CFP last date
20 February 2025
Reseach Article

LangchainIQ: Intelligent Content and Query Processing

Published on None 2025 by Chinmay Pichad, Roshan Sawant, Ganesh Supe
International Conference on “Large Language Models and Use cases” 2023
Control System labs
LLMUC2023 - Number 2
None 2025
Authors: Chinmay Pichad, Roshan Sawant, Ganesh Supe

Chinmay Pichad, Roshan Sawant, Ganesh Supe . LangchainIQ: Intelligent Content and Query Processing. International Conference on “Large Language Models and Use cases” 2023. LLMUC2023, 2 (None 2025), 25-28.

@article{
author = { Chinmay Pichad, Roshan Sawant, Ganesh Supe },
title = { LangchainIQ: Intelligent Content and Query Processing },
journal = { International Conference on “Large Language Models and Use cases” 2023 },
issue_date = { None 2025 },
volume = { LLMUC2023 },
number = { 2 },
month = { None },
year = { 2025 },
issn = 0975-8887,
pages = { 25-28 },
numpages = 4,
url = { /proceedings/llmuc2023/number2/langchainiq-intelligent-content-and-query-processing/ },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Proceeding Article
%1 International Conference on “Large Language Models and Use cases” 2023
%A Chinmay Pichad
%A Roshan Sawant
%A Ganesh Supe
%T LangchainIQ: Intelligent Content and Query Processing
%J International Conference on “Large Language Models and Use cases” 2023
%@ 0975-8887
%V LLMUC2023
%N 2
%P 25-28
%D 2025
%I International Journal of Computer Applications
Abstract

LangchainIQ is an educational platform that uses Artificial Intelligence (AI) and Natural Language Processing (NLP) technologies to uplift the learning experience. This platform is designed to enhance their content processing and query processing on a wide range of input formats with additional assessment capabilities by QnA generation with use of input text. LangchainIQ's AI-powered chatbot provides a wide array of content formats, including PDFs, Excel sheets, and YouTube videos. It breaks the given input data, then converts it into chuck and stores it in embedded form, ultimately increasing security. With use of LLM models the content processing power is enhanced. One of the groundbreaking features of LangchainIQ is its proficiency in creating knowledge bases from PDF files. This knowledge base facilitates efficient content retrieval and processing, enabling learners to quickly access and understand the information they need. Additionally, for CSV files, LangchainIQ processes queries by creating dataframes, making it a versatile tool for handling different data formats.

References
  1. Braun, S., & Tsay, J. (2022). A chatbot for PDFs: Using LangChain and Pinecone to build a conversational AI assistant for document management. arXiv preprint arXiv:2201.08244.
  2. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  3. Radford, A., Narasimhan, K., Salimans, T., & Sutskever, I. (2019). Language models are unsupervised multitask learners. OpenAI Blog, 1(8), 9-13.
  4. Wolf, T., Debut, L., Sanh, V., Chaurasia, R., Devlin, J., & Ruder, S. (2020). Huggingface transformers: State-of-the-art natural language processing. arXiv preprint arXiv:2005.14165.
  5. Kumar, A., & Raschka, S. (2021). Pinecone: A simple and efficient framework for large language model inference. arXiv preprint arXiv:2103.10811.
  6. Adith Sreeram A S, Pappuri Jithendra Sai: “An Effective Query System Using LLMs and LangChain”, IJERT, olume 12, Issue 06 (June 2023).
  7. NR Tejaswini, Vidya S, Dr. T Vijaya Kumar : “Langchain-Powered virtual assistant for PDF Communication”, IJERT, Issue 2023
Index Terms

Computer Science
Information Sciences

Keywords

Langchain OpenAI Vector Store Faiss Embedding Dataframe AI Transcripts LLM