STA Blog

March and April Update

By

STA Presentation Website

Started: 04/04/2024

Description: This website is the website showcasing the livestream for people online to watch!

Thank you to Nicolas for amazing banner.

Web Editor Help

Started: 04/04/2024

Description: This project helps staff at COLA to search easily the right documentation with the use of Retrieval Augmented Generation. Currently, they use Google Dialogue when it only returned one matching result and when adding a new documentation, people need to add a lot of phrases to the document in hope that it can match these phrases with user’s search. Moreover, the model or the techniques they use with Google Dialogue is a black box so it is hard to improve the system. Therefore, I come in to help with upgrading the retrieval part of the system with using Cosine Similarity Search when I converted the documents into vector embedding using Sentence Embedding Model. Then, all of the retrieved relevant documentaries are fed into LLM so that it can generate helpful responses.

All of the functions that wrote:

__construct()

calling_hugging_face($text)

convertHelpCorpusAndStoreToDatabase()

storeEmbeddingIntoDatabase(array $embeddingVector, $path, $title)

processEmbedding(Request $request)

return_best_match_pgvector($embeddingData, $k = 5)

show_validation()

showForm()

The results:

Without intent:
[2025-03-25 21:13:03] Validation Top K: 1, Validation Score: 61, Total: 134 -> 45.5%

[2025-03-25 21:11:49] Validation Top K: 2, Validation Score: 82, Total: 134 -> 61.2%

With intent:
[2025-04-04 19:25:30] Validation Top K: 1, Validation Score: 73, Total: 134 -> 54.5%

[2025-04-04 19:26:44] Validation Top K: 2, Validation Score: 94, Total: 134 -> 70.1%

After eliminating not useful validation entry:

[2025-04-04 19:41:12] Validation Top K: 2, Validation Score: 92, Total: 126 -> 73%

[2025-04-04 19:42:55] Validation Top K: 1, Validation Score: 72, Total: 126 -> 57%

[2025-04-04 19:51:38] Validation Top K: 2, Validation Score: 92, Total: 126
[2025-04-04 19:53:53] Validation Top K: 2, Validation Score: 92, Total: 126

The Rise and Fall of German in Texas Posters (TGDP)

By

The Rise and Fall of German in Texas Posters (TGDP)

I was tasked with continuing to work on the Texas German Dialect Project retractable posters. These posters had already been in the works, and I had to adjust based on client feedback. The client wanted 3 vertical posters with an icon key. Additionally, the client wanted the dates on the timelines to be proportional to the actual time (for example, if the date is labelled “1930-1934”, it should be clearly indicated that the event took place over that span of time).

Here are the posters that I was given to start with:

Changes I had to make:

  • Create icons and develop a visual key
  • Work on making date ranges look like a range on the poster

Creating Icons

This first thing I had to do was develop a visual key. The client wanted icons that represented 5 different types of events: society, immigration, schools, newspapers, and key event. I used Illustrator to draw icons, staying on brand with the colors given to me.

Society
Immigration
Schools
Newspapers
Key Event

Redesigning the Posters

Now that I had icons, I could move on to putting the posters themselves together. The main thing I wanted to focus on was how to show the date range. I settled on added a transparent box behind the event description and using arrows to indicate it’s date range.

After using this technique and adding the icons, the posters ended up looking like this:

Second Drafts

After sending my designs to the client, I got feedback to make sure that the events were proportionally distanced from each other and to add photos + captions to the poster.

Project status: Waiting for feedback

History SZB Posters

By

History SZB Posters

I was assigned to help create posters documenting the life of George I. Sanchez for the SZB building. I was given pictures and text, which I was then to format on posters using Adobe InDesign. The process mainly consisted of cleaning up the photos in Photoshop (sometimes converting to grayscale, removing blemishes, and adjusting them so they weren’t skewed), getting all the elements onto the page, and then rearranging them to make sure that the text was not too overwhelming and that the images were big enough.

View the exhibit:

Save the Date

By

Save the Date

The theme for STA Presentations this year was movie productions! The presentation poster was themed around “The Peanuts Movie” film poster, so Save the Date was to be similarly themed.

First Drafts

I decided to display the important information on a clapper board to keep with the movie theme. However, after doing that, the background looked really empty, so I added film strips behind it. I used the LAITS logo colors as the accent colors for my design.

Additionally, I came up with a secondary design because I felt that the colors on the clapper board may be unnecessary, and the black letters for the less important information (“Save the Date”, “College of Liberal Arts”) might be too bold. I also switched the order of the colored film strips in the background (and brightened them) to match the order they are in in the LAITS logo.

Lastly, I created an option with a different accent font choice. This is a font that matches the one on “The Peanuts Movie” poster, so I thought we may want to see what that looked like too.

This is an alternate design that I thought could work as well. I was also able to get the STA roles information in using this layout.

For style one, I received feedback to:

  • Add STA photos to the film strips with a color overlay
  • Replace “College of Liberal Arts” with the LAITS logo

For style two, I received feedback to:

  • Try and add more personality, as the black was a little overwhelming, and it wasn’t very dynamic
  • Rework the hierarchy/arrangement so that the date is more prominent
  • Add the LAITS logo

Second Drafts

For the first version, I added the STA cutouts to all the film strip rectangles because it looked a little odd to have some empty, even if they were covered with something in front. I also moved “Save the Date” to the slate because it became hard to read in the top left corner when I added the STA photos.

For the second version, I tried to add some movement by creating a new, curved film strip and tilting the film slate. I also added the date/time/location to the film strip because it was more prominent there and put the STA roles under the slate.

We decided to go with style 1, and I received feedback to:

  • reposition the STA photos so that they weren’t being blocked by the film slate
  • make the LAITS logo grayscale

Third draft

After adjusting the graphic according to the feedback I received, it ended up looking like this:

We then decided that there was too much white space in certain places, so we decided to use the more dynamic photos of STAs that were also used on the presentation poster. After deciding this, the graphic looked like this.

Final Thoughts

Overall, this assignment was a fun way for me to practice both my layout and graphic design skills. I don’t have as much practice with Illustrator, so making graphics for this assignment was a new and fun challenge. I’m also happy that we decided on adding the STAs inside the filmstrips—I think it’s a lot more visually interesting and unique. Here is the final design!

March (Thang Truong)

By

Feb – March Update

Project: UT Instapoll

Started on: Feb 20, 2024

Staff Guidance: Chris Pittman

Description: In this project, I redesigned and implemented the look of the application. It looks much better now on the website, but I still need to work on getting this look onto the pdf. Currently, the pdf does not have the logo and every question appears on different page.

Before

After

PDF:

Project: Web Editor Help

Started on: Feb 24, 2024

Staff Guidance: Geoff Boyd

Description: This project involves designing a better retrieval system for the web editor of COLA website. The website serves staff member to search for information easily with the documentation in the database. There are a lot of steps involved with redesigning the retrieval step, starting with implementing the pgvector database, implementing sentence-transformers for converting text to embedding, storing these embeddings into the database and then using cosine similarity to match.

Currently, I have done the first step of establishing the pgvector database and input some fake data into it. The first stage takes me a lot of time to set up and transition into pgvector from sql. But it has been good for now. The next stage I am doing is how to make sentence embedding to convert text to vectors for me.