From 6be3ddc92e21aab1dd3b028722b5a497463a1248 Mon Sep 17 00:00:00 2001 From: David Myriel Date: Thu, 21 Nov 2024 16:48:40 -0800 Subject: [PATCH] Update qdrant-landing/content/documentation/data-ingestion-beginners.md Co-authored-by: Anush --- .../content/documentation/data-ingestion-beginners.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/qdrant-landing/content/documentation/data-ingestion-beginners.md b/qdrant-landing/content/documentation/data-ingestion-beginners.md index f00c3e6ad..0d4293f3a 100644 --- a/qdrant-landing/content/documentation/data-ingestion-beginners.md +++ b/qdrant-landing/content/documentation/data-ingestion-beginners.md @@ -17,7 +17,7 @@ In this tutorial, we’ll create a streamlined data ingestion pipeline, pulling ## Ingestion Workflow Architecture -In this workflow, we’ll set up a powerful document ingestion and analysis pipeline using cloud storage, natural language processing (NLP) tools, and embedding technologies. Starting with raw data in an S3 bucket, we'll preprocess it with LangChain, apply embedding APIs for both text and images, and store the results in Qdrant – a vector database optimized for similarity search. +We’ll set up a powerful document ingestion and analysis pipeline in this workflow using cloud storage, natural language processing (NLP) tools, and embedding technologies. Starting with raw data in an S3 bucket, we'll preprocess it with LangChain, apply embedding APIs for both text and images and store the results in Qdrant – a vector database optimized for similarity search. **Figure 1: Data Ingestion Workflow Architecture**