How are databases tackling the modern challenges of #AI? 🤔

Find out in this Andrew Oram article by exploring vector databases, #SQL with vector support, and more: lpi.org/5d6x

#LPI #AI #Vector #Milvus #Qdrant #Weaviate #Vespa #ChromaDB #LanceDB

GitHub - chroma-core/context-1-data-gen Contribute to chroma-core/context-1-data-gen development by creating an account on GitHub.

#ChromaDB Context-1: Fast 20B model.
Small Specialized Language Model for fast #agentic search trained to retrieve supporting documents for complex, multi-hop queries. X10 faster than #LLM
#VectorDB #RAG #SLM #Agents
#OpenSource Apache 2.0 lic
github.com/chroma-core/...

How are databases tackling the modern challenges of #AI? 🤔
Find out in this Andrew Oram article by exploring vector databases, #SQL with vector support, and more: lpi.org/5d6x

#LPI #AI #Vector #Milvus #Qdrant #Weaviate #Vespa #ChromaDB #LanceDB

Original post on mastodon.social

Building My First RAG System (Which Sadly Failed the Tax Preparer Exam)
A while back, I posted about how I gave the IRS’ volunteer tax preparer exam to ChatGPT. It scored in the 70s, but an 80% is the minimum required score to pass and be certified. A short while later, I took a Coursera short […]

📖 Read the full article here:
medium.com/@techlatest....

#AI #VectorDatabase #MachineLearning #RAG #LLM #GenerativeAI #ChromaDB #Milvus

New Guide Published: Using ChromaDB as Long-Term Memory for AI Agents

AI agents built on LLMs are powerful, but they don’t naturally remember past interactions. To build smarter and more context-aware agents, developers need persistent memory systems.

#AI #LLM #VectorDatabase #ChromaDB #AIAgents

Как мы с ИИ сделали локальный ИИ, который учится по моим книгам и пишет за меня отчёты Я с GitHub Copilot (Claude) собра...

#python #ai #nlp #LLM #qwen #copilot #claude #chromadb

Origin | Interest | Match

While i'm out of ideas, my next goal for SANYA is a long-term memory. Working on "SANYA-Lex": a RAG module using C# & local SQLite on Linux.
Will be some kind of AoT or Self-contained Single File. Still need to read more about it.

#DotNet #LinuxDev #ChromaDB #SANYA

AI Skills 2025: LangChain, RAG & MLOps—The Complete Guide Comprehensive guide to the three critical AI competencies reshaping hiring in 2025: LangChain for orchestration, RAG for knowledge grounding, and MLOps for production deployment.

AI Skills 2025: LangChain, RAG & MLOps—The Complete Guide

techlife.blog/posts/ai-ski...

#LangChain #RAG #MLOps #LangGraph #DeepAgents #Kubernetes #VectorDatabases #ChromaDB #Weaviate #Pinecone #MLflow

I want to send some love to #LangChain, #ChromaDB, #FlashRank, #HuggingFace and #Ollama.
We've built a RAG system on a hackathon at our company last week and thanks to these marvelous tools we had a first version running already at the end of the first day. Good stuff!
#aiengineering

Выбираем векторную БД для AI-агентов и RAG: большой обзор баз данных и поиск смысла В этой статье я сделал обзо...

#базы #данных #milvus #pgvector #qdrant #redis #chroma #chromadb #ии-агенты #ai-агенты #LLM

Origin | Interest | Match

Выбираем векторную БД для AI-агентов и RAG: большой обзор баз данных и поиск смысла В этой статье я сделал обзо...

#базы #данных #milvus #pgvector #qdrant #redis #chroma #chromadb #ии-агенты #ai-агенты #LLM

Origin | Interest | Match

[Перевод] Как я построил RAG-систему за вечер с помощью 5 open source-инструментов Команда Python for Devs подготовила п...

#python #rag #chromadb #ollama #hnsw #langchain

Origin | Interest | Match

📦 (4/12) The Store Component offers:

• Vector storage abstraction
• Support for #RAG
• Semantic search capabilities
• Integration with #ChromaDB

Essential for building knowledge-based AI applications.

🚨 Why Your Database Will Fail in 2025 (And How to Future-Proof It) Your current database setup might be good enough — for now. But in the next 12 months, it’ll likely break under pressure.

Why Your Database Will Fail in 2025 (And How to Future-Proof It) Your current database setup might be good enough — for now. But in the next 12 months, it’ll likely break under pressure. Co...

#cloud-computing #postgresql #database #startup #chromadb

Origin | Interest | Match

Finished my AI and decided ChromaDB (aka Chroma) "an AI-native vector database" is a must to remember everything and preserve personality. #ChromaDB #Chroma #VectorDatabase #MemoryPersistence #AIMemory #AIPersonality #PersistentMemory #AIDevTools #EmbeddingStorage #OpenSourceAI #AI #Uncensored

I'm using Gemini AI to help me debug my Python code to build a local cybersecurity RAG vector database for a local DeepSeek AI and it feels very oroborous

#ai #deepseek #rag #chromadb #python #cyberserurity

𝐀 𝐅𝐮𝐥𝐥𝐲 𝐋𝐨𝐜𝐚𝐥 𝐀𝐈 𝐂𝐡𝐚𝐭𝐛𝐨𝐭 𝐔𝐬𝐢𝐧𝐠 𝐎𝐥𝐥𝐚𝐦𝐚, 𝐋𝐚𝐧𝐠𝐂𝐡𝐚𝐢𝐧 & 𝐂𝐡𝐫𝐨𝐦𝐚𝐃𝐁 🚀 Today, I got hands-on with a Retrieval-Augmented Generation (RAG) setup that runs entirely offline. I built a private AI assistant that can answer questions from Markdown and PDF documentation — no cloud, no API keys. 🧱 Ollama for local LLM & embedding 🔍 LangChain for RAG orchestration + memory 📦 ChromaDB for vector storage 💬 Streamlit for the chatbot UI Key features: ● Upload .md or .pdf Files ● Auto-re-index and embed with nomic-embed-text ● Ask natural questions to mistral (or other local LLMs) ● Multi-turn chat with memory ● Source highlighting for every answer 🧠 How This Local RAG Chatbot Works (Summary) 1) Upload Your Docs Drag and drop .md and .pdf files into the Streamlit app. The system supports both structured and unstructured formats — no manual formatting needed. 2) Chunking + Embedding Each document is split into small, context-aware text chunks and embedded locally using the nomic-embed-text model via Ollama. 3) Store in Chroma Vector DB The resulting embeddings are stored in ChromaDB, enabling fast and accurate similarity search when queries are made. 4) Ask Natural Questions You type a question like “What are DevOps best practices?”, and the app retrieves the most relevant chunks using semantic search. 5) Answer with LLM + Memory Retrieved context is passed to mistral (or any Ollama-compatible LLM). LangChain manages session memory for multi-turn Q&A. 6) Sources Included Each answer shows where it came from — including the filename and content snippet — so you can trust and trace every response. Display answer + source documents in Streamlit 💬 Example Prompts "What is a microservice?" "How does Kubernetes manage pod lifecycle?" "Give me an example Docker Compose file." "What are DevOps best practices?" Honestly, this was one of those projects that reminded me how far local AI tools have come. No cloud APIs, no fancy GPU rig — just a regular laptop, and I was able to build a fully working RAG chatbot that reads my docs and gives solid, contextual answers. If you’ve ever wanted to interact with your own knowledge base — internal docs, PDFs, notes — in a more natural way, this setup is 100% worth trying. It's private, surprisingly fast, and honestly, kind of fun to put together.

How to Build a Local RAG App with Ollama and ChromaDB in the R Programming Language A Large Language Model (LLM) is a type of machine learning model that is trained to understand and generate human-like text. These models are trained on vast datasets to capture the nuances of human l...

From #FreeCodeCamp: "How to Build a Local #RAG App with #Ollama and #ChromaDB in the R Programming Language"

www.freecodecamp.org/news/build-a...

#RStats #AI #LLM

How to Build a Local RAG App with Ollama and ChromaDB in the R Programming Language A Large Langu...

www.freecodecamp.org/news/build-a-local-rag-a...

#ollama #chromadb #R #Language

Event Attributes

Chroma is now 4x faster

🚀 Exciting news! Chroma v1.0.0 pre-release is now available! Completely rewritten in Rust, delivering a massive 4x speed increase. Check it out and experience the performance boost yourself: trychroma.com/project/1.0.0 #ChromaDB #VectorDatabase #Rust #MachineLearning​​​​​​​​​​​​​​​​
Will try later 👍

Announcing Chroma DB C# SDK - .NET Blog Get started building AI applications using Chroma DB using the C# client SDK

Announcing Chroma DB C# SDK.

devblogs.microsoft.com/dotnet/announcing-chroma...

#dotnet #chromadb #ai #oss #database #csharp

@jtpae.bsky.social Which vector database do you like? #ChromaDB, #pgVector, #Pinecone, something else? I think ChromaDB is neat but from what I understand it doesn't have a way to scale easily, whereas I like that pgVector is based on #Postgres which has a long and stable history.

Dive into Retrieval-Augmented Generation (RAG) with Aman Soni, AI/ML Engineer.

Integrate private data with #LLMs using #LangChain, #ChromaDB & @OpenAI embeddings. A must-watch for devs building scalable #AI retrieval systems!

Going live at 7PM 🔗 www.youtube.com/watch?v=BxoA...

Awakari App

How to resolve the package dependency conflict in python? I am trying to do a LLM project. So cre...

stackoverflow.com/questions/79392225/how-t...

#python #python-3.x #pip #huggingface-transformers #chromadb

Event Attributes

เบากว่า คือ ต้องการทรัพยากรสำหรับรันโปรแกรมน้อย #vectordb #opensearch #chromadb #epsilla

#DevoxxGenie now supports #RAG based prompt context, powered by #ChromaDB, #Ollama, and #Nomic-Embed all running locally! Plus, try the new '/find' command to trigger semantic search exclusively within your project files 🧠 🧞‍♂️
🔥 Test it now 🔥
github.com/devoxx/Devox...

I keep trying, and failing, to create seamless vector database integration in #Perl. I almost got there with #ChromaDB, but everything I'm doing says, "write all of it in #Python and spin up a server that Perl can call."

(Before anyone asks, #PgVector isn't seamless)