Statistics for topic information-retrieval

AdalFlow: The library to build & auto-optimize LLM applications.

:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d...

Retrieval and Retrieval-augmented LLMs

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

All-in-One: Text Embedding, Retrieval, Reranking and RAG

AdalFlow: The library to build & auto-optimize LLM applications.

Coeus 🌐 is an OSINT ToolBox empowering users with tools for effective intelligence gathering from open sources. From social media monitoring 📱 to data analysis 📊, it offers a centralized platform f...

Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses Web-LLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

The code used to train and run inference with the ColPali architecture.

AdalFlow: The library to build & auto-optimize LLM applications.

:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d...

Retrieval and Retrieval-augmented LLMs

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

All-in-One: Text Embedding, Retrieval, Reranking and RAG

AdalFlow: The library to build & auto-optimize LLM applications.

Coeus 🌐 is an OSINT ToolBox empowering users with tools for effective intelligence gathering from open sources. From social media monitoring 📱 to data analysis 📊, it offers a centralized platform f...

Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses Web-LLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

The code used to train and run inference with the ColPali architecture.

:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d...

AdalFlow: The library to build & auto-optimize LLM applications.

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Retrieval and Retrieval-augmented LLMs

💡 All-in-one open-source embeddings database for semantic search, LLM orchestration and language model workflows

Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses Web-LLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

The code used to train and run inference with the ColPali architecture.

All-in-One: Text Embedding, Retrieval, Reranking and RAG

AdalFlow: The library to build & auto-optimize LLM applications.

Efficient BM25 with DuckDB 🦆

AdalFlow: The library to build & auto-optimize LLM applications.

The code used to train and run inference with the ColPali architecture.

Fast lexical search implementing BM25 in Python using Numpy, Numba and Scipy

A compute framework for building Search, RAG, Recommendations and Analytics over complex (structured+unstructured) data, with ultra-modal vector embeddings.

Generative Representational Instruction Tuning

Gen-AI Chat for Teams - Think ChatGPT if it had access to your team's unique knowledge.

:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your d...

Open source libraries and APIs to build custom preprocessing pipelines for labeling, training, or production machine learning pipelines.

Retrieval and Retrieval-augmented LLMs

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

cuVS - a library for vector search and clustering on the GPU

Minimalist web-searching platform with an AI assistant that runs directly from your browser. Uses Web-LLM, Wllama and SearXNG. Demo: https://felladrin-minisearch.hf.space

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases (NeurIPS D&B 2024)

The RAG Experiment Accelerator is a versatile tool designed to expedite and facilitate the process of conducting experiments and evaluations using Azure Cognitive Search and RAG pattern.

Generative Representational Instruction Tuning