AI Exam/Question Generator
ATH Infosystems · Software Development
Certification per Microsoft Marketplace.
Evidence tier Source Confirmed · 2 captures on record
What the publisher says
As described on Microsoft Marketplace.
AI Exam/Question Generator is a self-hosted AI-powered educational application designed to help teachers create exam questions and obtain answers based on uploaded learning materials. It provides a web-based Teacher Bot interface where educators can provide source content and use artificial intelligence to analyze the material, answer questions related to the text, or generate sets of exam questions.
Features of AI Exam/Question Generator:
Show the rest of the publisher’s description (22 more lines)
- Self-hosted AI-powered Teacher Bot for exam and question generation.
- Provides a web-based interface built with Streamlit.
- Generates exam questions from provided educational content.
- Answers questions related to uploaded or provided source material.
- Uses OpenAI language models for AI-powered question generation and answering.
- Supports retrieval-based processing of educational content.
- Uses LangChain components for document and AI workflow integration.
- Supports FAISS-based vector search for content retrieval.
- Includes PDF and document-processing capabilities.
- Supports OCR processing through Tesseract for suitable image-based content.
- Can be deployed on a self-hosted Ubuntu server.
- Provides control over application configuration, documents, and deployment environment.
- Suitable for teachers, trainers, tutors, schools, colleges, and educational organizations.
Usage instructions:
Start AI Exam/Question Generator
$ sudo su
$ cd /opt/exam-question-generator
$ source venv/bin/activate
$ streamlit run main.py --server.address 0.0.0.0 --server.port 8501
Access AI Exam/Question Generator: $ http://YOUR_SERVER_IP:8501
Deployment details: The application was deployed using Python 3.11.13 in an isolated virtual environment on Ubuntu 26.04. The installed environment uses Streamlit 1.34.0, PyTorch 2.3.0 CPU, LangChain 0.2.0, OpenAI 1.25.0, and FAISS for the application workflow. .
Disclaimer: AI Exam/Question Generator is provided “as is” under its applicable license. Generated questions and answers may require teacher or subject-matter review for accuracy, relevance, difficulty, completeness, and suitability for the intended curriculum or examination. AI-generated educational content should be reviewed before use in formal assessments. Users are responsible for securely configuring API credentials, protecting uploaded educational materials, controlling access to the application, and complying with applicable privacy, copyright, and data-protection requirements.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment · as of 2026-08-29
Reconciled on 9/3/2026
Sources
Publisher resources
1 linkLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.