Merge pull request #270714 from wmwxwa/patch-8

Move up related concepts pt 1.md

Author: prmerger-automator[bot]

articles/cosmos-db/vector-database.md

@@ -52,6 +52,16 @@ It's especially popular to use vector databases to enable [retrieval-augmented g
 
 This process involves extracting pertinent information from a custom data source and integrating it into the model request through prompt engineering. Before sending a request to the LLM, the user input/query/request is also transformed into an embedding, and vector search techniques are employed to locate the most similar embeddings within the database. This technique enables the identification of the most relevant data records in the database. These retrieved records are then supplied as input to the LLM request using [prompt engineering](#prompts-and-prompt-engineering).
 
+## Vector database related concepts
+
+### Embeddings
+
+An embedding is a special format of data representation that machine learning models and algorithms can easily use. The embedding is an information dense representation of the semantic meaning of a piece of text. Each embedding is a vector of floating-point numbers, such that the distance between two embeddings in the vector space is correlated with semantic similarity between two inputs in the original format. For example, if two texts are similar, then their vector representations should also be similar. A vector database extension that allows you to store your embeddings with your original data ensures data consistency, scale, and performance.
+
+### Vector search
+
+Vector search is a method that helps you find similar items based on their data characteristics rather than by exact matches on a property field. This technique is useful in applications such as searching for similar text, finding related images, making recommendations, or even detecting anomalies. It works by taking the vector representations (lists of numbers) of your data that you created by using a machine learning model by using an embeddings API, such as [Azure OpenAI Embeddings](../ai-services/openai/how-to/embeddings.md) or [Hugging Face on Azure](https://azure.microsoft.com/solutions/hugging-face-on-azure). It then measures the distance between the data vectors and your query vector. The data vectors that are closest to your query vector are the ones that are found to be most similar semantically. Using a native vector search feature offers an efficient way to store, index, and search high-dimensional vector data directly alongside other application data. This approach removes the necessity of migrating your data to costlier alternative vector databases and provides a seamless integration of your AI-driven applications.
+
 Here are multiple ways to implement RAG on your data by using our vector database functionalities:
 
 ## How to implement integrated vector database functionalities
@@ -99,16 +109,6 @@ The natively integrated vector database in our NoSQL API will become available i
 > [!div class="nextstepaction"]
 > [Use the Azure Cosmos DB lifetime free tier](free-tier.md)
 
-## Vector database related concepts
-
-### Embeddings
-
-An embedding is a special format of data representation that machine learning models and algorithms can easily use. The embedding is an information dense representation of the semantic meaning of a piece of text. Each embedding is a vector of floating-point numbers, such that the distance between two embeddings in the vector space is correlated with semantic similarity between two inputs in the original format. For example, if two texts are similar, then their vector representations should also be similar. A vector database extension that allows you to store your embeddings with your original data ensures data consistency, scale, and performance.
-
-### Vector search
-
-Vector search is a method that helps you find similar items based on their data characteristics rather than by exact matches on a property field. This technique is useful in applications such as searching for similar text, finding related images, making recommendations, or even detecting anomalies. It works by taking the vector representations (lists of numbers) of your data that you created by using a machine learning model by using an embeddings API, such as [Azure OpenAI Embeddings](../ai-services/openai/how-to/embeddings.md) or [Hugging Face on Azure](https://azure.microsoft.com/solutions/hugging-face-on-azure). It then measures the distance between the data vectors and your query vector. The data vectors that are closest to your query vector are the ones that are found to be most similar semantically. Using a native vector search feature offers an efficient way to store, index, and search high-dimensional vector data directly alongside other application data. This approach removes the necessity of migrating your data to costlier alternative vector databases and provides a seamless integration of your AI-driven applications.
-
 ### Retrieval-augmented generation
 
 Retrieval-augmentated generation (RAG) is an architecture that augments the capabilities of LLMs like ChatGPT, GPT-3.5, or GPT-4 by adding an information retrieval system like vector search that provides grounding data, such as those stored in a vector database. This approach allows your LLM to generate contextually relevant and accurate responses based on your custom data sourced from vectorized documents, images, audio, video, etc.