#embedding — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #embedding, aggregated by home.social.
-
Learn how chunking strategies impact RAG performance in 2026, including fixed-size, semantic, and hybrid approaches. Discover optimization techniques for use cases like medical research and legal analysis using tools like LangChain and embedding models.
#RAG #chunking #semantic chunking #LangChain #embedding models
https://dasroot.net/posts/2026/02/chunking-strategies-rag-performance/
-
Learn how chunking strategies impact RAG performance in 2026, including fixed-size, semantic, and hybrid approaches. Discover optimization techniques for use cases like medical research and legal analysis using tools like LangChain and embedding models.
#RAG #chunking #semantic chunking #LangChain #embedding models
https://dasroot.net/posts/2026/02/chunking-strategies-rag-performance/
-
Learn how chunking strategies impact RAG performance in 2026, including fixed-size, semantic, and hybrid approaches. Discover optimization techniques for use cases like medical research and legal analysis using tools like LangChain and embedding models.
#RAG #chunking #semantic chunking #LangChain #embedding models
https://dasroot.net/posts/2026/02/chunking-strategies-rag-performance/
-
Learn how chunking strategies impact RAG performance in 2026, including fixed-size, semantic, and hybrid approaches. Discover optimization techniques for use cases like medical research and legal analysis using tools like LangChain and embedding models.
#RAG #chunking #semantic chunking #LangChain #embedding models
https://dasroot.net/posts/2026/02/chunking-strategies-rag-performance/
-
Learn how chunking strategies impact RAG performance in 2026, including fixed-size, semantic, and hybrid approaches. Discover optimization techniques for use cases like medical research and legal analysis using tools like LangChain and embedding models.
#RAG #chunking #semantic chunking #LangChain #embedding models
https://dasroot.net/posts/2026/02/chunking-strategies-rag-performance/
-
EFF To Court: Don’t Make Embedding Illegal
https://fed.brid.gy/r/https://www.techdirt.com/2026/03/11/eff-to-court-dont-make-embedding-illegal/
-
Малоресурсный язык ломает коммерческие embedding: R@1 0,83 (LaBSE) vs 0,21 (OpenAI) на армянском EPG
Платные модели embedding не гарантируют качество на малоресурсных языках. На задаче кроссязыкового сопоставления EPG-заголовков (EN/RU/HY) бесплатная LaBSE набирает R@1 = 0,83, а OpenAI text-embedding-3-large -- 0,21. Протестировано 19 моделей, код и данные открыты.
https://habr.com/ru/articles/1008422/
#embedding #openai #малоресурсный_язык #sentencetransformers #tokenizer #iptv #epg #benchmark #эмбеддинг
-
via @dotnet : Vector Data in .NET – Building Blocks for AI Part 2
https://ift.tt/VtJUvye
#VectorData #NET #AI #BuildingBlocks #SemanticSearch #RAG #Embedding #Embeddings #VectorDatabase #Qdrant #Redis #CosmosDB #SQLServer #PostgreSQL #SQLite #InMemory #VectorSto… -
Via #LLRX All In: #Embedding #AI in #Law School #Classroom – What is irreducibly human element in #legal #education when AI can pass the #bar #exam, generate effective lectures, provide personalized #learning & #academic support? This article by law prof Gregory M. Duhl confronts that ? head-on by documenting planning, design of a comprehensive transformation of a required doctrinal law school course for 1st yr #Contracts w AI fully embedded throughout the course design. https://www.llrx.com/2026/01/all-in-embedding-ai-in-the-law-school-classroom/
-
Почему ваш RAG не найдёт нужные документы: математический потолок embedding-моделей
Все говорят про embedding-модели в RAG: бенчмарки MTEB, размеры моделей, chunking-стратегии. Но никто не задаёт главный вопрос: а сколько вообще документов может найти single-vector retrieval? Google DeepMind посчитали. Оказалось, что даже 4096-мерные эмбеддинги упираются в математический потолок — есть задачи, где они физически не смогут найти нужный документ из топ-2, даже если модель идеально обучена. В статье разбирается исследование LIMIT, показаны примеры, где dense retrieval проваливается (а BM25 справляется), и объяснено, почему для production-систем нужен гибридный поиск, а не слепая вера в SOTA-эмбеддинги.
https://habr.com/ru/articles/987954/
#RAG #embedding #retrieval #machine_learning #BM25 #поиск #нейросети #векторные_базы_данных
-
Без интернета и шпионов: как мы собрали локального голосового ассистента
Облачные ассистенты вроде Алисы , Google Assistant и Siri давно стали привычными. Но у всех у них одни и те же слабые места: зависимость от быстрого интернета и риск утечки данных. И речь не только о персональной информации — дома нередко обсуждают темы, которые можно отнести к коммерческой или даже военной тайне. Неудивительно, что многим некомфортно говорить в присутствии микрофона, который каждое слово отправляет куда-то «в облако» (один из наших заказчиков прямо сказал: «никаких Алис в доме не будет») . На Хабре уже появлялись статьи про попытки заменить Алису на полностью локальные решения. Но почти всегда все сводилось к стандартной схеме: ESP32-микрофон → Home Assistant → intent recognition . Такая связка работает, но до действительно «умного» ассистента ей далеко. Мы пошли дальше и собрали свой голосовой ассистент, о котором расскажем в статье.
https://habr.com/ru/companies/wirenboard/articles/965856/
#Wiren_Board #BARY #Алиса #голосовой_ассистент #распознавание_речи #vosk #Piper #Embedding #Wake_Word #умный_дом
-
We've been told embedding search strictly superior to BM25 and all other keyword-search algorithms. Then why is it still used in so many modern search pipelines, especially for RAG?
In this post I'll explain you what hybrid search is and why keyword search is still so useful to improve your search results.
-
Embedding User-Defined Indexes in Apache Parquet
https://datafusion.apache.org/blog/2025/07/14/user-defined-parquet-indexes/
#HackerNews #Embedding #User-Defined #Indexes #in #Apache #Parquet #ApacheParquet #UserDefinedIndexes #DataFusion #BigData #Analytics
-
🔮✨ Behold the latest #revolution in web tech: #embedding Lisp—because what the internet truly needs is more parentheses! 🌐🙃 A bold step forward for those who believe #JavaScript is just too mainstream and not nearly cryptic enough. 🎩🧐
https://turtleware.eu/static/paste/wecl-test-gl/main.html #webtech #Lisp #alternatives #coding #humor #HackerNews #ngated -
'Variance-Aware Estimation of Kernel Mean Embedding', by Geoffrey Wolfer, Pierre Alquier.
http://jmlr.org/papers/v26/23-0161.html
#embeddings #embedding #empirical -
🔈Monthly release of 𝐖𝐡𝐚𝐭'𝐬 𝐧𝐞𝐰 𝐢𝐧 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩 | 𝐌𝐚𝐲 2024. 🔈
Article and tool co-authored with Oleksiy Meletskiy.
📢 New Features:
➡𝐖𝐫𝐢𝐭𝐞-𝐮𝐩 𝐬𝐜𝐫𝐞𝐞𝐧𝐬𝐡𝐨𝐭
➡𝐕𝐢𝐫𝐮𝐬𝐓𝐨𝐭𝐚𝐥 𝐈𝐎𝐂𝐬 𝐞𝐧𝐫𝐢𝐜𝐡𝐦𝐞𝐧𝐭
➡𝐄𝐦𝐛𝐞𝐝𝐝𝐞𝐝 𝐌𝐈𝐓𝐑𝐄 𝐀𝐓𝐓&𝐂𝐊® 𝐍𝐚𝐯𝐢𝐠𝐚𝐭𝐨𝐫
➡𝐏𝐃𝐅 𝐫𝐞𝐩𝐨𝐫𝐭 𝐢𝐦𝐩𝐫𝐨𝐯𝐞𝐦𝐞𝐧𝐭𝐬📰𝐁𝐥𝐨𝐠: https://lnkd.in/dgTnd-uD
💻 𝐀𝐩𝐩: https://lnkd.in/dSVdG2B4
⏩ 𝐆𝐢𝐭𝐇𝐮𝐛: https://lnkd.in/dJDSQx8Y𝐇𝐨𝐰 𝐭𝐨 𝐠𝐞𝐭 𝐢𝐧𝐯𝐨𝐥𝐯𝐞𝐝
The project is open to external contributions.
To collaborate, please check the GitHub repository: https://lnkd.in/dJDSQx8YIf you find TI Mindmap useful, please consider starring ⭐ the repository on GitHub.
hashtag#timindmap #ti #mindmap hashtag#mistral #ai #mistralai #threatintelligence #llm #llmapp #openai #azureopenai #largelanguagemodel #cybersecurity #cyber #security #python #streamlit #infer #embedding #chat #ioc #mitre
#ttp #cyberreport #report #mermaid #genai #generativeai #cyberthreatintelligence #github #prompt #promptengineering #FewShotPrompting #gpt hashtag#gpt4 #api #DataVisualization #threat #infosec #threatreport hashtag#oai #analyst #soc #cert #thumbnail #virustotal #stix #GPTo -
🔈Monthly release of 𝐖𝐡𝐚𝐭'𝐬 𝐧𝐞𝐰 𝐢𝐧 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩 | 𝐌𝐚𝐲 2024. 🔈
Article and tool co-authored with Oleksiy Meletskiy.
📢 New Features:
➡𝐖𝐫𝐢𝐭𝐞-𝐮𝐩 𝐬𝐜𝐫𝐞𝐞𝐧𝐬𝐡𝐨𝐭
➡𝐕𝐢𝐫𝐮𝐬𝐓𝐨𝐭𝐚𝐥 𝐈𝐎𝐂𝐬 𝐞𝐧𝐫𝐢𝐜𝐡𝐦𝐞𝐧𝐭
➡𝐄𝐦𝐛𝐞𝐝𝐝𝐞𝐝 𝐌𝐈𝐓𝐑𝐄 𝐀𝐓𝐓&𝐂𝐊® 𝐍𝐚𝐯𝐢𝐠𝐚𝐭𝐨𝐫
➡𝐏𝐃𝐅 𝐫𝐞𝐩𝐨𝐫𝐭 𝐢𝐦𝐩𝐫𝐨𝐯𝐞𝐦𝐞𝐧𝐭𝐬📰𝐁𝐥𝐨𝐠: https://lnkd.in/dgTnd-uD
💻 𝐀𝐩𝐩: https://lnkd.in/dSVdG2B4
⏩ 𝐆𝐢𝐭𝐇𝐮𝐛: https://lnkd.in/dJDSQx8Y𝐇𝐨𝐰 𝐭𝐨 𝐠𝐞𝐭 𝐢𝐧𝐯𝐨𝐥𝐯𝐞𝐝
The project is open to external contributions.
To collaborate, please check the GitHub repository: https://lnkd.in/dJDSQx8YIf you find TI Mindmap useful, please consider starring ⭐ the repository on GitHub.
hashtag#timindmap #ti #mindmap hashtag#mistral #ai #mistralai #threatintelligence #llm #llmapp #openai #azureopenai #largelanguagemodel #cybersecurity #cyber #security #python #streamlit #infer #embedding #chat #ioc #mitre
#ttp #cyberreport #report #mermaid #genai #generativeai #cyberthreatintelligence #github #prompt #promptengineering #FewShotPrompting #gpt hashtag#gpt4 #api #DataVisualization #threat #infosec #threatreport hashtag#oai #analyst #soc #cert #thumbnail #virustotal #stix #GPTo -
🔈Monthly release of 𝐖𝐡𝐚𝐭'𝐬 𝐧𝐞𝐰 𝐢𝐧 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩 | 𝐌𝐚𝐲 2024. 🔈
Article and tool co-authored with Oleksiy Meletskiy.
📢 New Features:
➡𝐖𝐫𝐢𝐭𝐞-𝐮𝐩 𝐬𝐜𝐫𝐞𝐞𝐧𝐬𝐡𝐨𝐭
➡𝐕𝐢𝐫𝐮𝐬𝐓𝐨𝐭𝐚𝐥 𝐈𝐎𝐂𝐬 𝐞𝐧𝐫𝐢𝐜𝐡𝐦𝐞𝐧𝐭
➡𝐄𝐦𝐛𝐞𝐝𝐝𝐞𝐝 𝐌𝐈𝐓𝐑𝐄 𝐀𝐓𝐓&𝐂𝐊® 𝐍𝐚𝐯𝐢𝐠𝐚𝐭𝐨𝐫
➡𝐏𝐃𝐅 𝐫𝐞𝐩𝐨𝐫𝐭 𝐢𝐦𝐩𝐫𝐨𝐯𝐞𝐦𝐞𝐧𝐭𝐬📰𝐁𝐥𝐨𝐠: https://lnkd.in/dgTnd-uD
💻 𝐀𝐩𝐩: https://lnkd.in/dSVdG2B4
⏩ 𝐆𝐢𝐭𝐇𝐮𝐛: https://lnkd.in/dJDSQx8Y𝐇𝐨𝐰 𝐭𝐨 𝐠𝐞𝐭 𝐢𝐧𝐯𝐨𝐥𝐯𝐞𝐝
The project is open to external contributions.
To collaborate, please check the GitHub repository: https://lnkd.in/dJDSQx8YIf you find TI Mindmap useful, please consider starring ⭐ the repository on GitHub.
hashtag#timindmap #ti #mindmap hashtag#mistral #ai #mistralai #threatintelligence #llm #llmapp #openai #azureopenai #largelanguagemodel #cybersecurity #cyber #security #python #streamlit #infer #embedding #chat #ioc #mitre
#ttp #cyberreport #report #mermaid #genai #generativeai #cyberthreatintelligence #github #prompt #promptengineering #FewShotPrompting #gpt hashtag#gpt4 #api #DataVisualization #threat #infosec #threatreport hashtag#oai #analyst #soc #cert #thumbnail #virustotal #stix #GPTo -
🔈Monthly release of 𝐖𝐡𝐚𝐭'𝐬 𝐧𝐞𝐰 𝐢𝐧 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩 | 𝐌𝐚𝐲 2024. 🔈
Article and tool co-authored with Oleksiy Meletskiy.
📢 New Features:
➡𝐖𝐫𝐢𝐭𝐞-𝐮𝐩 𝐬𝐜𝐫𝐞𝐞𝐧𝐬𝐡𝐨𝐭
➡𝐕𝐢𝐫𝐮𝐬𝐓𝐨𝐭𝐚𝐥 𝐈𝐎𝐂𝐬 𝐞𝐧𝐫𝐢𝐜𝐡𝐦𝐞𝐧𝐭
➡𝐄𝐦𝐛𝐞𝐝𝐝𝐞𝐝 𝐌𝐈𝐓𝐑𝐄 𝐀𝐓𝐓&𝐂𝐊® 𝐍𝐚𝐯𝐢𝐠𝐚𝐭𝐨𝐫
➡𝐏𝐃𝐅 𝐫𝐞𝐩𝐨𝐫𝐭 𝐢𝐦𝐩𝐫𝐨𝐯𝐞𝐦𝐞𝐧𝐭𝐬📰𝐁𝐥𝐨𝐠: https://lnkd.in/dgTnd-uD
💻 𝐀𝐩𝐩: https://lnkd.in/dSVdG2B4
⏩ 𝐆𝐢𝐭𝐇𝐮𝐛: https://lnkd.in/dJDSQx8Y𝐇𝐨𝐰 𝐭𝐨 𝐠𝐞𝐭 𝐢𝐧𝐯𝐨𝐥𝐯𝐞𝐝
The project is open to external contributions.
To collaborate, please check the GitHub repository: https://lnkd.in/dJDSQx8YIf you find TI Mindmap useful, please consider starring ⭐ the repository on GitHub.
hashtag#timindmap #ti #mindmap hashtag#mistral #ai #mistralai #threatintelligence #llm #llmapp #openai #azureopenai #largelanguagemodel #cybersecurity #cyber #security #python #streamlit #infer #embedding #chat #ioc #mitre
#ttp #cyberreport #report #mermaid #genai #generativeai #cyberthreatintelligence #github #prompt #promptengineering #FewShotPrompting #gpt hashtag#gpt4 #api #DataVisualization #threat #infosec #threatreport hashtag#oai #analyst #soc #cert #thumbnail #virustotal #stix #GPTo -
🔈Monthly release of 𝐖𝐡𝐚𝐭'𝐬 𝐧𝐞𝐰 𝐢𝐧 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩 | 𝐌𝐚𝐲 2024. 🔈
Article and tool co-authored with Oleksiy Meletskiy.
📢 New Features:
➡𝐖𝐫𝐢𝐭𝐞-𝐮𝐩 𝐬𝐜𝐫𝐞𝐞𝐧𝐬𝐡𝐨𝐭
➡𝐕𝐢𝐫𝐮𝐬𝐓𝐨𝐭𝐚𝐥 𝐈𝐎𝐂𝐬 𝐞𝐧𝐫𝐢𝐜𝐡𝐦𝐞𝐧𝐭
➡𝐄𝐦𝐛𝐞𝐝𝐝𝐞𝐝 𝐌𝐈𝐓𝐑𝐄 𝐀𝐓𝐓&𝐂𝐊® 𝐍𝐚𝐯𝐢𝐠𝐚𝐭𝐨𝐫
➡𝐏𝐃𝐅 𝐫𝐞𝐩𝐨𝐫𝐭 𝐢𝐦𝐩𝐫𝐨𝐯𝐞𝐦𝐞𝐧𝐭𝐬📰𝐁𝐥𝐨𝐠: https://lnkd.in/dgTnd-uD
💻 𝐀𝐩𝐩: https://lnkd.in/dSVdG2B4
⏩ 𝐆𝐢𝐭𝐇𝐮𝐛: https://lnkd.in/dJDSQx8Y𝐇𝐨𝐰 𝐭𝐨 𝐠𝐞𝐭 𝐢𝐧𝐯𝐨𝐥𝐯𝐞𝐝
The project is open to external contributions.
To collaborate, please check the GitHub repository: https://lnkd.in/dJDSQx8YIf you find TI Mindmap useful, please consider starring ⭐ the repository on GitHub.
hashtag#timindmap #ti #mindmap hashtag#mistral #ai #mistralai #threatintelligence #llm #llmapp #openai #azureopenai #largelanguagemodel #cybersecurity #cyber #security #python #streamlit #infer #embedding #chat #ioc #mitre
#ttp #cyberreport #report #mermaid #genai #generativeai #cyberthreatintelligence #github #prompt #promptengineering #FewShotPrompting #gpt hashtag#gpt4 #api #DataVisualization #threat #infosec #threatreport hashtag#oai #analyst #soc #cert #thumbnail #virustotal #stix #GPTo -
'Topological Node2vec: Enhanced Graph Embedding via Persistent Homology', by Yasuaki Hiraoka, Yusuke Imoto, Théo Lacombe, Killian Meehan, Toshiaki Yachimura.
http://jmlr.org/papers/v25/23-1185.html
#node2vec #embedding #topological -
🔈Second monthly release of 𝐖𝐡𝐚𝐭'𝐬 𝐧𝐞𝐰 𝐢𝐧 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩 | 𝐦𝐚𝐫 2024. 🔈
Article and tool co-authored with Oleksiy Meletskiy.📢 New Features:
➡Session management
➡Scraping enhancements
➡Code optimization
➡PDF Report enhancements
➡Mitre ATT&CK Navigator layer📰𝐁𝐥𝐨𝐠: https://lnkd.in/diuJTfrH
💻 𝐀𝐩𝐩: https://lnkd.in/dSVdG2B4
⏩ 𝐆𝐢𝐭𝐇𝐮𝐛: https://lnkd.in/dJDSQx8Y𝐇𝐨𝐰 𝐭𝐨 𝐠𝐞𝐭 𝐢𝐧𝐯𝐨𝐥𝐯𝐞𝐝
The project is open to external contributions.
To collaborate, please check the GitHub repository: https://lnkd.in/dJDSQx8YIf you find TI Mindmap useful, please consider starring ⭐ the repository on GitHub.
#timindmap #ti #mindmap #threatintelligence #llm #llmapp #openai #azureopenai #largelanguagemodel #cybersecurity #cyber #security #python #streamlit #infer #embedding #chat #ioc #mitre #ttp #cyberreport #report #mermaid #genai #generativeai #cyberthreatintelligence
#github #prompt #promptengineering #FewShotPrompting #gpt #gpt4
#api #DataVisualization #threat #infosec #threatreport #oai #analyst #soc -
Excited to share a series of periodic articles on the developments of TI Mindmap: 𝐖𝐡𝐚𝐭’𝐬 𝐧𝐞𝐰 𝐢𝐧 𝐓𝐈 𝐌𝐢𝐧𝐝𝐦𝐚𝐩, first issue.
Article and tool co-authored with Oleksiy Meletskiy.New Features:
➡Extract adversary tactics, techniques, and procedures
➡Tactics, techniques and procedures by execution time
➡Tactics, techniques and procedures timeline
➡AI Chat on your article
➡Mermaid live editor integration
➡PDF report
➡Tweet Mindmap𝐇𝐨𝐰 𝐭𝐨 𝐠𝐞𝐭 𝐢𝐧𝐯𝐨𝐥𝐯𝐞𝐝
The project is open to external contributions.
To collaborate, please check the GitHub repository: https://github.com/format81/TI-Mindmap-GPT/
If you find TI Mindmap useful, please consider starring the repository on GitHub.To learn more:
https://medium.com/@antonio.formato/whats-new-in-ti-mindmap-feb-2024-14cf3b383833#timindmap #ti #mindmap #threatintelligence #llm #llmapp #openai #azureopenai #largelanguagemodel #cybersecurity #cyber #security #python #streamlit #infer #embedding #chat #ioc #mitre #ttp #cyberreport #report #mermaid #genai #generativeai #cyberthreatintelligence
#github #prompt #promptengineering #FewShotPrompting #gpt #gpt4
#api #DataVisualization #threat #infosec #threatreport #oai #analyst #soc #cert -
'Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices', by Doudou Zhou, Tianxi Cai, Junwei Lu.
http://jmlr.org/papers/v24/22-0642.html
#embeddings #embedding #factorization -
'Insights into Ordinal Embedding Algorithms: A Systematic Evaluation', by Leena Chennuru Vankadara, Michael Lohaus, Siavash Haghiri, Faiz Ul Wahab, Ulrike von Luxburg.
http://jmlr.org/papers/v24/21-1170.html
#embeddings #embedding #ordinal -
'Small Transformers Compute Universal Metric Embeddings', by Anastasis Kratsios, Valentin Debarnot, Ivan Dokmanić.
http://jmlr.org/papers/v24/22-1246.html
#embeddings #embedding #dimensionality -
'Small Transformers Compute Universal Metric Embeddings', by Anastasis Kratsios, Valentin Debarnot, Ivan Dokmanić.
http://jmlr.org/papers/v24/22-1246.html
#embeddings #embedding #dimensionality