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.
Multi-Tenant RAG in TypeScript: Keeping One Customer's AI Out of Another's Data
gabrielanhaia profile

Multi-Tenant RAG in TypeScript: Keeping One Customer's AI Out of Another's Data

#typescript #rag #security #postgres
1
Comments 1
5 min read
Ranking in TypeScript RAG: Why Cosine Similarity Alone Fails
gabrielanhaia profile

Ranking in TypeScript RAG: Why Cosine Similarity Alone Fails

#typescript #rag #ai #node
Comments
5 min read
Chunking Markdown in TypeScript: 5 Strategies and What Each Breaks
gabrielanhaia profile

Chunking Markdown in TypeScript: 5 Strategies and What Each Breaks

#typescript #rag #markdown #node
Comments
6 min read
Caching Embeddings in Node: A 60-Line Layer That Cuts the Bill
gabrielanhaia profile

Caching Embeddings in Node: A 60-Line Layer That Cuts the Bill

#typescript #node #rag #ai
Comments
5 min read
OpenAI Just Solved a Problem Open Since 1999. It Still Can't Ask Its Own Question.

Verified by top mathematicians for $2k
dannwaneri profile

OpenAI Just Solved a Problem Open Since 1999. It Still Can't Ask Its Own Question.

#ai #llm #openai #rag
25
Comments 14
4 min read
LangChain + OpenAI-Compatible APIs: Debug Base URL Before RAG or Agents
edward_li_71f26791eac62b8 profile

LangChain + OpenAI-Compatible APIs: Debug Base URL Before RAG or Agents

#ai #langchain #rag #python
Comments
3 min read
Practical RAG, Part 1: The Simplest RAG That Actually Works
sumanpro profile

Practical RAG, Part 1: The Simplest RAG That Actually Works

#rag #python #llm #ai
Comments
5 min read
OpenSparrow v3.1 - RAG assistant, Record Image Galleries, and Workflow Stored Procedures
wrobeltomasz profile
Tomasz

OpenSparrow v3.1 - RAG assistant, Record Image Galleries, and Workflow Stored Procedures

#php #lowcode #rag #opensource
4
Comments 3
3 min read
RAG Without Vectors: How LLMs Are Learning to Navigate Documents Like Humans
shrividya_hegde profile

RAG Without Vectors: How LLMs Are Learning to Navigate Documents Like Humans

#ai #architecture #llm #rag
Comments
6 min read
Dify + OpenAI-Compatible APIs: Test the Provider Before the Workflow
edward_li_71f26791eac62b8 profile

Dify + OpenAI-Compatible APIs: Test the Provider Before the Workflow

#ai #dify #rag #openai
Comments
3 min read
RAG en entreprise : ce que j'ai appris en le déployant chez un industriel (REX)
victorjaikin profile

RAG en entreprise : ce que j'ai appris en le déployant chez un industriel (REX)

#ai #rag #llm #machinelearning
Comments
4 min read
AutoRAG vs RAGBuilder vs Red Hat AutoRAG: Which RAG Pipeline Wins on YOUR Data (and Their Shared OCR Blind Spot)
ahmetozel profile

AutoRAG vs RAGBuilder vs Red Hat AutoRAG: Which RAG Pipeline Wins on YOUR Data (and Their Shared OCR Blind Spot)

#rag #ai #llm #opensource
1
Comments
3 min read
RAG Retrieval Gotchas at Scale: Insights and Solutions
the-hive-collective profile

RAG Retrieval Gotchas at Scale: Insights and Solutions

#rag #retrieval #scalability #ai
1
Comments
2 min read
Polling Async Web Data Jobs Without Burning Your API Quota
anakin_writers profile
Anakin

Polling Async Web Data Jobs Without Burning Your API Quota

#rag #webscraping #architecture #async
Comments
4 min read
RAG vs. Agentic RAG vs. Graph RAG: Which One Actually Fits Your Use Case?
tienbku profile

RAG vs. Agentic RAG vs. Graph RAG: Which One Actually Fits Your Use Case?

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