Observed Signal · Jun 23, 2026 · Technical Release · Source: DEV Community · Impact: 4/5 · Sentiment: Positive
Azure Cosmos DB launches Integrated Embeddings Public Preview
Microsoft announced the public preview of Integrated Embeddings for Azure Cosmos DB, a feature that automatically generates and maintains vector embeddings as items are inserted or updated. Developers configure embeddings via a new embeddingSource block in the container vector policy, selecting source properties, a Microsoft Foundry embedding model deployment, and an output vector path. The preview supports Azure OpenAI embedding models deployed through Microsoft Foundry (text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002) and uses Microsoft Entra authentication. Initial SDK support includes the Azure Cosmos DB SDK (Python) with key-based auth and the management SDK (Python/JavaScript) with Entra ID; Azure Portal configuration is not yet available. Microsoft provides a sample Python app and a LangChain-based RAG walkthrough. Costs are limited to Foundry inference calls and Cosmos DB request units for change-feed reads/writes.
A major cloud provider (Microsoft) has integrated automatic embedding generation into a widely used database (Azure Cosmos DB), lowering engineering overhead for vector search, RAG applications and data-sync pipelines — a notable infrastructure change for AI-driven application development.
Track Microsoft Signals & Market Shifts in Real-Time
Polaris7 autonomous intelligence agents track regulatory filings, primary sources, executive changes, and deal flow 24/7. Create your free Explorer workspace to monitor these entities.
Key Takeaways & Evidence Grounding
- Azure Cosmos DB announced Integrated Embeddings in Public Preview.
- Integrated Embeddings automatically generates and updates item embeddings on writes/updates using a configured embeddingSource in the container vector policy.
- Supported Microsoft Foundry embedding models in preview: text-embedding-3-small, text-embedding-3-large, text-embedding-ada-002.
- Authentication for Integrated Embeddings currently supports Entra ID; SDK configuration available via Azure Cosmos DB SDK (Python) and management SDK (Python/JavaScript); Azure Portal support coming later.
- Microsoft published a sample Python app and a LangChain RAG example demonstrating vector search against embeddings generated by Integrated Embeddings.
Connected Companies & Entities
3 Entities mappedOntology Mapping & Concepts
Related Market Signals & Shifts
Recent verified developments and strategic activity across this market segment.
Microsoft Open-Sources OmniVec Embedding Platform
Microsoft (Azure Cosmos DB team) open-sourced OmniVec, a platform to build and operate embedding pipelines that keep vector representations of operational data in sync. OmniVec lets users register sources, embedding models, destinations (vector stores) and pipelines; it handles backfill, change tracking, model invocation, retries and writes to vector stores. The release includes support for Azure Cosmos DB, PostgreSQL, SQL Server (source and destination) and Azure Blob Storage (destination). OmniVec is deployed into an Azure subscription and provisions AKS, an Azure Cosmos DB metadata store and an ACR; it can call hosted Azure OpenAI models or self-hosted GPU models. The project is available on GitHub (AzureCosmosDB/OmniVec) and is published as a public preview.
Azure Cosmos DB vNext Emulator Reaches General Availability
Microsoft announced the general availability of the Azure Cosmos DB vNext emulator, distributed as a Docker image that runs on Linux, macOS and Windows for both x64 and ARM64. The GA emulator includes an embedded Azure Cosmos DB Shell, broader API/feature coverage (change feed, batch ops, JOINs, hierarchical partition keys, TTL, etc.), vector search support (with vectorEmbeddingPolicy, VectorDistance() queries and DiskANN index), OpenTelemetry (OTLP) exporters, and dedicated health probe endpoints. The image enables local development, CI integration tests, and local RAG/semantic-search AI workflows without an Azure subscription. The GA image is available from mcr.microsoft.com/cosmosdb/linux/azure-cosmos-emulator:vnext-latest and the project hosts docs and examples (including a GitHub repo and sample using LangChain and Ollama for embeddings).
NeuroLink TypeScript Guide: embed() and embedMany()
This technical guide explains how to build semantic search in TypeScript using NeuroLink's embed() and embedMany() APIs to generate vector embeddings and run similarity search. NeuroLink (the @juspay/neurolink SDK) supports multiple embedding providers — OpenAI, Google AI Studio, Google Vertex, and Amazon Bedrock — and lets developers override models per call. The post demonstrates single and batched embedding calls, an in-memory vector store example, recommended integration patterns with vector databases (e.g., Pinecone, Weaviate, ChromaDB), and NeuroLink's RAG convenience feature (rag: { files }) that automatically handles chunking, embedding and retrieval for retrieval-augmented generation workflows. The article includes code samples, installation links, and pointers to the GitHub repo and documentation.
Track Real-Time Market Signals & Shifts
Set up custom watchlists to receive automated, evidence-grounded executive digests whenever material signals or shifts occur across your tracked landscape.