← Back to cohort

Asfand Ali Irfan

FAST · 2019 · i19 - 1656

—

Phone

—

GitHub

—

Academic

Program

—

CGPA

—

Year

2019

Education

—

Address

—

DOB

—

Career

Current role

—

Target role

—

Skills

Python, Html, CSS, Javascript, Flask, Figma, Pytorch, Visual Studio, Bloomz LLM, Intent Classification, Entity Extraction, Response Generation, Urdu voice to voice integration, Location API

Verbatim text

The exact text the LLM saw on the page (or the booklet text from the old import). This is what powers semantic search.

Group Members: Asfand Ali Irfan (i19 - 1656) KisaanDost is a Mobile-first Web Application/Android Application where farmers can have a phone call-style conversation in which they query our chatbot to gain solutions to their problems. The chatbot is implemented in Python language. First, the user message is used to perform both intent classification and entity extraction. Intent Classification helps us judge which problem the user is trying to solve. Entity Extraction helps us gather the information we need from the user to solve the user's problem. Then Response Generation takes in user messages, intents, and entities as input to respond to the user. As speech is a natural medium for communication, the idea of a voice-powered chat will allow easy querying of useful information. It would help enable many farmers to ask their questions and get answers in our local language. Features include: Bloomz LLM finetuned with local Agri-data sources, An aesthetically pleasing and visibly understandable UI/UX, Factually backed dataset fed by industry professionals, Urdu voice to voice integration, Location API with weather update integrated, Personal farmer user profile. Technology Used: Python, Html, CSS, Javascript, Flask, Figma, Pytorch, Visual Studio. Supervisor Name: Dr. Mirza Omer Beg.

AI enrichment

Asfand Ali Irfan developed KisaanDost, a mobile-first web and Android application featuring a voice-powered chatbot for farmers. The project utilizes Python, Flask, and PyTorch to implement intent classification, entity extraction, and response generation using a fine-tuned Bloomz LLM.

Skills (AI)

["Python", "Flask", "PyTorch", "HTML", "CSS", "JavaScript", "LLM Fine-tuning", "Intent Classification", "Entity Extraction", "Natural Language Processing", "Voice Integration", "UI/UX Design"]

Status: ai_done

Provenance

Source file: FAST - School of Computing -Graduate Directory-2023.pdf
From job #14 page 496
Created: 1778170171