Taqi Haider@Geeks
is under improvement
11
Events attended
2
Submissions made
Data Scientist, Machine learning Pracitioner
Pakistan
1 year of experience
About me
I am Electrical Engineering graduate, Interested in AI. currently building AI based products and learning new things during this quest.
is under improvement
.png&w=640&q=75)
.png&w=640&q=75)
🤓 Submissions
Chatty Panda
Chatty Panda is an artificial intelligence-powered tool that enables businesses to provide efficient and effective support to their customers. This chatbot is designed to handle customer queries related to business policies, documents, and other important information in multiple languages. The chatbot is programmed with a company-specific database of information related to business policies, regulations, and documents, which allows it to provide accurate and helpful responses to customer inquiries. With its multilingual capabilities, the chatbot can cater to customers from different parts of the world who speak various languages. Customers can interact with the chatbot through a user-friendly interface and ask questions related to their concerns about company policies. The chatbot uses natural language processing to understand the queries and provides relevant answers in real-time. The multilingual customer representative chatbot is a cost-effective solution for businesses looking to improve customer support and streamline their operations. It reduces the workload of customer service representatives and ensures that customers receive quick and accurate responses to their queries, ultimately leading to higher customer satisfaction and loyalty.
Ask Quran
Our goal is to develop a system that can take documents in any language and allow users from different parts of the world with different languages to interact with those documents. This can help spread knowledge without any language barrier. We are first testing it out with Quranic text, which is in Arabic, and building a chatGPT-style bot for question answering. In future, we would like to expand it to additional documents in any language. We first perform embedding of the text using Cohere's multilingual embed model and save those embeddings in a vector database, Pinecone DB in our case. We then take user queries and also embed them and perform a similarity-based search to provide the most relevant results based on the query. The app is currently deployed and publicly available. Streamlit app link: https://taqihaider7-tafsir-quran-sementic-search-llm-app-fwh2if.streamlit.app/
