max Tokens
6. Optional- Configure K
7. Optional- Configure P
8. Optional- Configure Stop Sequences
9. Optional- Configure Frequency Penalty
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 Record (Instant, of Selectable Type) on Salesforce

Description:Emit new event when a record of the selected object type is created. [See the documentation](https://sforce.co/3yPSJZy)

Version:0.2.0

Key:salesforce_rest_api-new-record-instant

View on GitHub

Salesforce Overview#

The Salesforce (REST API) provides a powerful platform for creating and managing customer relationships with a wide array of features like data manipulation, querying, and complex automation. With Pipedream's serverless execution, you can create workflows that automate your sales processes, sync data with other platforms, enhance customer engagement, and trigger actions based on specific events. Dive into Salesforce data, streamline lead management, track customer interactions, and push or pull data to or from Salesforce seamlessly.

Trigger Code#

import startCase from "lodash/startCase.js";
import common from "../common.mjs";

export default {
  ...common,
  type: "source",
  name: "New Record (Instant, of Selectable Type)",
  key: "salesforce_rest_api-new-record-instant",
  description: "Emit new event when a record of the selected object type is created. [See the documentation](https://sforce.co/3yPSJZy)",
  version: "0.2.0",
  props: {
    ...common.props,
    fieldsToObtain: {
      propDefinition: [
        common.props.salesforce,
        "fieldsToObtain",
        (c) => ({
          objType: c.objectType,
        }),
      ],
      optional: true,
      description: "Select the field(s) to be retrieved for the records. Only applicable if the source is running on a timer. If running on a webhook, or if not specified, all fields will be retrieved.",
    },
  },
  hooks: {
    ...common.hooks,
    async deploy() {
      const objectType = this.objectType;
      const nameField = await this.salesforce.getNameFieldForObjectType(objectType);
      this.setNameField(nameField);

      // emit historical events
      const { recentItems } = await this.salesforce.listSObjectTypeIds(objectType);
      const ids = recentItems.map((item) => item.Id);
      for (const id of ids.slice(-25)) {
        const object = await this.salesforce.getSObject(objectType, id);
        const event = {
          body: {
            "New": object,
            "UserId": id,
          },
        };
        this.processWebhookEvent(event);
      }
    },
  },
  methods: {
    ...common.methods,
    generateTimerMeta(item, fieldName) {
      const { objectType } = this;
      const {
        CreatedDate: createdDate,
        [fieldName]: name,
        Id: id,
      } = item;
      const entityType = startCase(objectType);
      const summary = `New ${entityType} created: ${name ?? id}`;
      const ts = Date.parse(createdDate);
      return {
        id,
        summary,
        ts,
      };
    },
    generateWebhookMeta(data) {
      const nameField = this.getNameField();
      const { New: newObject } = data.body;
      const {
        CreatedDate: createdDate,
        Id: id,
        [nameField]: name,
      } = newObject;
      const entityType = startCase(this.objectType).toLowerCase();
      const summary = `New ${entityType} created: ${name ?? id}`;
      const ts = Date.parse(createdDate);
      return {
        id,
        summary,
        ts,
      };
    },
    getEventType() {
      return "new";
    },
    async processTimerEvent(eventData) {
      const {
        paginate,
        objectType,
        setLatestDateCovered,
        getObjectTypeColumns,
        getNameField,
        generateTimerMeta,
        $emit: emit,
      } = this;

      const {
        startTimestamp,
        endTimestamp,
      } = eventData;

      const fieldName = getNameField();
      const columns = getObjectTypeColumns();

      const events = await paginate({
        objectType,
        startTimestamp,
        endTimestamp,
        columns,
      });

      const [
        latestEvent,
      ] = events;

      if (latestEvent?.CreatedDate) {
        const latestDateCovered = new Date(latestEvent.CreatedDate);
        latestDateCovered.setSeconds(0);
        setLatestDateCovered(latestDateCovered.toISOString());
      }

      Array.from(events)
        .reverse()
        .forEach((item) => {
          const meta = generateTimerMeta(item, fieldName);
          emit(item, meta);
        });
    },
    async timerActivateHook() {
      const {
        objectType,
        getObjectTypeDescription,
        setObjectTypeColumns,
      } = this;

      let columns = this.fieldsToObtain;
      if (!columns?.length) {
        const { fields } = await getObjectTypeDescription(objectType);
        columns = fields.map(({ name }) => name);
      }

      setObjectTypeColumns(columns);
    },
  },
};

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
Salesforce	`salesforce`	`app`	This component uses the Salesforce app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
N/A	`http`	`$.interface.http`	This component uses `$.interface.http` to generate a unique URL when the component is first instantiated. Each request to the URL will trigger the `run()` method of the component.
	`timer`	`$.interface.timer`	The timer is only used as a fallback if instant event delivery (webhook) is not available.
Object Type	`objectType`	`string`	Select a value from the drop down menu.
Fields to Obtain	`fieldsToObtain`	`string[]`	Select a value from the drop down menu.

Trigger Authentication#

Salesforce uses OAuth authentication. When you connect your Salesforce account, Pipedream will open a popup window where you can sign into Salesforce and grant Pipedream permission to connect to your account. Pipedream securely stores and automatically refreshes the OAuth tokens so you can easily authenticate any Salesforce API.

Pipedream requests the following authorization scopes when you connect your account:

About Salesforce#

Web services API for interacting with Salesforce

Action#

Chat on Cohere

Description:Generates a text response to a user message. [See the documentation](https://docs.cohere.com/reference/chat)

Version:0.0.1

Key:cohere_platform-chat

View on GitHub

Cohere Overview#

The Cohere API enables the development of apps with advanced natural language understanding capabilities. Utilizing machine learning, it can help with tasks like text generation, summarization, sentiment analysis, and more. On Pipedream, you can seamlessly integrate Cohere's features into serverless workflows, triggering actions based on text input, processing large volumes of data, or even enhancing chatbots with more human-like responses.

Action Code#

import app from "../../cohere_platform.app.mjs";
import { clearObj } from "../../common/utils.mjs";

export default {
  key: "cohere_platform-chat",
  name: "Chat",
  version: "0.0.1",
  description: "Generates a text response to a user message. [See the documentation](https://docs.cohere.com/reference/chat)",
  type: "action",
  props: {
    app,
    message: {
      propDefinition: [
        app,
        "message",
      ],
    },
    model: {
      propDefinition: [
        app,
        "model",
      ],
    },
    temperature: {
      propDefinition: [
        app,
        "temperature",
      ],
    },
    maxTokens: {
      propDefinition: [
        app,
        "maxTokens",
      ],
    },
    k: {
      propDefinition: [
        app,
        "k",
      ],
    },
    p: {
      propDefinition: [
        app,
        "p",
      ],
    },
    stopSequences: {
      propDefinition: [
        app,
        "stopSequences",
      ],
    },
    frequencyPenalty: {
      propDefinition: [
        app,
        "frequencyPenalty",
      ],
    },
  },
  methods: {
    chat(data) {
      return this.app.client().chat(data);
    },
  },
  async run({ $ }) {
    const {
      chat,
      message,
      model,
      temperature,
      maxTokens,
      k,
      p,
      stopSequences,
      frequencyPenalty,

    } = this;
    const response = await chat(clearObj({
      message,
      model,
      ...(temperature && {
        temperature: parseFloat(temperature),
      }),
      maxTokens,
      k,
      ...(p && {
        p: parseFloat(p),
      }),
      stopSequences,
      ...(frequencyPenalty && {
        frequencyPenalty: parseFloat(frequencyPenalty),
      }),
    }));

    $.export("$summary", `The message was successfully responded with ID \`${response.response_id}\``);
    return 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
Cohere	`app`	`app`	This component uses the Cohere app.
Message	`message`	`string`	Text input for the model to respond to. Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
Model	`model`	`string`	Select a value from the drop down menu:`command-r-pluscommand-rcommandcommand-nightlycommand-lightcommand-light-nightlyembed-english-v3.0embed-english-light-v3.0embed-multilingual-v3.0embed-multilingual-light-v3.0embed-english-v2.0embed-english-light-v2.0embed-multilingual-v2.0rerank-english-v3.0rerank-multilingual-v3.0rerank-english-v2.0rerank-multilingual-v2.0`
Temperature	`temperature`	`string`	Must be between 0 and 1.0 inclusive that tunes the degree of randomness in generation. Lower temperatures mean less random generations, and higher temperatures mean more random generations. Randomness can be further maximized by increasing the value of the P parameter. Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments See Temperature for more details.
Max Tokens	`maxTokens`	`integer`	The maximum number of tokens the model will generate as part of the response. Note: Setting a low value may result in incomplete generations. Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments. See BPE Tokens for more details.
K	`k`	`integer`	Ensures only the top K most likely tokens are considered for generation at each step. Defaults to `0`, min value of `0`, max value of `500`. Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
P	`p`	`string`	Ensures that only the most likely tokens, with total probability mass of P, are considered for generation at each step. If both K and P are enabled, P acts after K. Defaults to `0.75`. min value of `0.01`, max value of `0.99`. Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
Stop Sequences	`stopSequences`	`string[]`	A list of up to 5 strings that the model will use to stop generation. If the model generates a string that matches any of the strings in the list, it will stop generating tokens and return the generated text up to that point not including the stop sequence. Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments
Frequency Penalty	`frequencyPenalty`	`string`	Defaults to `0.0`, min value of `0.0`, max value of `1.0`. Used to reduce repetitiveness of generated tokens. The higher the value, the stronger a penalty is applied to previously present tokens, proportional to how many times they have already appeared in the prompt or prior generation. Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker, Private Deployments

Action Authentication#

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

Generate and copy your API key from your Cohere Platform dashboard.

About Cohere#

Making NLP part of every developer's toolkit. Harness the power of language understanding. Join the developers and businesses who are using Cohere to generate, categorize and organize text at a scale that was previously unimaginable.