opensearch
Search-VL-SFT-36K
An Open Recipe for Frontier Multimodal Search Agents
Cold-Start Agentic SFT · Multi-Turn Fatal-Aware GRPO · Visual Tool Use
📑 Table of Contents
📖 Introduction
🗺️ Overview
🍭 Method Overview
📊 Main Results
🔎 Case Study
📁 Repository Layout
🛠️ Prerequisites
🏋️ Agentic SFT · code/SFT
🚀 Agentic RL · code/RL
📊 Inference & Evaluation · code/infer
🚧 TODO
🙌 Acknowledgements
📖 Introduction
OpenSearch-VL is a fully… See the full description on the dataset page: https://huggingface.co/datasets/OpenSearch-VL/Search-VL-SFT-36K.Search-VL-RL-8K
An Open Recipe for Frontier Multimodal Search Agents
Cold-Start Agentic SFT · Multi-Turn Fatal-Aware GRPO · Visual Tool Use
📑 Table of Contents
📖 Introduction
🗺️ Overview
🍭 Method Overview
📊 Main Results
🔎 Case Study
📁 Repository Layout
🛠️ Prerequisites
🏋️ Agentic SFT · code/SFT
🚀 Agentic RL · code/RL
📊 Inference & Evaluation · code/infer
🚧 TODO
🙌 Acknowledgements
📖 Introduction
OpenSearch-VL is a fully… See the full description on the dataset page: https://huggingface.co/datasets/OpenSearch-VL/Search-VL-RL-8K.opensearch-vl-image-cachemsmarco-hard-negatives-llm-scores
Dataset Card for MS MARCO Hard Negatives LLM Scores (OpenSearch)
Dataset Summary
This dataset is derived from the MS MARCO train split(Hugging Face) and provides hard-negative mining annotations to train retrieval systems. For each query from the source split, we retrieve the top-100 candidate documents using the opensearch-project/opensearch-neural-sparse-encoding-doc-v1 and attach re-ranking scores from bi-encoder teachers and cross-encoder teachers:… See the full description on the dataset page: https://huggingface.co/datasets/opensearch-project/msmarco-hard-negatives-llm-scores.opensearchcon-india-2025Qdrant embeddings of the schedule and event information of OpenSearchCon 2025 (https://opensearchconin2025.sched.com) happening in India in June 2025.
This was created to showcase how one can create an AI concierge agent using a custom knowledge base and Gaia's open-source AI framework with any LLM of their choice.
All logos or information about the event is owned by the event organizer.
msmarco-hard-negatives
Dataset Card for MS MARCO Hard Negatives (OpenSearch)
Dataset Summary
This dataset is derived from the MS MARCO train split(Hugging Face) and provides hard-negative mining annotations to train retrieval systems. For each query from the source split, we retrieve the top-100 candidate documents using the opensearch-project/opensearch-neural-sparse-encoding-doc-v1 and attach re-ranking scores from two cross-encoders: cross-encoder/ms-marco-MiniLM-L12-v2 and… See the full description on the dataset page: https://huggingface.co/datasets/opensearch-project/msmarco-hard-negatives.