Groq Prompt and Response

The Groq Chat Prompt Flow is designed to send a user-defined chat prompt to the Groq API, leveraging Groq's fast AI inference capabilities to generate a response. This flow allows you to structure and store AI-generated responses within the Contextual platform for further analysis or integration into other applications. It is particularly useful for implementing real-time conversational AI features or handling complex interactions requiring quick AI-driven responses.

You can find this template in the Services Catalog under these categories:

• AI, Contextual Basics

What's Included:

• 1 Flow

• 1 Object Type

• 1 Connection

What You'll Need:

• Access to the Groq API

• API Key for the Groq service

Ideas for Using the Groq Chat Prompt Flow:

• Conversational AI: Automate real-time interactions by sending user prompts to Groq’s fast AI inference models, delivering quick and accurate chatbot or virtual assistant responses.

• Decision Support: Implement this flow to rapidly process complex queries and retrieve AI-generated insights, enabling faster and more informed decision-making.

• Content Generation: Send tailored prompts to Groq’s high-performance models to efficiently generate AI-driven responses for content creation, research, or documentation workflows.

---

Flow Overview

Flow Start

The flow begins by injecting a test prompt and model configuration, which can be modified to suit specific needs.

Send Prompt and Receive Response

The flow sends the prompt to the Groq API. The API processes the prompt and returns a response, which is then logged and passed on for further formatting.

Format Response & Create Record

The response from the Groq API is structured into a record format that includes the original prompt, model used, and AI-generated response. This data is then stored in the system.

Error Handling

Any errors encountered during the flow are captured and logged for troubleshooting, ensuring that issues can be quickly identified and resolved.

Flow End

The flow concludes once the records have been successfully created or any errors have been logged.

---

Groq Chat Prompt Flow Details

Inbound Send to Agent Events

• Nodes: contextual-start

• Purpose: The flow begins by receiving a start signal, typically initiated by an external event or agent.

In-Editor Testing

• Nodes: Test Prompt, Prepare Prompt

• Purpose: Allows for testing the flow directly within the editor. The user prompt is prepared and passed to the Groq API for processing.

Code Example: Prepare Prompt Function

// Prepare the payload for Groq API request
msg.payload = {
    model: msg.payload.model, // The model specified in the inject node at start.
    messages: [
        {
            role: "user",
            content: msg.payload.prompt // The content of the user’s prompt
        }
    ]
};
return msg;

Explanation: This function constructs the payload for the Groq API, specifying the model and formatting the prompt in the required structure. The payload is then passed to the next node in the flow, where it will be sent to the API.

Send Prompt and Receive Response

• Nodes: Prompt Groq Chat, Groq Chat Response

• Purpose: The prepared prompt is sent to the Groq API. The response is logged and passed on for further formatting and processing.

Code Example: Groq Chat Response Log

// Log the response from the Groq API
msg.payload.response = {
    aiResponse: msg.payload.response.choices[0].message.content
};
return msg;

Explanation: This function logs the response received from the Groq API, capturing the AI-generated content for further processing and storage.

Format Response & Create Record

• Nodes: Prepare Record Data, Create AI Response Record, Create AI Response Record Log

• Purpose: The AI response is formatted into a structured record and stored in the system, including the original prompt, model, and AI-generated response.

Code Example: Prepare Record Data Function

// Prepare data for Create Object node and assign to msg.payload
let body = {
    prompt: msg.payload.messages[0].content, // Original user prompt
    model: msg.payload.model, // Model specified in the inject start node
    aiResponse: msg.payload.response.choices[0].message.content // AI response from Groq API
};

// Assign the prepared data to msg.payload for use in the Create Object node
msg.payload = body;
return msg;

Explanation: This function formats the API response into a structured object, which includes the original prompt, model, and AI-generated response. This data is then ready to be stored as a record.

Error Handling

• Nodes: catch, Error Catch Log, contextual-error

• Purpose: Catches any errors that occur during the flow and logs them for review, ensuring that issues can be identified and resolved.

Flow End

• Nodes: contextual-end

• Purpose: The flow completes its process, either after successfully creating records or after logging any errors that occurred.

---

Summary of Flow:

• Flow Start: Initiate the flow with a test prompt and model selection.

• Data Preparation: Prepare the user prompt for interaction with the Groq API.

• API Interaction: Send the user prompt to the Groq API and log the response.

• Record Creation: Format and store the AI-generated response as a record for analysis.

• Error Handling: Capture and log any errors that occur during the process.

• Flow End: Conclude the flow after records are created or errors are logged.