HTS Assignment 09

Uploaded by

shahidaazeem84

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

0% found this document useful (0 votes)

23 views2 pages

HTS Assignment 09

Uploaded by

shahidaazeem84

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

You are on page 1/ 2

Assignment #09

Hope to Skills
Free Artificial Intelligence Advance Course
Instructor: Irfan Malik, Dr. Sheraz

Submission:
● Create a new python file and create a Streamlit application.
● Submit a .zip file which contains the .py and requirements.txt files. No other format will be
accepted.
● Submission file should be named as Assignment_09_StudentName.zip
● Deadline for this Assignment is Friday 20-09-2024.
● Strictly follow the submission deadline.
● Make Submission in the Assignment-09 Google Form and press the submit button.
● Click here to submit the Assignment

What you will learn

● How to build a chatbot application from scratch using Streamlit.
● How to integrate and use any Large Language Model (LLM) API keys with Langchain.
● How to use retrieval-augmented generation (RAG) to generate more accurate and contextually
relevant chatbot responses.
● Implement audio input/output handling in Streamlit and use text-to-speech (TTS) and
speech-to-text (STT) functionalities for Urdu.
● Basics of conversational design using modern AI tools.
● Use of vector database

Solve the Following Task

Question 1: Create an intelligent chatbot using Streamlit and Langchain (RAG), where the
chatbot can receive voice input in Urdu, process it, and return both text and audio responses in
Urdu. The chatbot should be able to interact with users fluently, allowing for seamless
audio-to-text and text-to-audio communication in the Urdu language.
Workflow:

● Build the Streamlit interface for real-time Urdu audio input and output.
● Integrate Langchain (RAG) with an LLM (Language Model) API to generate dynamic responses
based on the user’s input. (use PDF files only)
● Ensure the chatbot responds not only with a text-based answer in Urdu but also converts that
response back to audio and plays it for the user.

Instructions:

In this assignment, you are required to use one of the following models for building your chatbot:

● Claude (Anthropic): You can use the Claude Haiku model, which is lightweight and optimized
for fast responses. Claude provides $5 worth of free credit for new users to explore their API.
Visit Claude AI for more details.
● AI21 Labs (Jamba 1.5 Mini): This model is designed for efficient, lightweight inference tasks.
AI21 Labs offers $10 free credits for three months, allowing you to experiment without a credit
card. You can learn more at AI21 Labs.
● Google Gemini API: Google provides the Gemini 1.5 Flash model, which is highly optimized
for multimodal tasks such as text, images, and audio. For details, visit Google Gemini API.
● OpenAI GPT (OpenAI API): OpenAI offers GPT-4o mini, a smaller and more cost-effective
model that is ideal for chatbot tasks. Check out OpenAI's pricing for more details.
●

You can choose either model for this project to handle the chatbot's generative tasks effectively.

Note:

This assignment was actually announced by Sir Irfan Malik in the 38th lecture of Free AI Advance
Course (on 5th September, 2024). Now we are sharing the form with you to submit the assignment.