Merge pull request #272551 from wmwxwa/patch-20

prmerger-automator[bot] · web-flow · commit e9007c45a5f5 · 2024-04-18T02:40:33.000Z
Update vector-database.md
diff --git a/articles/cosmos-db/vector-database.md b/articles/cosmos-db/vector-database.md
@@ -35,7 +35,7 @@ A pure vector database is designed to efficiently store and manage vector embedd
 
 A vector database that is integrated in a highly performant NoSQL or relational database provides additional capabilities. The integrated vector database in a NoSQL or relational database can store, index, and query embeddings alongside the corresponding original data. This approach eliminates the extra cost of replicating data in a separate pure vector database. Moreover, keeping the vector embeddings and original data together better facilitates multi-modal data operations, and enables greater data consistency, scale, and performance.
 
-## What are some vector database use cases?
+### Vector database use cases
 
 Vector databases are used in numerous domains and situations across analytical and generative AI, including natural language processing, video and image recognition, recommendation system, search, etc. For example, you can use a vector database to:
 
@@ -78,11 +78,11 @@ A prompt refers to a specific text or information that can serve as an instructi
 - Cues: direct the LLM's output in the right direction
 - Supporting content: represents supplemental information the LLM can use to generate output
 
-The process of creating good prompts for a scenario is called prompt engineering. For more information about prompts and best practices for prompt engineering, see Azure OpenAI Service [prompt engineering techniques](../ai-services/openai/concepts/advanced-prompt-engineering.md). [[Go back](#what-are-some-vector-database-use-cases)]
+The process of creating good prompts for a scenario is called prompt engineering. For more information about prompts and best practices for prompt engineering, see Azure OpenAI Service [prompt engineering techniques](../ai-services/openai/concepts/advanced-prompt-engineering.md). [[Go back](#vector-database-use-cases)]
 
 ### Tokens
 
-Tokens are small chunks of text generated by splitting the input text into smaller segments. These segments can either be words or groups of characters, varying in length from a single character to an entire word. For instance, the word hamburger would be divided into tokens such as ham, bur, and ger while a short and common word like pear would be considered a single token. LLMs like ChatGPT, GPT-3.5, or GPT-4 break words into tokens for processing. [[Go back](#what-are-some-vector-database-use-cases)]
+Tokens are small chunks of text generated by splitting the input text into smaller segments. These segments can either be words or groups of characters, varying in length from a single character to an entire word. For instance, the word hamburger would be divided into tokens such as ham, bur, and ger while a short and common word like pear would be considered a single token. LLMs like ChatGPT, GPT-3.5, or GPT-4 break words into tokens for processing. [[Go back](#vector-database-use-cases)]
 
 ### Retrieval-augmented generation
 
@@ -97,20 +97,17 @@ A simple RAG pattern using Azure Cosmos DB for NoSQL could be:
 5.	Create a function to perform vector similarity search based on a user prompt
 6.	Perform question answering over the data using an Azure OpenAI Completions model
 
-The RAG pattern, with prompt engineering, serves the purpose of enhancing response quality by offering more contextual information to the model. RAG enables the model to apply a broader knowledge base by incorporating relevant external sources into the generation process, resulting in more comprehensive and informed responses. For more information on "grounding" LLMs, see [grounding LLMs](https://techcommunity.microsoft.com/t5/fasttrack-for-azure/grounding-llms/ba-p/3843857). [[Go back](#what-are-some-vector-database-use-cases)]
+The RAG pattern, with prompt engineering, serves the purpose of enhancing response quality by offering more contextual information to the model. RAG enables the model to apply a broader knowledge base by incorporating relevant external sources into the generation process, resulting in more comprehensive and informed responses. For more information on "grounding" LLMs, see [grounding LLMs](https://techcommunity.microsoft.com/t5/fasttrack-for-azure/grounding-llms/ba-p/3843857). [[Go back](#vector-database-use-cases)]
 
 Here are multiple ways to implement RAG on your data by using our integrated vector database functionalities:
 
 ## How to implement integrated vector database functionalities
 
 You can implement integrated vector database functionalities for the following [Azure Cosmos DB APIs](choose-api.md):
 
-> [!NOTE]
-> For our NoSQL API, the native integration of a state-of-the-art vector indexing algorithm will be announced during Build in May 2024. Please stay tuned.
-
 ### API for MongoDB
 
-Use the natively [integrated vector database in Azure Cosmos DB for MongoDB](mongodb/vcore/vector-search.md), which 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.
+Use the natively [integrated vector database in Azure Cosmos DB for MongoDB](mongodb/vcore/vector-search.md) (vCore architecture), which 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.
 
 #### Code samples
 
@@ -122,6 +119,9 @@ Use the natively [integrated vector database in Azure Cosmos DB for MongoDB](mon
 - [Python notebook tutorial - LLM Caching integration through LangChain](https://python.langchain.com/docs/integrations/llms/llm_caching#azure-cosmos-db-semantic-cache)
 - [Python - LlamaIndex integration](https://docs.llamaindex.ai/en/stable/examples/vector_stores/AzureCosmosDBMongoDBvCoreDemo.html)
 - [Python - Semantic Kernel memory integration](https://github.com/microsoft/semantic-kernel/tree/main/python/semantic_kernel/connectors/memory/azure_cosmosdb)
+
+> [!div class="nextstepaction"]
+> [Use Azure Cosmos DB for MongoDB lifetime free tier](mongodb/vcore/free-tier.md)
   
 ### API for PostgreSQL
 
@@ -133,6 +133,9 @@ Use the natively integrated vector database in [Azure Cosmos DB for PostgreSQL](
 
 ### NoSQL API
 
+> [!NOTE]
+> For our NoSQL API, the native integration of a state-of-the-art vector indexing algorithm will be announced during Build in May 2024. Please stay tuned.
+
 The natively integrated vector databaseg in the NoSQL API is under development. In the meantime, you may implement RAG patterns with Azure Cosmos DB for NoSQL and [Azure AI Search](../search/vector-search-overview.md). This approach enables powerful integration of your data residing in the NoSQL API into your AI-oriented applications.
 
 #### Code samples
@@ -143,7 +146,7 @@ The natively integrated vector databaseg in the NoSQL API is under development.
 - [.NET tutorial - recipe chatbot w/ Semantic Kernel](https://github.com/microsoft/AzureDataRetrievalAugmentedGenerationSamples/tree/main/C%23/CosmosDB-NoSQL_CognitiveSearch_SemanticKernel)
 - [Python notebook tutorial - Azure product chatbot](https://github.com/microsoft/AzureDataRetrievalAugmentedGenerationSamples/tree/main/Python/CosmosDB-NoSQL_CognitiveSearch)
   
-## Next step
+### Next step
 
 [30-day Free Trial without Azure subscription](https://azure.microsoft.com/try/cosmosdb/)
 
