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.
Extractive QA to build structured data

Extractive QA to build structured data

8
Comments
3 min read
Train a QA model

Train a QA model

9
Comments 1
3 min read
Export and run models with ONNX

Export and run models with ONNX

11
Comments
12 min read
Train a text labeler

Train a text labeler

9
Comments
2 min read
Train without labels

Train without labels

8
Comments
3 min read
Distributed embeddings cluster

Distributed embeddings cluster

5
Comments
5 min read
Extract text from documents

Extract text from documents

9
Comments
7 min read
Translate text between languages

Translate text between languages

9
Comments 4
4 min read
Run pipeline workflows

Run pipeline workflows

9
Comments
6 min read
Transcribe audio to text

Transcribe audio to text

10
Comments 1
3 min read
Similarity search with images

Similarity search with images

10
Comments
4 min read
Building abstractive text summaries

Building abstractive text summaries

11
Comments
3 min read
Tutorial series on txtai

Tutorial series on txtai

25
Comments
11 min read
Add semantic search to Elasticsearch

Add semantic search to Elasticsearch

13
Comments
7 min read
txtai API Gallery

txtai API Gallery

5
Comments 2
6 min read
đź‘‹ Sign in for the ability to sort posts by relevant, latest, or top.