Unified LLM API client library for Python. Simple API for Chat, Embedding, Rerank, and Tokenizer. OpenAI-compatible with streaming support and unified usage tracking.

The Tensorflow implementation of accepted ACL 2018 paper "A deep relevance model for zero-shot document filtering", Chenliang Li, Wei Zhou, Feng Ji, Yu Duan, Haiqing Chen, http://aclweb.org/anthology/P18-1214

Pytorch implementation of CACM (WSDM'20)

Fine-Grained Relevance Annotations for Multi-Task Document Ranking and Question Answering

ir_explain: a Python Library of Explainable IR Methods

An information retrieval system for document ranking. Implementation and evaluation of Okapi BM25, Cosine Similarity, and Language Models for document ranking and retrieval. Includes precision-recall evaluation metrics and a detailed project report.

EE448 Big Data Mining Project: Query Expansion with Rocchio Algorithm & Document Ranking with BM25 Score

𝗜𝗻𝗳𝗼𝗿𝗺𝗮𝘁𝗶𝗼𝗻 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹 | 𝗖𝗦𝟲𝟬𝟬𝟵𝟮 | 𝗕𝗼𝗼𝗹-𝗦𝗲𝗮𝗿𝗰𝗵, 𝗥𝗮𝗻𝗸𝗲𝗿, 𝗪𝗼𝗿𝗱𝗡𝗲𝘁 𝗦𝘂𝗺𝗺𝗮𝗿𝗶𝘇𝗲𝗿

This repo contains mini projects in Information Retrieval. Covers indexing, document ranking, web crawling, page ranking, and evaluating different models

🔝 HW1 of Intelligent Information Retrieval MSc Course ECE@UT

😷 Attempt on deep learning track challenge in TREC 2019 - https://microsoft.github.io/TREC-2019-Deep-Learning/

Scikit-learn implementation of co-occurrence word graph based semantic query search using machine learning and vector space similarity measures.

Probabilistic Reasoning and Bayes Rule; Text Data Analysis; Document Ranking and Evaluation.

TinyBERT-based bi-encoder, cross-encoder, and poly-encoder trained on MS MACRO for passage re-ranking

Created a document ranking system with Boolean, probabilistic, and vector space models.

Implement the Pivoted Normalization and BM25 Retrieval Functions

A search engine that ranks documents by relevance to a query using a weighting scheme, tokenization, stop word removal, and stemming

Galago related homeworks of Information Retrieval Course

Assignment Submission for course Information Retrieval (CS F469)

This project implements a Document Retrieval System that integrates GPT-3.5-turbo for query expansion and answer generation. It fetches and ranks documents based on user queries, leveraging MongoDB for document storage, Redis for caching, and web scraping to keep documents updated. The system is designed to provide fast and accurate search results