DEV Community

#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.
I Built an AI Chatbot That Knows Everything About Me
akromdev profile

I Built an AI Chatbot That Knows Everything About Me

#ai #rag #typescript #tutorial
Comments
6 min read
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 1
5 min read
Embeddings on the Edge: sentence-transformers vs Hosted APIs
gabrielanhaia profile

Embeddings on the Edge: sentence-transformers vs Hosted APIs

#rag #embeddings #ai #python
1
Comments
8 min read
Introducing HCEL: The Most Fluent Way to Build AI Pipelines in TypeScript
arslan_mecom profile

Introducing HCEL: The Most Fluent Way to Build AI Pipelines in TypeScript

#ai #llm #rag #typescript
5
Comments
7 min read
Beyond Static RAG: Using 1958 Biochemistry to Beat Multi-Hop Retrieval by 14%
emilcelestix profile
Emil

Beyond Static RAG: Using 1958 Biochemistry to Beat Multi-Hop Retrieval by 14%

#machinelearning #ai #python #rag
Comments
2 min read
RAG Evaluation Beyond Recall@K: Faithfulness, Coverage, Robustness
gabrielanhaia profile

RAG Evaluation Beyond Recall@K: Faithfulness, Coverage, Robustness

#ai #rag #llm #observability
Comments
9 min read
Caching Pre-Computed Embeddings: TTL, Versioning, and the Cold-Start Problem
gabrielanhaia profile

Caching Pre-Computed Embeddings: TTL, Versioning, and the Cold-Start Problem

#rag #ai #embeddings #python
Comments
8 min read
RAG Series (7): Retrieval Strategies — How to Find the Most Relevant Content
wonderlab profile

RAG Series (7): Retrieval Strategies — How to Find the Most Relevant Content

#rag #ai #mmr #llm
Comments
7 min read
Beyond RAG: Building Graph-Aware Retrieval for Contract Reasoning
pyalwin profile

Beyond RAG: Building Graph-Aware Retrieval for Contract Reasoning

#ai #rag #opensource #database
Comments
12 min read
Stop Drowning in Vectors: How I Built a Graph-Powered RAG That Actually Scales
tejas1233 profile

Stop Drowning in Vectors: How I Built a Graph-Powered RAG That Actually Scales

#ai #rag #python #neo4j
5
Comments
3 min read
RAG Re-Indexing Without Downtime: A Dual-Write Pattern for Embeddings
gabrielanhaia profile

RAG Re-Indexing Without Downtime: A Dual-Write Pattern for Embeddings

#rag #ai #postgres #python
1
Comments
8 min read
Why Your Vector Index Returns Five Copies of the Same Doc
gabrielanhaia profile

Why Your Vector Index Returns Five Copies of the Same Doc

#rag #ai #embeddings #python
Comments
7 min read
Embedding Drift Detection: A 50-Line Monitor for Production RAG
gabrielanhaia profile

Embedding Drift Detection: A 50-Line Monitor for Production RAG

#rag #ai #observability #python
Comments
6 min read
Why RAG Falls Short for Documentation Search (and What to Try Instead)
alanwest profile

Why RAG Falls Short for Documentation Search (and What to Try Instead)

#ai #rag #llm #python
1
Comments
5 min read
RAG Series (6): Vector Databases — Storage and Retrieval Infrastructure
wonderlab profile

RAG Series (6): Vector Databases — Storage and Retrieval Infrastructure

#rag #vectordatabase #qdrant #ai
Comments
7 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.