Forem

# rag

Retrieval augmented generation, or RAG, is an architectural approach that can improve the efficacy of large language model (LLM) applications by leveraging custom data.

Posts

đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.
Upgrading Kiwi-chan’s Brain: Pushing a 30GB "Frankenstein" GPU Rig to the Limit with Qwen 3.6-35B-A3B

Upgrading Kiwi-chan’s Brain: Pushing a 30GB "Frankenstein" GPU Rig to the Limit with Qwen 3.6-35B-A3B

Comments
4 min read
LLMs for Workflow Automation, Agent Orchestration & Enhanced Code Review

LLMs for Workflow Automation, Agent Orchestration & Enhanced Code Review

Comments
3 min read
When the Reranker Hurts: Recall@5 Cases Where Two-Stage Retrieval Loses to One
Cover image for When the Reranker Hurts: Recall@5 Cases Where Two-Stage Retrieval Loses to One

When the Reranker Hurts: Recall@5 Cases Where Two-Stage Retrieval Loses to One

Comments
7 min read
RAG Without Embeddings: When BM25 Beats Your $0.20-per-1K Vector Index
Cover image for RAG Without Embeddings: When BM25 Beats Your $0.20-per-1K Vector Index

RAG Without Embeddings: When BM25 Beats Your $0.20-per-1K Vector Index

Comments
7 min read
Cosine Similarity Lies. Here's What to Use When Your Embeddings All Cluster at 0.85
Cover image for Cosine Similarity Lies. Here's What to Use When Your Embeddings All Cluster at 0.85

Cosine Similarity Lies. Here's What to Use When Your Embeddings All Cluster at 0.85

Comments
7 min read
Start With Context: Building the Retrieval Core for Agentic Apps
Cover image for Start With Context: Building the Retrieval Core for Agentic Apps

Start With Context: Building the Retrieval Core for Agentic Apps

Comments
8 min read
Beyond Basic RAG: Architecting a Fault-Tolerant, Agentic AI Platform

Beyond Basic RAG: Architecting a Fault-Tolerant, Agentic AI Platform

Comments
5 min read
pdfmux vs LlamaParse vs Docling vs Unstructured: Which PDF extractor for RAG in 2026?

pdfmux vs LlamaParse vs Docling vs Unstructured: Which PDF extractor for RAG in 2026?

Comments
10 min read
How We Automated Hallucination Detection in Enterprise RAG Pipelines
Cover image for How We Automated Hallucination Detection in Enterprise RAG Pipelines

How We Automated Hallucination Detection in Enterprise RAG Pipelines

Comments
1 min read
I Built an AI Chatbot Into My Portfolio Website Using AWS Bedrock — Here's Exactly How
Cover image for I Built an AI Chatbot Into My Portfolio Website Using AWS Bedrock — Here's Exactly How

I Built an AI Chatbot Into My Portfolio Website Using AWS Bedrock — Here's Exactly How

1
Comments
10 min read
RAG vs MCP is the wrong debate — here's the right framing for production AI systems

RAG vs MCP is the wrong debate — here's the right framing for production AI systems

Comments
4 min read
Build a RAG System in Python (Without Overcomplicating It)

Build a RAG System in Python (Without Overcomplicating It)

Comments
2 min read
When NOT to use RAG (lessons from building a Claude-powered support bot)
Cover image for When NOT to use RAG (lessons from building a Claude-powered support bot)

When NOT to use RAG (lessons from building a Claude-powered support bot)

Comments
4 min read
Optimizing LLM Workflows: Claude for Evaluation, Blender Integration & Token Efficiency

Optimizing LLM Workflows: Claude for Evaluation, Blender Integration & Token Efficiency

Comments
3 min read
40 Days Training on RAG

40 Days Training on RAG

Comments
2 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.