TerpAI is a GenAI chatbot similar to popular GenAI chatbots you may have heard about. TerpAI is being presented to the UMD campus by the AI Solutions team.
This is part of an ongoing effort to encourage greater AI awareness and provide AI resources to the UMD community. Having a strong knowledge of AI tools such as TerpAI can help differentiate you from others in the job market, especially as GenAI's impact continues to grow.
TerpAI is located at https://terpai.umd.edu.
The AI Solutions team is part of the Division of Information Technology. Our team supports TerpAI among other AI products and services.
The AI Solutions team does not encompass all AI work being done on campus. The campus has many diverse groups that offer services, do research, and educate the UMD community in AI. If your request lies outside the team's purview, we can direct you to other on-campus resources.
You can always email the AI Solutions team at dit-ais@umd.edu.
GenAI is short for Generative AI. In a nutshell, GenAI chatbots can comprehend user questions and generate human-like responses.
Although GenAI chatbots are the most widely used type of GenAI tool, there are other GenAI tools which generate images, speech, music, and more!
This answer will be a little technical and only serves as background information.
GenAI technology is based on a Large Language Model (LLM) built with neural networks. The LLM encodes vast amounts of information including a knowledge of language as well as general facts on many topics. GenAI chatbots can comprehend user questions or requests. It responds with human-like answers.
GenAI gets its name because "gen" stands for the generation of responses. It's this human-like response that differentiates GenAI chatbots from search engines.
The best place to start learning about TerpAI is at the AI@UMD website. Go to the following URL: https://ai.umd.edu/resources/services/terpai
There, you can get a high-level overview of TerpAI's capabilities. Watch the video on that webpage (scroll down to find the video). The video gives you a quick overview of TerpAI.
Afterwards, you can learn what TerpAI can and can't do. You'll learn how TerpAI provides data privacy. You'll see the estimated usage limits of TerpAI based on interactions or file types.
After you've finished reading the information at the AI@UMD website, come back here and learn more about TerpAI!
Non-deterministic means you may get somewhat different answers even if you ask the exact same question to TerpAI twice.
GenAI models, such as those used in natural language processing and image generation, are often non-deterministic. This is considered a feature.
Here are a few reasons why this occurs:
Stochastic Processes: Many generative models incorporate randomness as part of their design. For example, during the generation process, models might sample from a probability distribution to make decisions about which word or feature to generate next. This introduces variability in the output.
Training Variability: The process of training generative models often involves stochastic gradient descent or similar optimization techniques, which can lead to different model parameters even if the training process is repeated with the same data.
Temperature Settings: In models like GPT, the "temperature" parameter can be adjusted to control the randomness of the output. A higher temperature results in more random outputs, while a lower temperature makes the output more deterministic. Users can adjust this setting to balance creativity and coherence.
Beam Search and Sampling Methods: In tasks like text generation, methods such as beam search or sampling with top-k or nucleus sampling introduce elements of randomness to explore different possible continuations of a sequence.
These factors contribute to the non-deterministic behavior of generative AI, allowing for creative and diverse outputs, which can be particularly useful in applications requiring variability and innovation, such as creative writing, art generation, and more.
Other popular GenAI chatbots have stricter limitations on their free versions. You won’t get unlimited use of TerpAI but it has a larger quota than many free GenAI chatbots.
It means your access to TerpAI is not unlimited.
Why? Due to the immense computational requirements of GenAI chatbots and the cost to run these tools, most free GenAI chatbots place limits on their use, including TerpAI. You are given a daily quota to limit that usage. Each interaction with TerpAI decreases the quota you have. If you ask TerpAI too many questions or make too many requests, you will reach your quota. When that happens, you won't be able to use TerpAI. You'll have to wait until your daily quota is reset at 7 pm EST.
For students, there isn't a way to do this now.
For faculty and staff, read further down in the FAQ on how to get additional quota below starting at: How do I switch to another TerpAI Agent?
Contact the AI Solutions team to discuss other ways to increase the quota by emailing: dit-ais@umd.edu.
TerpAI is approved for up to Level 1, "Low Risk" data, based on the University of Maryland Data Classification Standard.
Any data you put into TerpAI will not be shared with other users or used to train the AI.
Current students, faculty, and staff have access to TerpAI.
Yes, they are faculty.
No.
Yes. The one exception is emeritus professors who continue to have access. Losing access to TerpAI also means losing access to a your chat history.
No, administrators do not have access to chat histories.
Each chat session from the chat history can be exported. Click on three dots (see yellow box bellow) in the chat session you want to save which is the right of a short description of that chat. The chat history appears on the left panel of TerpAI.
Unfortunately, there is no bulk way to export your entire chat history: it has to be exported one chat session at a time.
Yes.
When you navigate away from an active TerpAI tab while it is generating a response, the system will pause its output. It will resume only when you return to the tab. Please be aware that this may lead to issues with TerpAI's configured timeouts.
You should watch the TerpAI video at https://ai.umd.edu/resources/services/terpai. It gives you a quick overview of TerpAI.
The steps are
Go to https://terpai.umd.edu/. You will have to log in the first time you use it.
Click on Guidelines highlighted in pink and click on the “I agree” button in the lower right corner.
You can then prompt TerpAI by asking a question or making a request.
A prompt is the input or question sent to a GenAI chatbot. Here are some sample prompts
“What is Generative AI?”
“Write a rap about the pressure students feel during final exams in the style of Eminem.”
In TerpAI, you can type in your prompt at the bottom near the paper clip and microphone icon. Once you hit Enter, TerpAI will provide a response to your prompt.
A search engine query primarily responds with a list of URLs ranked in order of relevance.
By contrast, TerpAI gives human-like responses to user prompts. It's like talking with a very knowledgeable person.
Unlike search engines, you can ask followup questions to TerpAI. TerpAI retains the context of earlier conversations within the same chat session. For example, you could prompt TerpAI with "What is a black hole?" and get a response. If you then prompt "Explain like I'm five", TerpAI will give a simpler explanation. It recalls that you asked about black holes.
Or you could follow up with "Is it the same as dark matter?". TerpAI understands that "it" refers to a black hole.
With TerpAI, you can have back and forth conversations. TerpAI recalls past conversation within the same chat session. When you start a new chat session, TerpAI begins with a clean slate. It will not have knowledge of previous chat sessions.
One strength of GenAI chatbots is its ability to analyze programs and to generate programs based on your prompts. TerpAI works best with popular programming languages like Java, C#, or Python, but it can handle other languages as well. It also has a broad knowledge of many technical subjects from physics to biology to technologies used in the cloud. TerpAI's breadth of knowledge is extraordinary.
Here's one thing search engines can't do: suggest ideas. Let's say you're asked to give a speech on AI use in higher education--TerpAI can help you outline that speech. Or maybe you need ideas for dinner this week. Ask TerpAI to recommend recipes based on the ingredients you have at home. If you don't like the recipe, ask TerpAI to make changes!
You might expect TerpAI to give a perfect response. It won't and you shouldn't expect it to. It won't write a perfect speech the first time. What TerpAI will do, is get you started on that speech. Sometimes, all we need is a little push to accomplish our goals!
TerpAI can do all this and more!
TerpAI understands many languages besides English. It can understand French, Japanese, Tamil, and Filipino among many, many other languages. TerpAI will respond to prompts in the language of the prompt. For example, if you prompt TerpAI with Japanese characters, TerpAI will respond with Japanese characters.
Another feature of TerpAI is to translate text from one language to another. If you don't know Tamil, you can ask TerpAI to translate Tamil text to English.
For students, they will see GPT 4o-mini - UMD. The dropdown only contains this one choice for students.
Faculty and staff can pick from one of two GPT systems. The default GPT system is GPT 4o; the other is GPT 4o-mini.
GPT 4o delivers top-tier performance, handling complex tasks and providing highly detailed responses. GPT 4o-mini offers a faster, more efficient experience, perfect for quick answers and lighter tasks, while still maintaining great quality. Both are designed to suit different needs seamlessly.
No. GPT 4o has a daily quota, and GPT 4o-mini has a separate daily quota. Each chat session in your chat history is either associated with GPT 4o or GPT 4o-mini, so previous conversations retain the GPT system and do not change when you change systems in a new chat.
if you're faculty/staff, and you run out of quota on GPT 4o, you can switch to GPT 4o-mini. Once you've used up both quotas, you have to wait until 7 PM EST to have the quotas reset back to full.
Here are the steps to use GPT 4o-mini assuming GPT 4o is the current selection.
After you accept the guidelines and enter a prompt, the chat session is set to the selected GPT system. For example, if you select GPT 4o and begin chatting, the dropdown disappears.
You can't switch to 4o-mini in the middle of a conversation. You need to start a new chat. Furthermore, you can't continue the old conversation that was originally in GPT 4o in GPT 4o-mini.
You'd have to ask TerpAI the same questions again in GPT 4o-mini which would decrease the GPT 4o-mini quota.
This is a fairly technical question, so we’ll only answer it briefly. GPT stands for Generative Pre-Trained Transformer. It’s basically a neural network that’s been previously trained on large amounts of text. That's the pre-trained part.
From this information, a GPT system generates a response. That's the generative part.
Finally, transformer refers to the kind of neural network used to understand language when you enter a prompt and
The chat history appears on the left, just under New Chat. If you click on a previous chat session, such as "What is Generative AI?", you can continue the conversation. Continuing a conversation can decrease quota due to the previous conversation, so it's best to start a New Chat if you have new prompts to send to TerpAI.
The chat history is divided into separate lines, one per chat session.
You will see three dots on the right. If you click, you will see:
Rename renames the title of the chat session. You could rename the top session to a shorter title: AI In Education. Archive archines the chat session. Delete removes the chat session from the chat history. If you have no need to keep an old chat session, consider deleting it. Export downloads the text of the chat session.
For the most part, yes. However, GenAI chatbots, like TerpAI, can hallucinate.
When a GenAI chatbot hallucinates a response, it is providing answers that range from somewhat inaccurate to totally fictional. Hallucinating isn’t specific to TerpAI but happens to all popular GenAI chatbots. You should always double-check the response especially if it sounds suspicious. Unfortunately, this is an outcome of the neural network training. Fortunately, hallucinations are infrequent and newer GenAI models aim to reduce hallucinations.
No, TerpAI does not have the most recent information. TerpAI uses GPT 4o, the same model that ChatGPT uses. The last time this model was updated was October 2023. The model should get updated at some point, or a new model may come out. TerpAI may have real-time information soon. Keep an eye out!
No. TerpAI has general knowledge of many things, but it has not been specifically trained on UMD websites. TerpAI uses the GPT 4o model which has vast amounts of general information, some of which includes UMD. However, because it has general information, TerpAI can miss UMD-specific information like lectures given on campus, announced snow days, etc.
This appears on the right side of the chat input bar at the bottom of the TerpAI screen. It appears where the red box with the up arrow icon would normally appear.
This spinning icon indicates a lag while TerpAI is working on a response. If you click on the spinning icon, TerpAI will stop working on the response. This is a good idea if the spinning lasts a long time. Once you stop TerpAI's response, you can start a new chat, and the lag should go away.
If you don’t need to continue an earlier chat, start a new chat. To do so, click on New Chat on the top left. Then, click on Guidelines, then I Agree. This will start a new chat.
If you do want to revisit an older chat session, find it on chat history in the left panel and click on the appropriate session. Continue the conversation where you left off!
Go to https://ai.umd.edu/resources/services/terpai to find a list of TerpAI features. Here are a few other features.
It can understand prompts in many languages, including French, Japanese, Tamil, and Filipino. It responds in the language of the prompt.
It can translate text from one language to another. You can prompt it by saying “Translate the following to English: 日本の首都はどこですか. (It translates to “What is the capital of Japan?”).
Not only can TerpAI analyze code, but it can also generate programs in the most popular programming languages. Make sure to follow rules for a class that might restrict the use of TerpAI or any GenAI from being used in specific situations.
You can think of an idea for a song, then have it write lyrics in the style of a singer. Or ask for the song to be written like Dr. Seuss.
TerpAI recalls its answers from the same chat session so if you need clarification, you can provide follow-up prompts and interact back and forth.
You should confirm with your instructor about their policy using TerpAI (or any GenAI) for your courses. Also be sure to read through the acceptable usage guidelines when using TerpAI.
Yes. TerpAI has a microphone icon. Click on it. Ask a question or give a request, then stop the recording by clicking the microphone icon again. As you speak, it will automatically do a speech-to-text conversion. Once you have stopped the recording, press the Enter button, and TerpAI will respond. The speech-to-text only handles English. It lacks support for other languages. However, you can type prompts in other languages.
Yes. Once you get a response, at the bottom, there is a set of icons. The second icon from the left is a speaker icon. Click on it to hear TerpAI speak its response.
This is one feature where TerpAI can't handle multiple languages. It can speak English. However, TerpAI pronounces French answers as if they were English words which means it is being mispronounced. For languages that don't use the Latin alphabet (English and French use the Latin alphabet) such as Tamil and Chinese, the speaking feature does not work at all.
This is a feature of TerpAI. You can upload a single file, including images (JPG or PNG), Word documents, Excel spreadsheets, and PDFs. Once uploaded, you can ask TerpAI a question or request it do something with that uploaded file.
Click on the paper clip icon which is used to chat with a file (an image is a file). The current supported image file formats are jpg and png. This icon is located left of the “Type a message” where you type in a prompt.
Upload an image or drag and drop an image as directed. Once uploaded, you'll see the file name, in this case, pizza.jpg. Click the button Chat with File. Then enter a prompt such as "What is in this image?"
You can ask followup questions. TerpAI is able to count the slices of pizza and the number of pepperoni pieces. It can tell what surface the pizza is lying on. TerpAI's ability to analyze images is quite impressive!
It's similar to chatting with an image. Click on the paper clip icon. Upload any of these files, then add a follow-up prompt.
It takes a substantial amount of technology and computational resources to run TerpAI. This is true for all widely used GenAIs. To avoid using too many resources, GenAIs, like TerpAI, limit how much you can interact with them.
By contrast, search engines require less computation and therefore less money to run. Google made its search engine freely available by selling ads to customers that wanted to target their ads to certain relevant queries. Other search engines have followed a similar approach. GenAI is far more computationally expensive compared to search engines.
Go to https://ai.umd.edu/resources/services/terpai where you'll find a chart that shows the maximum number of interactions of types of file you can use in one day. Use the chart from that to determine how many words you can use in a day. As that value might change in the future, we'll say the quota is N words where N is the number in the chart.
As mentioned earlier, you get daily quotas for each model: one for GPT 4o and one for GPT 4o-mini. You should start a new chat and select GPT 4o-mini instead of switching in a current chat. Otherwise, you may encounter errors.
No, it's not free to upload images just because we use the term "words".
Think of "words" as the unit of measurement for the daily quota. Those who are more familiar with GenAI technology have heard the term tokens. Think of going to an amusement park where you pay some money, and get some tokens. These tokens are the "currency" to get on rides or play games. There's a similar concept in gambling where you exchange money for chips, and play games of chance with chips. Those are basically tokens.
GenAI tokens are similar. Roughly speaking, one token is about one word. The precise definition of a token is technical and not that important. We use words to make it easier to understand, but think of these words like a unit of currency.
Uploading an image decreases your daily quota by about 450 words. This is regardless of the file size of the image up to the maximum allowable size that can be uploaded by TerpAI.
A typical interaction involves a user prompting TerpAI and TerpAI giving a response. Both the prompt and the response decrease the quota. In general, prompting TerpAI uses far less quota than TerpAI's response. As noted earlier with images, file uploads also come with a cost. The costs are much higher for a non-image than an image. The limits by file type can be found in a chart located at https://ai.umd.edu/resources/services/terpai.
N words represents the total quota. If you have ask TerpAI questions directly through a prompt or chat with a file and then ask TerpAI questions, all of this is part of the quota. For example, if you use 20,000 words using text interactions, that leaves fewer words for loading a PDF.
The answer is fairly technical. TerpAI can only retain the information in the chat to continue conversations for a limited time. When you resume a chat the following day, TerpAI has to reload the conversation from the prior day so it can continue the chat session.
The reload isn't free. It reduces your quota. You can avoid this reload charge if you start with a new chat. We highly recommend starting with new chats each day unless you really need to continue an old chat session. You should start new sessions if you are away from your computer for a while to avoid this problem.
You will be informed that you have to wait until the next day to get the equivalent of N words. This happens at 7pm EST.
No, the quota is reset back to the full quota at 7 pm EST each day. Unused quota from prior days do not rollover.
AI technology is quickly evolving. TerpAI is expected to make future improvements. This FAQ may have to be changed from time to time to reflect those updates. Look out for future enhancements!