Error fetching results in DomoAI Textual Analysis App

amberd · 2025-05-21T18:21:51+00:00

There was an error rendering this rich post.

Hi there!

I learned about the DomoAI Textual Analysis App at Domopalooza, and have found it helpful in analyzing responses to open-ended survey questions (whenever I have a fairly small data set). However, our annual product survey has a lot of responses (7000+), and when I try to use the Textual Analysis App, I just get the error message "error fetching responses." ChatCPT tells me the following:

The "Error fetching data" you're hitting is most likely due to the prompt length becoming too long when concatenating 7000+ survey responses into a single GPT request. GPT models have a token limit (usually ~4,000–8,000 tokens for standard endpoints), and you’re probably exceeding that.

Strategy: Chunk your data into smaller batches and process them iteratively. Instead of sending all 7000+ responses in one big prompt, break them into chunks (e.g., 200–300 at a time), run GPT on each chunk, and then optionally aggregate the chunked responses.

However, I don't love this solution. The whole point is to streamline how we analyze these large numbers of open-ended responses. Any ideas on what else I might try? Thank you!

Quick Links

Accepted answers

nathankilcrease

Hey @amberd!

I'm Nathan, the one who actually developed the app and presented it at Domopalooza, I'm glad you've found use from it!

ChatGPT is correct, the token limit for Domo's LLM is pretty small (I've found through testing that the Text Generation model caps out at around ~450,000 characters), but after the presentation, I have continued to dig into this, and discovered that if you use the Text Summarization model instead, it can handle a much larger amount of input data! Sadly, I discovered this too late, and the app is already published in the App Store using the Text Gen model.

It takes a bit of JavaScript magic to swap the models out in the code, but if you're interested in this solution, here's the new JS function that I'm now using:

async function getGPTResponse(prompt) {

  const endpoint = {

    url: "summarize",

    body: {

      "input":prompt,

      "system":'You are a helpful assistant that writes concise summaries. DO NOT mention that this is a concise summary, just give me the numbered list with descriptions, nothing else. \n',

      "promptTemplate":{

        "template":"${input}"

      },

      "model":"domo.domo_ai.domogpt-summarize-v1:anthropic",

      "outputStyle":"NUMBERED",

      "outputWordLength":{

        "max":300,

        "min":100

      }

    }

  };

  try {

      let result = await domo.post('/domo/ai/v1/text/' + endpoint.url, endpoint.body);

      if (result && result.choices[0] && result.choices[0].output) {

          return result.choices[0].output;

      }

  } catch (err) {

      console.log(err);

      // Check if the error has a response property with additional details

      if (err.response) {

          console.error(`Error Response: ${JSON.stringify(err.response)}`);

          return `Unexpected error occurred: ${err.response.status} - ${err.response.statusText}`;

      } else {

          // Log generic error details if the response is not present

          console.error(`Error: ${err.message}`);

          return `Unexpected error occurred: ${err.message}`;

      }

  }


  return ERROR_MESSAGE;
}

You'll want to update the "system" variable in there to match the context you want to give Domo, but this should get you started!

BIG DISCLAIMER: I have found that this model is way more inconsistent than Text Generation, and it will sometimes mis-format or simply ignore some parts of your prompt. If you know any JS, then you can try to put more instructions in the "system" variable and remove it from the "prompt" variable, since it seems to listen to that a little bit better than the prompt itself.

Hope this helps you!

All comments

ColemenWilson

@nathankilcrease

nathankilcrease

Hey @amberd!

I'm Nathan, the one who actually developed the app and presented it at Domopalooza, I'm glad you've found use from it!

It takes a bit of JavaScript magic to swap the models out in the code, but if you're interested in this solution, here's the new JS function that I'm now using:

async function getGPTResponse(prompt) {

  const endpoint = {

    url: "summarize",

    body: {

      "input":prompt,

      "system":'You are a helpful assistant that writes concise summaries. DO NOT mention that this is a concise summary, just give me the numbered list with descriptions, nothing else. \n',

      "promptTemplate":{

        "template":"${input}"

      },

      "model":"domo.domo_ai.domogpt-summarize-v1:anthropic",

      "outputStyle":"NUMBERED",

      "outputWordLength":{

        "max":300,

        "min":100

      }

    }

  };

  try {

      let result = await domo.post('/domo/ai/v1/text/' + endpoint.url, endpoint.body);

      if (result && result.choices[0] && result.choices[0].output) {

          return result.choices[0].output;

      }

  } catch (err) {

      console.log(err);

      // Check if the error has a response property with additional details

      if (err.response) {

          console.error(`Error Response: ${JSON.stringify(err.response)}`);

          return `Unexpected error occurred: ${err.response.status} - ${err.response.statusText}`;

      } else {

          // Log generic error details if the response is not present

          console.error(`Error: ${err.message}`);

          return `Unexpected error occurred: ${err.message}`;

      }

  }


  return ERROR_MESSAGE;
}

Hope this helps you!

amberd

Thanks Nathan! This was super helpful - I copied in that JS function & it worked like a charm! Appreciate your help!

other categories

Product Ideas
Have a Domo product enhancement idea? Submit or upvote on ideas in the Ideas Exchange.
Ideas Exchange
Suggest & vote on new features you would like to see implemented in the Domo Product.
Data Connections
Ask questions about Connectors, Workbench, Cloud Amplifier and get best practices from Domo peers
Connectors
Connectors, Custom Connectors, Writeback
Workbench
Ask questions about Workbench, a secure, client-side solution for uploading your on-premise data to Domo.
Cloud Integrations
Ask questions about Cloud Integrations and Federated Data connection to your data warehouse or lake.
Data & ETL
Ask questions about Magic ETL, SQL DataFlows, DataFusion, Dataset Views and get best practices from Domo peers
Magic ETL
Ask Magic ETL questions and get answers from Domo peers
SQL DataFlows
Ask SQL DataFlow questions and get answers from Domo peers
Datasets
Ask DataFusion and Dataset Views questions and get answers from Domo peers
Visualize & Apps
Ask questions about Beast Mode, Cards, Charting, Dashboards, Stories, Variables and get best practices from Domo peers
Dashboards
Ask Cards, Dashboards, and Stories questions and get answers from Domo peers
App Studio
Ask questions about building apps in App Studio.
Pro-code Components
Ask questions about pro-code components and Domo Bricks and get answers from Domo peers.
Charting & Analyzer
Ask questions about charting and Analyzer and get answers from Domo peers.
Calculations & Variables (Beast Mode)
Ask questions about using calculated fields and Variables (Beast Modes) in Analyzer.
AI & Data science
Ask questions about DomoAI and get answers from Domo peers.
Domo AI & AI Chat
Ask questions about AI Chat and AI assistants.
Managing AI
Ask questions about managing AI with AI Playground, AI projects, AI models, and more.
Jupyter Workspaces
Ask questions about Jupyter Workspaces, Notebooks, and file share.
Automate
Ask questions about App Framework, Workflows, Domo Bricks, Domo Developer, API and get best practices from Domo peers
Workflows
Ask questions about Task Center, building automations with Domo Workflows, and executing JavaScript or Python code with Code Engine.
Alerts
Ask questions about managing alerts in Domo and get answers from Domo peers.
Distribute
Ask questions about Domo Everywhere, Scheduled Reports, Mobile and get best practices from Domo peers
Domo Everywhere
Ask questions about embedded analytics with Domo Everywhere.
Reporting
Ask questions about Scheduled Reports, Report Builder, and Slideshow Publications.
Manage
Ask questions about Governance Administration, Approvals, Teams, Alerts, and Buzz and get best practices from Domo peers
Governance & Security
Ask questions about People, Groups, Roles, Sandbox, Activity log, Buzz, Teams, Approvals and PDP and get best practices from Domo peers
Navigation & Productivity
Ask questions about navigation, Projects & Tasks, Goals, and Buzz chat.
APIs
Ask APIs and Developer.domo.com questions and get answers from Domo peers
Add-ins & Plugins
Ask questions about plugins, Microsoft add-ins, and other third-party software integrations.
Domo Community Gallery
Watch how our Customers are using Domo to solve their complex problems.
Product Releases
Domo support and product teams are here to live-answer questions about the most recent product releases. Please post questions in this Forum board for all users to benefit (rather than submitting a support ticket).
Domo University
Questions or discussions related to Domo University, trainings and certifications
Community Forums
Getting Started
Welcome to Domo's Community Forums! You'll find everything you need to get started in this category.
Community Announcements
Get the latest from Domo's Community Team.
Social Groups
Archive
Old or outdated content that could still be found helpful.

Find more posts tagged with

Apps

AI Models