How veeresh-math/janmitra-ai-scheme-assistant works
JanMitra is a Streamlit assistant for finding government welfare schemes and answering scheme questions in six languages. The main journey is citizen profile entry, eligibility scoring and scheme recommendation, then ranked scheme cards with application details. A separate Q&A journey classifies a natural-language query and presents a structured answer with follow-up prompts. The excerpts show page-level behavior and state handoff, but not the full app setup or model-loading code; unshown runtime links are omitted or marked unverified.
Main entry points: citizen_input.py Profile input · ask_language.py Ask JanMitra · app.py Streamlit app · eligible_schemes.py Eligible schemes
Components 11
Citizen experience
- Streamlit app
app.py - Profile input
app_pages/citizen_input.py
Scheme matching
- Eligibility score
app_pages/citizen_input.py - Scheme recommender
models/scheme_recommender.pkl - Eligible schemes
app_pages/eligible_schemes.py - Processed schemes
data/processed/schemes_processed.csv
Multilingual Q&A
- Ask JanMitra
app_pages/ask_language.py - Intent classifier
models/intent_classifier.pkl - Intent responses
app_pages/ask_language.py
Other components
- Citizen
- Government portal
Connections 11
- Citizen → Streamlit app: uses
README.md - Streamlit app → Profile input: offers profile
README.md - Profile input → Eligibility score: calculates score
app_pages/citizen_input.py - Profile input → Scheme recommender: recommends schemes
README.md - Profile input → Eligible schemes: routes to
app_pages/citizen_input.py - Eligible schemes → Processed schemes: displays scheme details
- Eligible schemes → Government portal: links to apply
README.md - Streamlit app → Ask JanMitra: offers Q&A
README.md - Citizen → Ask JanMitra: asks query
README.md - Ask JanMitra → Intent classifier: classifies query
app_pages/ask_language.py - Ask JanMitra → Intent responses: renders answer
app_pages/ask_language.py