Chat using Functions with 302.AI API on New Session Updated from Zep API

Pipedream makes it easy to connect APIs for 302.AI, Zep and 2,900+ other apps remarkably fast.

Trigger workflow on

New Session Updated from the Zep API

Next, do this

Chat using Functions with the 302.AI 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 Zep trigger and 302.AI action. When you configure and deploy the workflow, it will run on Pipedream's servers 24x7 for free.

Select this integration
Configure the New Session Updated trigger
1. Connect your Zep account
2. Configure timer
Configure the Chat using Functions action
1. Connect your 302.AI account
2. Select a Model
3. Configure Chat Input
4. Configure Functions
5. Optional- Configure Instructions
6. Optional- Select a Tool Choice
7. Optional- Select a Parallel Function Calling
8. Optional- Configure Max Tokens
9. Optional- Configure Temperature
10. Optional- Select a Response Format
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 Session Updated on Zep

Description:Emit new event when an existing session is updated. [See the documentation](https://help.getzep.com/api-reference/memory/list-sessions)

Version:0.0.3

Key:zep-session-updated

View on GitHub

Trigger Code#

import common from "../common/base.mjs";

export default {
  ...common,
  key: "zep-session-updated",
  name: "New Session Updated",
  description: "Emit new event when an existing session is updated. [See the documentation](https://help.getzep.com/api-reference/memory/list-sessions)",
  version: "0.0.3",
  type: "source",
  dedupe: "unique",
  methods: {
    ...common.methods,
    getNewResults(lastTs, max) {
      return this.getSessions({
        lastTs,
        max,
        orderBy: "updated_at",
      });
    },
    generateMeta(session) {
      const ts = Date.parse(session.updated_at);
      return {
        id: `${session.session_id}${ts}`,
        summary: `Updated Session: ${session.session_id}`,
        ts,
      };
    },
  },
};

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
Zep	`zep`	`app`	This component uses the Zep app.
N/A	`db`	`$.service.db`	This component uses `$.service.db` to maintain state between executions.
	`timer`	`$.interface.timer`

Trigger Authentication#

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

About Zep#

The Foundational Memory Layer for AI. Equip your agents with the knowledge to complete tasks, from the mundane to monumental.

Action#

Chat using Functions on 302.AI

Description:Enable your 302.AI model to invoke user-defined functions. Useful for conditional logic, workflow orchestration, and tool invocation within conversations. [See documentation](https://doc.302.ai/211560247e0)

Version:0.0.1

Key:_302_ai-chat-using-functions

View on GitHub

Action Code#

import _302_ai from "../../_302_ai.app.mjs";
import constants from "../common/constants.mjs";

export default {
  name: "Chat using Functions",
  version: "0.0.1",
  annotations: {
    destructiveHint: false,
    openWorldHint: true,
    readOnlyHint: false,
  },
  key: "_302_ai-chat-using-functions",
  description: "Enable your 302.AI model to invoke user-defined functions. Useful for conditional logic, workflow orchestration, and tool invocation within conversations. [See documentation](https://doc.302.ai/211560247e0)",
  type: "action",
  props: {
    _302_ai,
    modelId: {
      propDefinition: [
        _302_ai,
        "chatCompletionModelId",
      ],
    },
    input: {
      type: "string",
      label: "Chat Input",
      description: "Text input to the model used to generate a response",
    },
    functions: {
      type: "string",
      label: "Functions",
      description: "A valid JSON array of tools/functions using the OpenAI function schema definition. Each tool must have a `type` property set to \"function\" and a `function` object with `name`, `description`, and `parameters`.",
      default:
`[
  {
    "type": "function",
    "function": {
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA"
          },
          "unit": {
            "type": "string",
            "enum": ["celsius", "fahrenheit"]
          }
        },
        "required": ["location"]
      }
    }
  }
]`,
    },
    instructions: {
      type: "string",
      label: "Instructions",
      description: "System instructions for the model",
      optional: true,
    },
    toolChoice: {
      type: "string",
      label: "Tool Choice",
      description: "- **auto**: The model decides whether and how many functions to call.\n- **required**: The model must call one or more functions.\n- **function_name**: Enter a custom function name to force the model to call this specific function.",
      optional: true,
      default: "auto",
      options: [
        "auto",
        "required",
      ],
    },
    parallelToolCalls: {
      type: "string",
      label: "Parallel Function Calling",
      description: "Allow or prevent the model to call multiple functions in a single turn",
      optional: true,
      default: "1",
      options: [
        {
          label: "Enabled",
          value: "1",
        },
        {
          label: "Disabled",
          value: "0",
        },
      ],
    },
    maxTokens: {
      label: "Max Tokens",
      description: "The maximum number of tokens to generate in the completion.",
      type: "string",
      optional: true,
    },
    temperature: {
      label: "Temperature",
      description: "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.",
      type: "string",
      optional: true,
    },
    responseFormat: {
      type: "string",
      label: "Response Format",
      description: "- **Text**: Returns unstructured text output.\n- **JSON Schema**: Enables you to define a specific structure for the model's output using a JSON schema.",
      options: [
        constants.CHAT_RESPONSE_FORMAT.TEXT.value,
        constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value,
      ],
      default: constants.CHAT_RESPONSE_FORMAT.TEXT.value,
      optional: true,
      reloadProps: true,
    },
  },
  additionalProps() {
    const props = {};

    if (this.responseFormat === constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value) {
      props.jsonSchema = {
        type: "string",
        label: "JSON Schema",
        description: "Define the schema that the model's output must adhere to.",
      };
    }

    return props;
  },
  async run({ $ }) {
    const messages = [];

    if (this.instructions) {
      messages.push({
        role: "system",
        content: this.instructions,
      });
    }

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

    const data = {
      model: this.modelId,
      messages,
      parallel_tool_calls: parseInt(this.parallelToolCalls) === 1,
      tools: [],
    };

    if (this.maxTokens) {
      data.max_tokens = parseInt(this.maxTokens);
    }

    if (this.temperature) {
      data.temperature = parseFloat(this.temperature);
    }

    let functions = this.functions;
    if (typeof functions === "string") {
      try {
        functions = JSON.parse(functions);
      } catch (error) {
        throw new Error("Invalid JSON format in the provided Functions Schema");
      }
    }

    if (Array.isArray(functions)) {
      data.tools.push(...functions);
    } else {
      data.tools.push(functions);
    }

    if (this.toolChoice) {
      if (this.toolChoice === "auto" || this.toolChoice === "required") {
        data.tool_choice = this.toolChoice;
      } else {
        data.tool_choice = {
          type: "function",
          name: this.toolChoice,
        };
      }
    }

    if (this.responseFormat === constants.CHAT_RESPONSE_FORMAT.JSON_SCHEMA.value
      && this.jsonSchema) {
      try {
        data.response_format = {
          type: this.responseFormat,
          json_schema: typeof this.jsonSchema === "string"
            ? JSON.parse(this.jsonSchema)
            : this.jsonSchema,
        };
      } catch (error) {
        throw new Error("Invalid JSON format in the provided JSON Schema");
      }
    }

    const response = await this._302_ai.createChatCompletion({
      $,
      data,
    });

    if (response) {
      $.export("$summary", `Successfully sent chat with id ${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
302.AI	`_302_ai`	`app`	This component uses the 302.AI app.
Model	`modelId`	`string`	Select a value from the drop down menu.
Chat Input	`input`	`string`	Text input to the model used to generate a response
Functions	`functions`	`string`	A valid JSON array of tools/functions using the OpenAI function schema definition. Each tool must have a `type` property set to "function" and a `function` object with `name`, `description`, and `parameters`.
Instructions	`instructions`	`string`	System instructions for the model
Tool Choice	`toolChoice`	`string`	Select a value from the drop down menu:`autorequired`
Parallel Function Calling	`parallelToolCalls`	`string`	Select a value from the drop down menu:`{ "label": "Enabled", "value": "1" }{ "label": "Disabled", "value": "0" }`
Max Tokens	`maxTokens`	`string`	The maximum number of tokens to generate in the completion.
Temperature	`temperature`	`string`	What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.
Response Format	`responseFormat`	`string`	Select a value from the drop down menu:`textjson_schema`