Add RAG alias for Extractor, closes #732

neuml · Jun 18, 2024 · 42583f0 · 42583f0
1 parent 19961f0
commit 42583f0
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 2 deletions.
diff --git a/docs/pipeline/text/extractor.md b/docs/pipeline/text/extractor.md
@@ -3,7 +3,7 @@
 ![pipeline](../../images/pipeline.png#only-light)
 ![pipeline](../../images/pipeline-dark.png#only-dark)
 
-The Extractor pipeline joins a prompt, context data store and generative model together to extract knowledge.
+The Extractor pipeline (aka RAG) joins a prompt, context data store and generative model together to extract knowledge.
 
 The data store can be an embeddings database or a similarity instance with associated input text. The generative model can be a prompt-driven large language model (LLM), an extractive question-answering model or a custom pipeline. This is known as prompt-driven search or retrieval augmented generation (RAG).
 

diff --git a/src/python/txtai/__init__.py b/src/python/txtai/__init__.py
@@ -7,7 +7,7 @@
 # Top-level imports
 from .app import Application
 from .embeddings import Embeddings
-from .pipeline import LLM
+from .pipeline import LLM, RAG
 
 # Configure logging per standard Python library recommendations
 logger = logging.getLogger(__name__)

diff --git a/src/python/txtai/pipeline/__init__.py b/src/python/txtai/pipeline/__init__.py
@@ -12,5 +12,6 @@
 from .llm import *
 from .nop import Nop
 from .text import *
+from .text import Extractor as RAG
 from .tensors import Tensors
 from .train import *