Docling で PDF を Markdown に変換してみる

LLMのRAG精度、結局「PDFをどうMarkdown化するか」で決まるよね。

最近試したIBMの「Docling」、これかなりいい。レイアウト構造を保ったまま変換してくれるから、RAGの前処理がかなり楽になった。

特に表構造の認識が優秀。ドキュメント解析で消耗してる人は一度試してみて。

#AI #LLM #Python #RAG

https://zenn.dev/fukurou_labo/articles/f523b8c34fcf43

From zero to a #RAG system: successes and failures

https://en.andros.dev/bl

#LLM

Как помочь вашему RAG адаптироваться? Принимайте DRAG with KNEE! Часть 1 Все мы проходили через это: скармливаешь RAG...

#rag #knee #hierarchical #structure #optimization #retrieval #augmented #generation

Origin | Interest | Match

Coming up from @techupskills.bsky.social and @nofluffjuststuff.bsky.social in April, two of our most popular courses on Understanding #AI #agents & #AI for #app #development - create and deploy a full-featured AI chatbot with #RAG & #MCP! More details on our site getskillsnow.com and in the video!

Cog — Cognitive Architecture for Claude Code Cog is a cognitive architecture for Claude Code. Persistent memory, self-reflection, foresight, and scenario simulation — the first layer of continuous awareness for AI agents.

I have been looking for ways to better integrate my current experiences and recent memories into my AI work. This looks worth exploring.

lab.puga.com.br/cog/

#AI #memory #RAG

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/...

#324: Add a UI to the Python Friday RAG - Python Friday

#Python Friday #324: Add a UI to the Python Friday #RAG - #ai

pythonfriday.dev/2026/03/324-...

Building an Offline AI Interview Coach with Foundry Local, RAG, and SQLite | Microsoft Community Hub How to build a 100% offline, AI-powered interview preparation tool using Microsoft Foundry Local, Retrieval-Augmented Generation, and nothing but...

Building an Offline AI Interview Coach with Foundry Local, RAG, and SQLite | by Lee Stott

buff.ly/iLB1SCI

#ai #sqlite #foundrylocal #aimodels #rag #foundry

RAG Pipelines in Production: Vector Database Benchmarks, Chunking Strategies, and Hybrid Search Data 72% of enterprises run RAG in production. Qdrant hits 6ms p50 latency. Hybrid search boosts recall 17%. Compare Pinecone, Qdrant, Weaviate, ChromaDB with embedding model scores, chunking benchmarks, and deployment patterns.

RAG Pipelines in Production: Vector Database Benchmarks, Chunking Strategies, and Hybrid Search Data

72% of enterprises run RAG in production. Qdrant hits 6ms p50 latency. Hybrid search boosts …

#RAG #VectorDatabases #Pinecone

pooya.blog/blog/rag-pipelines-produ...

Email us - sales@nofeck.com
Contact Us - +919786070481
WhatsApp Us - zurl.co/nkXow
SMM - zurl.co/Ey7H8
#nofeck #aiagents #rag #crm #aipersonalassistant

RAG-бот на YandexGPT без Python и оркестраторов. Кейс внедрения «Яндекс Агента» в медицине Автоматизация клиентског...

#yandexgpt #чат-бот #rag #ai #php #wordpress #llm #нейросети

Origin | Interest | Match

Vocês já viram essa relíquia? Estava mostrando meus pôsteres do Ragnarok Online para os amigos ontem.

#ragnarok #ragnarokonline #rag

RAG vs Fine-Tuning - When to Use Each A practical guide to choosing between RAG and fine-tuning for your AI project, with cost comparisons, latency trade-offs, and a decision framework.

RAG vs Fine-Tuning - When to Use Each

https://awesomeagents.ai/guides/rag-vs-fine-tuning/

#Rag #FineTuning #Llm

What is RAG?
An AI technique that combines power of information retrieval with a LLM to enhance the accuracy and context-awareness of AI-generated answer.

more on comments:

#GenAI #RAG #AI #learn_in_public

PostagreSQL

PostgreSQL คืออะไร

อ่านต่อ : www.blockdit.com/posts/69c5ed...

#ShoperGamer #PostgreSQL #RDBMS #DataBase #SQL #NOSQL #VertorDB #RAG #OpenSource #Knowledge #Study #Feed

RAG vs Fine-Tuning - When to Use Each A practical guide to choosing between RAG and fine-tuning for your AI project, with cost comparisons, latency trade-offs, and a decision framework.

RAG vs Fine-Tuning - When to Use Each

https://awesomeagents.ai/guides/rag-vs-fine-tuning/

#Rag #FineTuning #Llm

Build an Offline Hybrid RAG Stack with ONNX and Foundry Local | Microsoft Community Hub If you are building local AI applications, basic retrieval augmented generation is often only the starting point. This sample shows a more practical...

Build an Offline Hybrid RAG Stack with ONNX and Foundry Local | by Lee Stott

techcommunity.microsoft.com/blog/educato...

#ai #onnx #rag #foundry #foundrylocal #softwaredev #javascript #npm

RAG вместо GPT: как мы сделали внутреннего ассистента для корпоративных данных В больших компаниях поиск почт...

#rag #корпоративная #архитектура #поиск #llm

Origin | Interest | Match

Готовим ИИ-агента к продакшену Всем привет! На связи Сергей Смирнов, действующий и практикующий AI-инженер. И...

#ии-агенты #rag #ai-agents #llm #agentic #ai #evaluation #observability #mcp

Origin | Interest | Match

doc brown from back to the future is making a funny face with his eyes closed . ALT: doc brown from back to the future is making a funny face with his eyes closed .

5 #RAG sur ma VM en parallèle… c'est déjà trop. Du coup, je sais ce que je fais faire à retraite quand la bulle aura explosé depuis longtemps et que cela sera l'heure du “Rétro-RAG Revival” le retour de la vengeance 3 :-)

IVF vs HNSW Indexing in Milvus

Modern AI apps—from semantic search to RAG pipelines—face one core challenge: finding the k most similar vectors across billions of embeddings in milliseconds.

#Milvus #RAG #database #opensource

Is your RAG system failing silently? Most demos look great, but production reveals a ticking time bomb of subtle errors. Learn why your data pipeline is the real culprit.

thepixelspulse.com/posts/rag-system-failure...

#rag #llm #ai

LlamaIndex 활용법과 강력한 대안 5가지 비교 분석 - 기술 덕후 한가닥 데이터의 홍수 속에서 우리가 가진 문서를 AI가 똑똑하게 읽게 만드는 것은 이제 필수 생존 기술이 되었습니다. LlamaIndex는 그중에서도 외부 데이터를 LLM과 매끄럽게 연결하는 핵심 프레임워크로 자리 잡았죠. 하지만 프로젝트의 성격에 따라 더 적합한 도구가 있을 수 있습니다.

LlamaIndex 활용법과 강력한 대안 5가지 비교 분석

https://bit.ly/3PZXJYc

#LlamaIndex #LLM 프론트엔드 #AI 데이터 처리 #RAG 구현 방법 #대안 프레임워크 #기술 블로그 #생존 기술

RAG Pipelines in Production: Vector Database Benchmarks, Chunking Strategies, and Hybrid Search Data 72% of enterprises run RAG in production. Qdrant hits 6ms p50 latency. Hybrid search boosts recall 17%. Compare Pinecone, Qdrant, Weaviate, ChromaDB with embedding model scores, chunking benchmarks, and deployment patterns.

RAG Pipelines in Production: Vector Database Benchmarks, Chunking Strategies, and Hybrid Search Data

72% of enterprises run RAG in production. Qdrant hits 6ms p50 latency. Hybrid search boosts …

#RAG #VectorDatabases #Pinecone

pooya.blog/blog/rag-pipelines-produ...

🚀 Building a Serverless RAG Pipeline on AWS (Without Losing Your Mind) RAG doesn't have to mean heavy infrastructure. In this post, I walk through how I built an end-to-end serverless RAG pipeline on AWS — from S3 ingestion to Bedrock-powered responses — sharing architecture decisions, cost tips, and IAM gotchas along the way.

"🚀 Building a Serverless RAG Pipeline on AWS (Without Losing Your Mind)" by Maitry Patel

#aws-serverless-application-repository #rag #aws-lambda #llm #amazon-bedrock

RAG Pipelines in Production: Vector Database Benchmarks, Chunking Strategies, and Hybrid Search Data 72% of enterprises run RAG in production. Qdrant hits 6ms p50 latency. Hybrid search boosts recall 17%. Compare Pinecone, Qdrant, Weaviate, ChromaDB with embedding model scores, chunking benchmarks, and deployment patterns.

RAG Pipelines in Production: Vector Database Benchmarks, Chunking Strategies, and Hybrid Search Data

72% of enterprises run RAG in production. Qdrant hits 6ms p50 latency. Hybrid search boosts …

#RAG #VectorDatabases #Pinecone

pooya.blog/blog/rag-pipelines-produ...

🧠 From SQL to Intelligence: Why the Future of Data is AI + Graphs + Agents Most modern data stacks are broken in a subtle way. Not because they lack tools — but because they...

🧠 From SQL to Intelligence: Why the Future of Data is AI + Graphs + Agents Most modern data stacks are broken in a subtle way. Not because they lack tools — but because they separate things th...

#graphrag #rag #ai #agents

Origin | Interest | Match

Best RAG Tools and Vector Databases in 2026 A practical comparison of six vector databases and two RAG frameworks, with real pricing and benchmark data to help you pick the right stack.

Best RAG Tools and Vector Databases in 2026

https://awesomeagents.ai/tools/best-ai-rag-tools-2026/

#Rag #VectorDatabases #Llamaindex

RAG та PDF: створюємо власний пошук по документам Створіть робочий RAG пайплайн для PDF. PyMuPDF, pdfplumber, Tesseract, EasyOCR і локальні або API-моделі для Q&A.

“Хочете швидко шукати відповіді в PDF? 📄 Наш повний гайд по RAG показує, як перетворювати документи на базу знань та ставити питання LLM ефективно. 👉 webscraft.org/blog/rag-dly... #RAG #AI #PDF”

AI agents are evolving fast—but their biggest bottleneck is still context management.

Today, we’ve published a deep dive on OpenViking, an open-source system that’s redefining how AI agents store, retrieve, and learn from information.

#RAG #opensource #aiagents