Trending

So you wanna build a local RAG?

Show HN: Offline RAG System Using Docker and Llama 3 (No Cloud APIs)

Building a Simple Search Engine That Works

Word2Vec-style vector arithmetic on docs embeddings

The Parallel Search API

The Case Against PGVector

Syllabi – Open-source agentic AI with tools, RAG, and multi-channel deploy

Binary Retrieval-Augmented Reward Mitigates Hallucinations

Production RAG: what I learned from processing 5M+ documents

I'm in 9th grade and I built a "Mixture-of-LoRAs" architecture from scratch (Router + Experts + RAG) that runs on a single RTX 3060.

[D] I built a reasoning pipeline that boosts 8B models using structured routing + verification

From experience: best multi-agent systems for AI agents, RAG pipelines and more

Agentic RAG: from Zero to Hero

I worked on RAG for a $25B+ company (What I learnt & Challenges)

11 problems nobody talks about building Agents (and how to approach them)

Agentic RAG is mostly hype. Here's what I'm seeing.

[D] Measuring how similar a vector's neighbourhood (of vectors) is

Employ Different LLMs at Different Stages of an Agentic Workflow? 🤖

Liquid AI

Save item

LFM2-1.2B-RAG

Task: text-generation

Jina AI

Save item

jina-embeddings-v4

Task: visual-document-retrieval

mindsdb

Save item

mindsdb

Federated query engine for AI - The only MCP Server you'll ever need

langchain-ai

Save item

langchain

🦜🔗 The platform for reliable agents.

pathwaycom

Save item

pathway

Python ETL framework for stream processing, real-time analytics, LLM pipelines, and RAG.

run-llama

Save item

llama_index

LlamaIndex is the leading framework for building LLM-powered agents over your data.