How bavenraj08/quintelligence works
This is a FastAPI service that generates role-specific multiple-choice assessment questions. A request resolves a role’s skills and linked courses from Excel catalogs, retrieves reference-data process material from Chroma, builds generation instructions, and sends them with the request to an Azure chat-completions model; the API returns the model’s JSON output. The repository also contains a document-embedding path for Excel and PDF sources. No README was provided, so capabilities and wiring are based on the sampled source and tree.
Main entry points: main.py Assessment API · model.py Chat model adapter · data_embedding.py Document embedding · dataset.py Role and course lookup
Components 13
Request API
- Assessment API
main.py
Assessment Setup
- Role and course lookup
dataset.py - Reference catalog
knowledge_source/reference_data/excel/reference_data.xlsx - Finance catalog
knowledge_source/finance/excel/finance.xlsx
Knowledge Retrieval
- Retrieval prompt builder
model_instruction.py - Reference Chroma store
knowledge_source/reference_data/chroma_db - Document embedding
data_embedding.py - Reference source files
knowledge_source/reference_data - Finance source files
knowledge_source/finance
Question Generation
- Question instructions
instruction.py - Chat model adapter
model.py
Other components
- Assessment requester
- Azure chat service
Connections 15
- Assessment requester → Assessment API: submits request
- Assessment API → Role and course lookup: looks up role
- Role and course lookup → Reference catalog: reads catalog
- Role and course lookup → Finance catalog: reads catalog
- Assessment API → Retrieval prompt builder: builds instructions
- Retrieval prompt builder → Reference Chroma store: queries passages
- Retrieval prompt builder → Question instructions: adds retrieved context
- Document embedding → Reference source files: loads documents
- Document embedding → Finance source files: loads documents
- Document embedding → Reference Chroma store: upserts chunks
- Assessment API → Chat model adapter: invokes generation
- Chat model adapter → Azure chat service: requests completion
- Azure chat service → Chat model adapter: returns completion
- Chat model adapter → Assessment API: returns text
- Assessment API → Assessment requester: returns JSON