Skip to content

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.

👋 Sign in for the ability to sort posts by relevant, latest, or top.

David Mezzetti for NeuML

Jul 1 '22

Pictures are a worth a thousand words

#ai #llm #rag #vectordatabase

3 min read

David Mezzetti for NeuML

May 6 '22

Build a QA database

#ai #llm #rag #vectordatabase

3 min read

David Mezzetti for NeuML

Apr 20 '22

Query translation

#ai #llm #rag #vectordatabase

4 min read

David Mezzetti for NeuML

Mar 31 '22

Model explainability

#ai #llm #rag #vectordatabase

5 min read

David Mezzetti for NeuML

Mar 10 '22

Near duplicate image detection

#ai #llm #rag #vectordatabase

3 min read

David Mezzetti for NeuML

Mar 10 '22

Embeddings SQL custom functions

#ai #llm #rag #vectordatabase

4 min read

David Mezzetti for NeuML

Mar 2 '22

Anatomy of a txtai index

#ai #llm #rag #vectordatabase

7 min read

David Mezzetti for NeuML

Feb 10 '22

Push notifications with workflows

#ai #llm #rag #vectordatabase

7 min read

David Mezzetti for NeuML

Feb 3 '22

Workflow Scheduling

#ai #llm #rag #vectordatabase

6 min read

David Mezzetti for NeuML

Jan 26 '22

Entity extraction workflows

#ai #llm #rag #vectordatabase

3 min read

David Mezzetti for NeuML

Jan 26 '22

Generate image captions and detect objects

#ai #llm #rag #vectordatabase

2 min read

David Mezzetti for NeuML

Jan 6 '22

💡 What's new in txtai 4.0

#ai #llm #rag #vectordatabase

7 min read

David Mezzetti for NeuML

Jan 6 '22

Tensor workflows

#ai #llm #rag #vectordatabase

5 min read

David Mezzetti for NeuML

Nov 10 '21

Transform tabular data with composable workflows

#ai #llm #rag #vectordatabase

14 min read

David Mezzetti for NeuML

Oct 14 '21

Export and run other machine learning models

#ai #llm #rag #vectordatabase

6 min read

👋 Sign in for the ability to sort posts by relevant, latest, or top.