Fosstodon

0 posts0 participants0 posts today

Alvin AshcraftAnnouncing Chroma DB C# SDK. <a href="https://devblogs.microsoft.com/dotnet/announcing-chroma-db-csharp-sdk/?hide_banner=true" rel="nofollow noopener noreferrer" target="_blank">https://devblogs.microsoft.com/dotnet/announcing-chroma-db-csharp-sdk/?hide_banner=true</a> <a class="hashtag" href="https://bsky.app/search?q=%23dotnet" rel="nofollow noopener noreferrer" target="_blank">#dotnet</a> <a class="hashtag" href="https://bsky.app/search?q=%23chromadb" rel="nofollow noopener noreferrer" target="_blank">#chromadb</a> <a class="hashtag" href="https://bsky.app/search?q=%23ai" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a class="hashtag" href="https://bsky.app/search?q=%23oss" rel="nofollow noopener noreferrer" target="_blank">#oss</a> <a class="hashtag" href="https://bsky.app/search?q=%23database" rel="nofollow noopener noreferrer" target="_blank">#database</a> <a class="hashtag" href="https://bsky.app/search?q=%23csharp" rel="nofollow noopener noreferrer" target="_blank">#csharp</a> <a href="https://devblogs.microsoft.com/dotnet/announcing-chroma-db-csharp-sdk/?hide_banner=true" rel="nofollow noopener noreferrer" target="_blank">Announcing Chroma DB C# SDK - ...</a>

Alvin Ashcraft 🐿️Announcing Chroma DB C# SDK.<a href="https://devblogs.microsoft.com/dotnet/announcing-chroma-db-csharp-sdk/?hide_banner=true" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://devblogs.microsoft.com/dotnet/announcing-chroma-db-csharp-sdk/?hide_banner=true</a> <a href="https://hachyderm.io/tags/dotnet" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#dotnet</a> <a href="https://hachyderm.io/tags/chromadb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#chromadb</a> <a href="https://hachyderm.io/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a href="https://hachyderm.io/tags/oss" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#oss</a> <a href="https://hachyderm.io/tags/database" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#database</a> <a href="https://hachyderm.io/tags/csharp" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#csharp</a>

Brandon H :csharp: :verified:via <a href="https://dotnet.social/@dotnet" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@dotnet</a> : Announcing Chroma DB C# SDK<a href="https://ift.tt/UXHGRPJ" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://ift.tt/UXHGRPJ</a> <a href="https://hachyderm.io/tags/ChromaDB" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ChromaDB</a> <a href="https://hachyderm.io/tags/CSharpSDK" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#CSharpSDK</a> <a href="https://hachyderm.io/tags/AIApplications" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#AIApplications</a> <a href="https://hachyderm.io/tags/DotNet" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#DotNet</a> <a href="https://hachyderm.io/tags/SemanticSearch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#SemanticSearch</a> <a href="https://hachyderm.io/tags/VectorSearch" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#VectorSearch</a> <a href="https://hachyderm.io/tags/OpenSource" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#OpenSource</a> <a href="https://hachyderm.io/tags/Database" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Database</a> <a href="https://hachyderm.io/tags/RetrievalAugmentedGeneration" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#RetrievalAugmentedGeneration</a> <a href="https://hachyderm.io/tags/ChromaClient" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ChromaClient</a> <a href="https://hachyderm.io/tags/NuGet" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#NuGet</a> <a href="https://hachyderm.io/tags/Docker" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Docker</a> <a href="https://hachyderm.io/tags/Azure" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Azure</a> <a href="https://hachyderm.io/tags/DataCommunity" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#DataCommunity</a> <a href="https://hachyderm.io/tags/Developers" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Developers</a> <a href="https://hachyderm.io/tags/TechAn" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#TechAn</a>…

HabrSecurity-RAG или как сделать AI Security tool на коленкеLLM-ки и LLM-агенты продолжают наводить шум. Cтатьи про то как сделать очередной RAG или Агента продолжают клепаться (да блин даже мы одна из этих статей), huggingface выпускают smolagents , квантизация позволяет дойти LLM-кам до простых работяг и обывателей, давая им возможность в них потыкаться в той же LM studio или других приложениях. Пока бизнес спешит внедрить очередного виртуального помощника, тот зачастую превращается в неумелого продавца, который не только мешает клиентам связаться со службой поддержки, но и... Удиви меня<a href="https://habr.com/ru/articles/874820/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://habr.com/ru/articles/874820/</a><a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#llm</a> <a href="https://zhub.link/tags/llmattack" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#llmattack</a> <a href="https://zhub.link/tags/llm%D0%BF%D1%80%D0%B8%D0%BB%D0%BE%D0%B6%D0%B5%D0%BD%D0%B8%D1%8F" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#llmприложения</a> <a href="https://zhub.link/tags/ml" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ml</a> <a href="https://zhub.link/tags/langchain" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#langchain</a> <a href="https://zhub.link/tags/langfuse" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#langfuse</a> <a href="https://zhub.link/tags/chromadb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#chromadb</a> <a href="https://zhub.link/tags/%D0%BF%D1%80%D0%BE%D0%BC%D0%BF%D1%82%D0%B8%D0%BD%D1%8A%D0%B5%D0%BA%D1%86%D0%B8%D0%B8" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#промптинъекции</a> <a href="https://zhub.link/tags/%D0%B8%D1%81%D0%BA%D1%83%D1%81%D1%81%D1%82%D0%B2%D0%B5%D0%BD%D0%BD%D1%8B%D0%B9_%D0%B8%D0%BD%D1%82%D0%B5%D0%BB%D0%BB%D0%B5%D0%BA%D1%82" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#искусственный_интеллект</a>

AlexCrimiI had some fun putting together <a href="https://mstdn.social/tags/KnowledgeGraph" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#KnowledgeGraph</a> and RAG for <a href="https://mstdn.social/tags/LLMs" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#LLMs</a> The idea is that the vector embedding to extend the knowledge of an LLM is reinforced by a knowledge graph. Here full explanation and code including GUI, permanent storage with <a href="https://mstdn.social/tags/Chromadb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Chromadb</a>, etc: <a href="https://medium.com/towards-artificial-intelligence/how-i-built-an-llm-app-based-on-graph-rag-system-with-chromadb-and-chainlit-f70c9cca4400" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://medium.com/towards-artificial-intelligence/how-i-built-an-llm-app-based-on-graph-rag-system-with-chromadb-and-chainlit-f70c9cca4400</a>it seems even more cumbersome as they say in Matsumoto et al. <a href="https://academic.oup.com/bioinformatics/article/40/6/btae353/7687047" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://academic.oup.com/bioinformatics/article/40/6/btae353/7687047</a>or maybe it has to do with the size of the graph, as suggested here <a href="https://arxiv.org/abs/2404.16130" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://arxiv.org/abs/2404.16130</a>Let me know what you think about it

Joe Steinbring :thisisfine:<a href="https://mastodon.social/@grimmy" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@grimmy</a> Every time you run the script, it gets the JSON feed from the Kopp’s website, builds a collection in a <a href="https://toot.works/tags/ChromaDB" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ChromaDB</a> vector database, populates it with what today is, what today’s flavor is, and what tomorrow’s flavor is, and then uses that for the embedding. I wasn’t expecting to need to tell it what today’s date is.<a href="https://toot.works/tags/Ollama" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Ollama</a> <a href="https://toot.works/tags/Python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Python</a>

HabrВекторные БД vs Точность — часть 1Как я пытался собрать "по-быстрому" локальный RAG(retrieval augmentation generation), который будет находить термины из словаря Ожегова и поделиться об этом тут. На просторах интернетах все просто. Но на практике для моей задачи это оказалось не так. Точность...<a href="https://habr.com/ru/articles/807957/" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://habr.com/ru/articles/807957/</a><a href="https://zhub.link/tags/llm" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#llm</a> <a href="https://zhub.link/tags/%D0%B2%D0%B5%D0%BA%D1%82%D0%BE%D1%80%D0%BD%D1%8B%D0%B5_%D0%B1%D0%B0%D0%B7%D1%8B_%D0%B4%D0%B0%D0%BD%D0%BD%D1%8B%D1%85" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#векторные_базы_данных</a> <a href="https://zhub.link/tags/retrieval_augmented_generation" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#retrieval_augmented_generation</a> <a href="https://zhub.link/tags/chromadb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#chromadb</a>

Ferdinando Simonetti [ Implementing semantic cache to improve a RAG system with FAISS. - Hugging Face Open-Source AI Cookbook ] <a href="https://huggingface.co/learn/cookbook/semantic_cache_chroma_vector_database" rel="nofollow noopener noreferrer" target="_blank">https://huggingface.co/learn/cookbook/semantic_cache_chroma_vector_database</a> <a href="https://misskey.social/tags/RAG" rel="nofollow noopener noreferrer" target="_blank">#RAG</a> <a href="https://misskey.social/tags/ChromaDB" rel="nofollow noopener noreferrer" target="_blank">#ChromaDB</a> <a href="https://misskey.social/tags/FAISS" rel="nofollow noopener noreferrer" target="_blank">#FAISS</a> <a href="https://misskey.social/tags/Cache" rel="nofollow noopener noreferrer" target="_blank">#Cache</a>

q.bin<a href="https://mastodon.social/tags/vectordatabases" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#vectordatabases</a> are amazing. Created an Q&A <a href="https://mastodon.social/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ai</a> running completely local. And it is shockingly good whilst being shockingly easy to implement...I just dump a folder of PDFs into <a href="https://mastodon.social/tags/apache" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#apache</a> <a href="https://mastodon.social/tags/tika" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#tika</a>. Concat them, split them by /n/n to get paragraphs. Yoink them into <a href="https://mastodon.social/tags/chromadb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#chromadb</a>. DoneNow I can pose a question that will query chroma to return 20 semantically similar documents. Those documents are dumped into a mixtral-instruct in combination with the original question. The results are nearly perfect!

Ferdinando Simonetti <a href="https://docs.trychroma.com/usage-guide#running-chroma-in-clientserver-mode" rel="nofollow noopener noreferrer" target="_blank">https://docs.trychroma.com/usage-guide#running-chroma-in-clientserver-mode</a> <a href="https://misskey.social/tags/ChromaDB" rel="nofollow noopener noreferrer" target="_blank">#ChromaDB</a> <a href="https://misskey.social/tags/Vector" rel="nofollow noopener noreferrer" target="_blank">#Vector</a> <a href="https://misskey.social/tags/Database" rel="nofollow noopener noreferrer" target="_blank">#Database</a> <a href="https://misskey.social/tags/ML" rel="nofollow noopener noreferrer" target="_blank">#ML</a>

Pieter de Bruin 🌍🌈☮️Create an <a href="https://hachyderm.io/tags/Azure" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Azure</a> <a href="https://hachyderm.io/tags/OpenAI" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#OpenAI</a>, <a href="https://hachyderm.io/tags/LangChain" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#LangChain</a>, <a href="https://hachyderm.io/tags/ChromaDB" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ChromaDB</a>, and <a href="https://hachyderm.io/tags/Chainlit" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Chainlit</a> chat app in <a href="https://hachyderm.io/tags/AKS" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#AKS</a> using <a href="https://hachyderm.io/tags/Terraform" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Terraform</a> by <a href="https://bird.makeup/users/babosbird" class="u-url mention" rel="nofollow noopener noreferrer" target="_blank">@babosbird</a> <a href="https://techcommunity.microsoft.com/t5/fasttrack-for-azure/create-an-azure-openai-langchain-chromadb-and-chainlit-chat-app/ba-p/4024070" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://techcommunity.microsoft.com/t5/fasttrack-for-azure/create-an-azure-openai-langchain-chromadb-and-chainlit-chat-app/ba-p/4024070</a>

HabrRetrieval-Augmented Generation в техподдержке на основе YandexGPTСтатья посвящена рассмотрению процесса создания системы генерации ответов службы технической поддержки . Для этого используется методика с расширенным поиском, известная как Retrieval-Augmented Generation ( RAG ). Процесс основан на использовании шаблонов и реальных вопросов-ответов техподдержки. В качестве основных инструментов применяются YandexGPT и ChromaDB .<a href="https://habr.com/ru/articles/784298/" rel="nofollow noopener noreferrer" target="_blank">https://habr.com/ru/articles/784298/</a><a href="https://zhub.link/tags/yandexcloud" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#yandexcloud</a> <a href="https://zhub.link/tags/yandexgpt_%D0%B4%D0%BB%D1%8F_%D0%B1%D0%B8%D0%B7%D0%BD%D0%B5%D1%81%D0%B0" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#yandexgpt_для_бизнеса</a> <a href="https://zhub.link/tags/chromadb" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#chromadb</a> <a href="https://zhub.link/tags/%D1%8D%D0%BC%D0%B1%D0%B5%D0%B4%D0%B4%D0%B8%D0%BD%D0%B3%D0%B8" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#эмбеддинги</a> <a href="https://zhub.link/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ai</a> <a href="https://zhub.link/tags/python" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#python</a>

0×4a6f4672<a href="https://ruby.social/tags/Chroma" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#Chroma</a> is hiring. It was founded recently by Jeff Huber and Anton Troynikov in <a href="https://ruby.social/tags/SanFrancisco" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#SanFrancisco</a>. Their product <a href="https://ruby.social/tags/ChromaDB" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#ChromaDB</a> is a <a href="https://ruby.social/tags/VectorDatabase" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#VectorDatabase</a> for storing and retrieving vector embeddings. <a href="https://trychroma.notion.site/careers-chroma-9d017c3007c7478ebd85bad854101497" rel="nofollow noopener noreferrer" translate="no" target="_blank">https://trychroma.notion.site/careers-chroma-9d017c3007c7478ebd85bad854101497</a>

Recent searches

Search options

Administered by:

Server stats:

#ChromaDB