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.
"A Survey of LLM-based Deep Search Agents" (2026)
24p0748_arhamali_896c9e profile

"A Survey of LLM-based Deep Search Agents" (2026)

#agents #ai #llm #rag
Comments 1
2 min read
Pure semantic search missed 4 of 5 of my agent queries. Hybrid + parallel fan-out fixed it.
Cover image for Pure semantic search missed 4 of 5 of my agent queries. Hybrid + parallel fan-out fixed it.
reneza profile

Pure semantic search missed 4 of 5 of my agent queries. Hybrid + parallel fan-out fixed it.

#claudecode #rag #agents #ai
Comments
7 min read
Day 1 - RAG
indumathi_r_afd5683658092 profile

Day 1 - RAG

#ai #rag
Comments
3 min read
RAG Series (3): Tuning These 4 Parameters to Go From 'It Works' to 'It Works Well'
Cover image for RAG Series (3): Tuning These 4 Parameters to Go From 'It Works' to 'It Works Well'
wonderlab profile

RAG Series (3): Tuning These 4 Parameters to Go From 'It Works' to 'It Works Well'

#rag #chunk #vectordatabase #tuning
Comments
10 min read
Improving Determinism with LLMs: Prompting, Model Selection, Context, and Tools
Cover image for Improving Determinism with LLMs: Prompting, Model Selection, Context, and Tools
derrickpedranti profile

Improving Determinism with LLMs: Prompting, Model Selection, Context, and Tools

#ai #webdev #rag #promptengineering
1
Comments
7 min read
Lost-in-the-Middle Is Still Real in 2026 (Even on 1M-Token Models)
Cover image for Lost-in-the-Middle Is Still Real in 2026 (Even on 1M-Token Models)
gabrielanhaia profile

Lost-in-the-Middle Is Still Real in 2026 (Even on 1M-Token Models)

#ai #llm #rag #python
2
Comments
6 min read
RAG Series (4): Document Processing — From Raw Files to High-Quality Chunks
Cover image for RAG Series (4): Document Processing — From Raw Files to High-Quality Chunks
wonderlab profile

RAG Series (4): Document Processing — From Raw Files to High-Quality Chunks

#rag #ai #llm #chunk
Comments
7 min read
RAG Series (1): Why LLMs Need External Memory
Cover image for RAG Series (1): Why LLMs Need External Memory
wonderlab profile

RAG Series (1): Why LLMs Need External Memory

#llm #rag #ai #vectordatabase
Comments
7 min read
Hello World of RAG - Day 1
Cover image for Hello World of RAG - Day 1
gokul_kannan_1011 profile

Hello World of RAG - Day 1

#beginners #llm #ai #rag
Comments
6 min read
I published my first Python package — a reusable RAG core library
glemiu6 profile
Vlad

I published my first Python package — a reusable RAG core library

#ai #rag #python #opensource
Comments
1 min read
Stop Your RAG Pipeline From Hallucinating: A 15-Line Fix published
Cover image for Stop Your RAG Pipeline From Hallucinating: A 15-Line Fix published
agentoracle profile

Stop Your RAG Pipeline From Hallucinating: A 15-Line Fix published

#rag #ai #python #llm
Comments
9 min read
Local LLMs with PandasAI, Claude for Code Security & Jupyter Integration
soytuber profile
soy

Local LLMs with PandasAI, Claude for Code Security & Jupyter Integration

#ai #rag #automation
Comments
3 min read
VelesDB now has a Haystack connector - build a RAG pipeline with zero infrastructure
wiscale profile

VelesDB now has a Haystack connector - build a RAG pipeline with zero infrastructure

#ai #python #rag #tutorial
2
Comments
5 min read
AI is your Copilot, not to replace humans
amberitas17 profile

AI is your Copilot, not to replace humans

#ai #llm #rag #humanintheloop
Comments
3 min read
Building a RAG Evaluation Harness That Actually Catches Problems
Cover image for Building a RAG Evaluation Harness That Actually Catches Problems
shiva_shrestha_1b37675aab profile

Building a RAG Evaluation Harness That Actually Catches Problems

#rag #ai #python #llm
3
Comments
5 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.