keefereuther commited on
Commit
8f7b030
·
1 Parent(s): 04bc56b

Simplify README setup instructions and update author links

Browse files

- Remove detailed Part 1-5 setup instructions, refer to PDF manual instead
- Add link to Keefe Reuther's website
- Update acknowledgments section

Files changed (1) hide show
  1. README.md +18 -103
README.md CHANGED
@@ -10,12 +10,11 @@ pinned: true
10
  license: gpl-3.0
11
  short_description: AI-enhanced study app for students
12
  ---
13
-
14
  # Schema Study: An AI-Enhanced Study App for Biology Students
15
 
16
  Schema Study is a free, no-code, open-source web application that turns a spreadsheet of course terms into an AI-powered study coach. Designed for asynchronous student learning and inquiry, Schema Study helps biology students master core course concepts through evidence-based AI-powered conversations. The app leverages OpenAI's latest GPT models via the Responses API to provide instant formative feedback, Socratic questioning, and personalized study support.
17
 
18
- **Key Pedagogical Approach:** Schema Study uses a Socratic questioning method that (1) withholds direct solutions while providing brief, targeted feedback, (2) poses exactly one scenario-grounded follow-up question per turn, and (3) presses for mechanistic reasoning, justification, and connections between concepts. The tool provides formative practice through question-led dialogue; independent performance is evaluated in secure assessments outside the app.
19
 
20
  ## Features
21
 
@@ -34,16 +33,16 @@ Schema Study is a free, no-code, open-source web application that turns a spread
34
 
35
  Before creating your own copy, explore the evaluation versions:
36
 
37
- - **Version 1** (Winter 2025): [https://huggingface.co/spaces/keefereuther/Schema_Study_v1](https://huggingface.co/spaces/keefereuther/Schema_Study_v1)
38
  - **Version 2** (Current Preview): [https://huggingface.co/spaces/keefereuther/Schema_Study_Preview](https://huggingface.co/spaces/keefereuther/Schema_Study_Preview)
39
 
40
  **Note:** These are evaluation versions for testing. You'll need your OpenAI API key to interact with the chatbot on these evaluation versions. The production version can be found at [https://huggingface.co/spaces/keefereuther/Schema_Study](https://huggingface.co/spaces/keefereuther/Schema_Study).
41
 
42
  ## How to Use (Students)
 
43
  1. **Access the App:** Go to your Hugging Face Space URL. Enter the password provided by your instructor.
44
  2. **Select a Term:** Use the dropdown to pick a course term.
45
- 3. **Start Studying:** Respond to the prompt or use a template button to begin your session.
46
- 4. **Chat with the AI:** Ask questions, answer prompts, and explore the term in depth.
47
 
48
  ## How to Use (Instructors)
49
 
@@ -57,102 +56,17 @@ Before starting, you'll need:
57
  - Your course syllabus or a list of course learning objectives
58
  - About 1-2 hours to create your customized copy of Schema Study
59
 
60
- ### Part 1: Setting Up Accounts
61
-
62
- #### 1. Create a Hugging Face Account
63
-
64
- Your chatbot will run inside a Hugging Face Space. Sign-up is browser-based and takes approximately 2 minutes.
65
-
66
- 1. Go to [huggingface.co](https://huggingface.co) → Sign Up
67
- 2. Verify your email before continuing
68
-
69
- #### 2. Open an OpenAI Platform Account
70
-
71
- **NOTE: This is different from a ChatGPT account.** An API (Application Programming Interface) is a way for your application to talk to OpenAI's systems. An API Key is like a special password that gives you permission to use OpenAI's services and keeps track of how much you're using.
72
-
73
- **Pricing Information:**
74
- - **GPT-4.1:** ~$2 per million input tokens, ~$8 per million output tokens
75
- - **GPT-5.1:** ~$1.25 per million input tokens, ~$10 per million output tokens
76
- - **GPT-5.2:** ~$1.75 per million input tokens, ~$14 per million output tokens
77
-
78
- *Note: One million tokens ≈ 750,000 words. Prices may vary by deployment tier.*
79
-
80
- 1. Visit [platform.openai.com](https://platform.openai.com)
81
- 2. Follow the [walkthrough video](https://www.youtube.com/watch?v=QiJ6cWm9Dx4) to generate an API key
82
- 3. Preload $5-10 in API credits
83
- 4. **Important:** Copy and save your API key in a secure place. You will need it later.
84
-
85
- ### Part 2: Creating Your Terms CSV File
86
-
87
- 1. **Download the template:** Use the `terms.csv` file as a starting point
88
- 2. **Refine your TERM entries:**
89
- - Do not alter column headers (TERM and CONTEXT)
90
- - Edit the TERM column to contain terms and phrases relevant to your course learning objectives
91
- - Terms can include concepts, case studies, people, course policies, mathematical/computing functions, or anything else you want students to learn deeply
92
- - Add as many rows as you like
93
- 3. **Tip:** Feed your syllabus to a generative AI chatbot (ChatGPT, Gemini, Claude) to generate a first draft of terms, then curate manually
94
-
95
- **CSV Format:**
96
- - First column: TERM (the term or concept name)
97
- - Second column: CONTEXT (definition, explanation, or course-specific context)
98
-
99
- ### Part 3: Setting Up Your Hugging Face Space
100
 
101
- 1. **Fork or Duplicate the Space:**
102
- - Go to [https://huggingface.co/spaces/keefereuther/Schema_Study](https://huggingface.co/spaces/keefereuther/Schema_Study)
103
- - Click "Duplicate this Space" to create your own copy
104
- - Or clone via git:
105
- ```bash
106
- git clone https://huggingface.co/spaces/<your-username>/<your-space-name>
107
- cd <your-space-name>
108
- ```
109
 
110
- 2. **Edit Configuration:**
111
- - Update `config.py` for your course (title, instructions, prompt templates, etc.)
112
- - Configure AI model settings:
113
- - `ai_model`: Choose "gpt-5.2" (default), "gpt-5.1", or "gpt-4.1"
114
- - `reasoning_effort`: For GPT-5.2 and GPT-5.1, set to "none" (fastest), "minimal", "low", or "medium"
115
- - `enable_web_search`: Set to `True` or `False` (default: True)
116
- - Place your terms CSV (e.g., `terms.csv`) in the root directory
117
-
118
- 3. **Set Secrets:**
119
- - In your Hugging Face Space, go to **Settings > Repository secrets**
120
- - Add the following secrets:
121
- - `username`: Your desired username for app access
122
- - `password`: Your desired password for app access
123
- - `OPENAI_API_KEY`: Your OpenAI API key
124
-
125
- 4. **Push Changes:**
126
- ```bash
127
- git add .
128
- git commit -m "Update configuration and terms"
129
- git push
130
- ```
131
-
132
- ### Part 4: Customizing Schema Study
133
-
134
- All customization is done through `config.py`. Key sections include:
135
-
136
- - **A. Basic App Settings:** App title, terms CSV file, warning messages
137
- - **B. AI Model Settings:** Model selection, reasoning effort, temperature, web search
138
- - **C. Student Instructions:** Instructions displayed in the expander
139
- - **D. Prompt Template Buttons:** Five customizable conversation starters
140
- - **E. Attribution & License:** Sidebar footer information
141
- - **F. Resources List:** Sidebar links and downloadable files
142
- - **G. AI System Prompt:** Advanced customization of the tutor's behavior
143
-
144
- See the user manual (S2_user_manual_v3.pdf) for detailed configuration instructions.
145
-
146
- ### Part 5: Sharing and Embedding
147
-
148
- 1. **Share via Direct Link:** Copy your Space URL and share with students along with the username & password
149
- 2. **Embed in LMS:** In the Space header, select "Embed this Space" and copy the `<iframe>` snippet. Post or embed inside your LMS (e.g., Canvas) along with the username & password. Students can authenticate seamlessly within your course platform.
150
-
151
- ### Model Selection Guide
152
-
153
- - **GPT-5.2** (default): Latest reasoning model, fastest with reasoning="none", supports web search
154
- - **GPT-5.1**: Reasoning model with reasoning="none" default for faster responses, supports web search
155
- - **GPT-4.1**: Use if you need temperature control or prefer non-reasoning model, excellent web search support
156
 
157
  ## Configuration
158
 
@@ -169,6 +83,7 @@ See the user manual (S2_user_manual_v3.pdf) for detailed configuration instructi
169
  Schema Study enforces structured pacing to prevent cognitive overload. The system prompt enforces **one focused question plus one short, realistic application example per turn** to reduce confusion from multiple simultaneous follow-ups.
170
 
171
  **Universal Design for Learning (UDL) Adjustments:**
 
172
  - **For additional scaffolding:** Modify `term_prompt` to allow brief clarifying questions
173
  - **For advanced students:** Add instructions to keep responses focused and move efficiently toward connections
174
 
@@ -183,6 +98,7 @@ The five prompt templates provide structured entry points for students who need
183
  ## Technical Details
184
 
185
  ### API & Models
 
186
  - **API Framework:** OpenAI Responses API (streaming-enabled)
187
  - **Supported Models:** GPT-5.2 (default), GPT-5.1, GPT-4.1
188
  - **Streaming:** Real-time token-by-token response streaming
@@ -200,6 +116,7 @@ The five prompt templates provide structured entry points for students who need
200
  - `S2_user_manual_v3.pdf` — Comprehensive user manual with detailed setup and configuration instructions
201
 
202
  ## License
 
203
  This project is licensed under the GNU GPL-3 License. See the [LICENSE](LICENSE) file for details.
204
 
205
  ## Best Practices for Integration
@@ -214,7 +131,7 @@ Based on classroom testing and iterative refinement, here are recommended best p
214
 
215
  ## Research & Citation
216
 
217
- This app, its corresponding manuscript, and all documentation was authored, edited, and tested by Keefe Reuther, [Liam O Mueller](https://biology.ucsd.edu/research/faculty/lomueller), Grace Constantian, Albert Nguyen, and the members of the Reuther Lab.
218
 
219
  Schema Study was developed to address critical challenges in undergraduate biology education: providing immediate, personalized formative feedback to increasingly large, diverse classes. The app uses evidence-based teaching practices and Socratic questioning to deepen understanding, correct misconceptions, and encourage students to find connections among course concepts.
220
 
@@ -228,10 +145,8 @@ The production version of this app can be found at [https://huggingface.co/space
228
 
229
  ## Acknowledgments
230
 
231
- Developed by Keefe Reuther, Assistant Teaching Professor in the UC San Diego School of Biological Sciences. Special thanks to Dr. Liam O Mueller, Grace Constantian, Albert Nguyen, and the members of the Reuther Lab for their support and contributions.
232
-
233
  This work was supported by University of California, San Diego intramural grants TG114333 and RG113974.
234
 
235
  ## Support
236
 
237
- For questions about creating your own version of this application for use in your classroom, please email kdreuther@ucsd.edu.
 
10
  license: gpl-3.0
11
  short_description: AI-enhanced study app for students
12
  ---
 
13
  # Schema Study: An AI-Enhanced Study App for Biology Students
14
 
15
  Schema Study is a free, no-code, open-source web application that turns a spreadsheet of course terms into an AI-powered study coach. Designed for asynchronous student learning and inquiry, Schema Study helps biology students master core course concepts through evidence-based AI-powered conversations. The app leverages OpenAI's latest GPT models via the Responses API to provide instant formative feedback, Socratic questioning, and personalized study support.
16
 
17
+ **Key Pedagogical Approach:** Schema Study uses a Socratic questioning method that (1) withholds direct solutions while providing brief, targeted feedback, (2) poses exactly one scenario-grounded follow-up question per turn, and (3) presses for mechanistic reasoning, justification, and connections between concepts. The tool provides formative practice through question-led dialogue.
18
 
19
  ## Features
20
 
 
33
 
34
  Before creating your own copy, explore the evaluation versions:
35
 
36
+ - **Version 1** (Legacy): [https://huggingface.co/spaces/keefereuther/Schema_Study_v1](https://huggingface.co/spaces/keefereuther/Schema_Study_v1)
37
  - **Version 2** (Current Preview): [https://huggingface.co/spaces/keefereuther/Schema_Study_Preview](https://huggingface.co/spaces/keefereuther/Schema_Study_Preview)
38
 
39
  **Note:** These are evaluation versions for testing. You'll need your OpenAI API key to interact with the chatbot on these evaluation versions. The production version can be found at [https://huggingface.co/spaces/keefereuther/Schema_Study](https://huggingface.co/spaces/keefereuther/Schema_Study).
40
 
41
  ## How to Use (Students)
42
+
43
  1. **Access the App:** Go to your Hugging Face Space URL. Enter the password provided by your instructor.
44
  2. **Select a Term:** Use the dropdown to pick a course term.
45
+ 3. **Start Studying:** Respond to the prompt or use a template button to begin your session. Ask questions, answer prompts, and explore the term in depth.
 
46
 
47
  ## How to Use (Instructors)
48
 
 
56
  - Your course syllabus or a list of course learning objectives
57
  - About 1-2 hours to create your customized copy of Schema Study
58
 
59
+ ### Setup Instructions
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
+ For comprehensive setup instructions, including account creation, terms CSV file creation, Hugging Face Space configuration, customization options, and sharing/embedding, please see the **[Schema Study User Manual](S2_user_manual_v3.pdf)** included in this repository.
 
 
 
 
 
 
 
62
 
63
+ The user manual provides step-by-step guidance for:
64
+ - Setting up Hugging Face and OpenAI accounts
65
+ - Creating and customizing your terms CSV file
66
+ - Configuring your Hugging Face Space
67
+ - Customizing all app settings through `config.py`
68
+ - Sharing and embedding Schema Study in your LMS
69
+ - Model selection and pricing information
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
 
71
  ## Configuration
72
 
 
83
  Schema Study enforces structured pacing to prevent cognitive overload. The system prompt enforces **one focused question plus one short, realistic application example per turn** to reduce confusion from multiple simultaneous follow-ups.
84
 
85
  **Universal Design for Learning (UDL) Adjustments:**
86
+
87
  - **For additional scaffolding:** Modify `term_prompt` to allow brief clarifying questions
88
  - **For advanced students:** Add instructions to keep responses focused and move efficiently toward connections
89
 
 
98
  ## Technical Details
99
 
100
  ### API & Models
101
+
102
  - **API Framework:** OpenAI Responses API (streaming-enabled)
103
  - **Supported Models:** GPT-5.2 (default), GPT-5.1, GPT-4.1
104
  - **Streaming:** Real-time token-by-token response streaming
 
116
  - `S2_user_manual_v3.pdf` — Comprehensive user manual with detailed setup and configuration instructions
117
 
118
  ## License
119
+
120
  This project is licensed under the GNU GPL-3 License. See the [LICENSE](LICENSE) file for details.
121
 
122
  ## Best Practices for Integration
 
131
 
132
  ## Research & Citation
133
 
134
+ This app, its corresponding manuscript, and all documentation was authored, edited, and tested by [Keefe Reuther](https://keefereuther.com), [Liam O Mueller](https://biology.ucsd.edu/research/faculty/lomueller), Grace Constantian, and Albert Nguyen.
135
 
136
  Schema Study was developed to address critical challenges in undergraduate biology education: providing immediate, personalized formative feedback to increasingly large, diverse classes. The app uses evidence-based teaching practices and Socratic questioning to deepen understanding, correct misconceptions, and encourage students to find connections among course concepts.
137
 
 
145
 
146
  ## Acknowledgments
147
 
 
 
148
  This work was supported by University of California, San Diego intramural grants TG114333 and RG113974.
149
 
150
  ## Support
151
 
152
+ For questions about creating your own version of this application for use in your classroom, please email kdreuther@ucsd.edu.