# Firestore Firestore is a serverless NoSQL document database for storing, synchronizing, and querying application data, with SDKs, security rules, and real-time capabilities. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Authentication made easy: Building a secure e-commerce shopping cart with Firebase DevFeed: [Authentication made easy: Building a secure e-commerce shopping cart with Firebase]() Original publisher: [Read original article]() Author: Karl Weinmeister Published: 2026-09-01T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Authentication](), [Firebase](), [Firestore](), [Authorization](), [Security]() Tags: [authentication](), [cloud-run](), [e-commerce](), [firebase](), [firestore](), [security-rules](), [shopping](), [tutorials](), [web]() ### AI overview This tutorial explains how to build a secure e-commerce shopping cart with Firebase Authentication and Cloud Firestore. It covers guest onboarding through anonymous authentication, migration of guest carts to permanent accounts, real-time synchronization, and checkout while addressing database permissions and security. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Triple-layer security for Firebase web apps DevFeed: [Triple-layer security for Firebase web apps]() Original publisher: [Read original article]() Author: Roger Martinez Published: 2026-07-30T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Security](), [Web app](), [Firestore]() Tags: [app-check](), [apps](), [article](), [cloud-functions](), [firebase](), [firestore](), [security](), [security-rules](), [tutorials](), [web](), [web-apps]() ### AI overview This tutorial explains three layers of security for Firebase web apps: Firebase Security Rules, Google Cloud service accounts, and Firebase App Check. It focuses on narrowing Firestore rules by resource, allowed operations, and client identity, including a rule that limits reads to published articles. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Zero-flicker Firestore SSR with React DevFeed: [Zero-flicker Firestore SSR with React]() Original publisher: [Read original article]() Author: Jeff Huleatt Published: 2026-06-24T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Firestore](), [Server-side rendering](), [React](), [Next.js](), [web applications]() Tags: [firebase](), [firestore](), [next-js](), [react](), [real-time](), [serialization](), [server-side-rendering](), [ssr](), [web](), [web-app]() ### AI overview This tutorial explains how to use Firebase JS SDK SSR-specific APIs to serialize Firestore query results on the server, resume them on the client, and support realtime updates in a Next.js and React application. It also discusses payload size and when serialization is unnecessary. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Live text search with Firestore pipelines and React DevFeed: [Live text search with Firestore pipelines and React]() Original publisher: [Read original article]() Author: Jeff Huleatt Published: 2026-05-28T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Firestore](), [React](), [Firebase](), [web applications](), [TypeScript]() Tags: [firebase](), [firestore](), [full-text-search](), [javascript](), [react](), [typescript](), [web](), [web-app]() ### AI overview This tutorial explains how to implement text search in a React web app using Firestore Enterprise text indexes and pipelines. It covers a reusable search-results component, React Suspense with TanStack Query, search on form submission, and debounced live search. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Building Svitgrid, a Solar Monitoring Platform for Home Systems DevFeed: [Building Svitgrid, a Solar Monitoring Platform for Home Systems]() Original publisher: [Read original article]() Author: Ivan Ursul Published: 2026-05-21T00:00:00Z Content type: article Language: en Sources: [Ivan Ursul]() Topics: [Monitoring](), [dashboards](), [real-time](), [Fastify](), [Flutter](), [Modbus](), [TypeScript](), [Cloud Run](), [ESP-IDF](), [ESP32-S3](), [Firestore](), [Mobile]() Tags: [android](), [battery](), [cloud-run](), [energy-monitoring](), [esp-idf](), [esp32](), [esp32-s3](), [firestore](), [flutter](), [gcp](), [iot](), [java](), [migrations](), [mobile](), [modbus](), [mongodb](), [monitoring](), [real-time](), [side-project](), [solar](), [typescript](), [web]() ### AI overview This article explains how Svitgrid, a solar monitoring platform for residential systems, was built. It covers the product's goals, cross-platform clients, cloud backend, ESP32-S3 edge hardware, inverter data paths, and support for multiple inverter systems over Modbus TCP. ### Source excerpt Svitgrid dashboard: real-time power flow from PV to battery, home, and grid ## Firestore adds generally available pipeline operations with full-text search, JOINs, geospatial queries, and data manipulation DevFeed: [Firestore adds generally available pipeline operations with full-text search, JOINs, geospatial queries, and data manipulation]() Original publisher: [Read original article]() Author: Morgan Chen; Minh Nguyen Published: 2026-04-27T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firestore](), [NoSQL](), [Database](), [Serverless](), [serverless architecture]() Tags: [database](), [firebase](), [firestore](), [full-text-search](), [geo-queries](), [geospatial](), [javascript](), [nosql](), [real-time](), [serverless](), [serverless-architecture]() ### AI overview Firestore pipeline operations reached general availability on the enterprise edition, adding full-text search, geospatial queries, JOIN capabilities through subqueries, and data manipulation while retaining Firestore's NoSQL and serverless features. ### Source excerpt With support for full-text search, joins, and geospatial queries, Firestore is ready to meet all of your app's querying needs. ## What's new from Firebase at Cloud Next 2026 DevFeed: [What's new from Firebase at Cloud Next 2026]() Original publisher: [Read original article]() Author: Seba Gnagnarella; Arthur Thompson; Kristen Richards Published: 2026-04-22T11:30:00Z Content type: news Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Cloud](), [Firestore](), [PostgreSQL](), [SQL](), [Mobile](), [Web](), [GraphQL]() Tags: [2026](), [ai](), [ai-logic](), [ai-studio](), [app-check](), [application-design-center](), [authentication](), [cloud-functions](), [cloud-next](), [dart-on-the-server](), [firebase](), [firestore](), [flutter](), [full-text-search](), [gemini](), [geo-queries](), [graphql](), [hybrid-inference](), [mobile](), [news](), [phone-number-verification](), [postgresql](), [sql](), [sql-connect](), [updates](), [web]() ### AI overview Firebase describes announcements from Cloud Next 2026, including the evolution of Firebase Data Connect into Firebase SQL Connect with realtime syncing, offline cache, and native SQL support. The article also covers Firestore Enterprise pipeline queries moving to general availability. ### Source excerpt News, tutorials, and updates from the Firebase team. ## From prompt to production: Build full-stack apps faster with Google AI Studio and Firebase DevFeed: [From prompt to production: Build full-stack apps faster with Google AI Studio and Firebase]() Original publisher: [Read original article]() Author: Kara Yu; Sam Phillips Published: 2026-03-19T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Google AI](), [Firestore](), [Google](), [Authentication](), [backends](), [Agent Harness]() Tags: [agent](), [agent-harness](), [ai](), [ai-studio](), [antigravity](), [authentication](), [backends](), [build](), [firebase](), [firebase-studio](), [firestore](), [google](), [security]() ### AI overview Firebase announces an integration with Google AI Studio that can provision Firebase projects, Firestore, Authentication, sign-in pages, application code, and draft Security Rules with user approval. The announcement also describes a new Google AI Studio coding agent for multi-step code edits and connections to services such as payment processors and Google Maps. ### Source excerpt Today, we're announcing that Firebase is now integrated with Google AI Studio, accelerating your path from prompt to production so you can turn your vibe-coded ideas into fully functional apps with robust backends. Read on to learn how this works and what this means for Firebase Studio. ## Firebase releases Agent Skills for AI agents building full-stack web apps DevFeed: [Firebase releases Agent Skills for AI agents building full-stack web apps]() Original publisher: [Read original article]() Author: Luke Schlangen Published: 2026-02-17T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Agent Skills](), [Firebase](), [AI Agent](), [Web Development](), [Authentication](), [Firestore](), [Database]() Tags: [agent-skills](), [agents](), [ai](), [ai-agent](), [auth](), [firebase](), [firebase-cli](), [firestore](), [mcp](), [web-development]() ### AI overview Firebase announces Agent Skills for Firebase, specialized instructions and context that help compatible AI agents build and operate Firebase applications. The initial release focuses on full-stack web development, including project setup, authentication, and user flows. ### Source excerpt Use Agent Skills for Firebase to build and deploy a fullstack application with Firebase Auth and a Firestore database! ## Firestore introduces Pipeline operations and an advanced query engine DevFeed: [Firestore introduces Pipeline operations and an advanced query engine]() Original publisher: [Read original article]() Author: Morgan Chen; Tyler Crowe; Minh Nguyen Published: 2026-01-15T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firestore](), [Databases](), [NoSQL](), [Google](), [SDKs]() Tags: [admin-sdk](), [databases](), [firebase](), [firestore](), [javascript](), [nosql-databases](), [offline](), [pipeline](), [real-time](), [sdks]() ### AI overview Firestore announces Pipeline operations and a redesigned query engine for its Enterprise edition. The update adds chained query stages, aggregations, map operations, regular-expression string matching, and optional indexes. ### Source excerpt With a new advanced query engine and querying methods in the SDKs, Firestore is more powerful than ever. ## Antigravity and Firebase MCP accelerate app development DevFeed: [Antigravity and Firebase MCP accelerate app development]() Original publisher: [Read original article]() Author: Alexander Nohe Published: 2025-11-21T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [MCP Server](), [Development](), [ide](), [Angular](), [Firestore](), [hosting](), [API]() Tags: [ai](), [angular](), [antigravity](), [api-keys](), [app-development](), [development](), [firebase](), [firebase-cli](), [firestore](), [hosting](), [how-to](), [mcp](), [mcp-server](), [next-js]() ### AI overview This tutorial explains how to add the Firebase MCP server to Google's Antigravity IDE, initialize Firebase in an existing project, build an application with Firebase services, and deploy it with Firebase Hosting. It describes an example racing game using email-and-password sign-in and Cloud Firestore for a leaderboard, and notes support for App Hosting for server-rendered Next.js and Angular apps. ### Source excerpt Learn how to enable the Firebase MCP server in Antigravity to accelerate app development ## Data Connect: Event Triggers and Generated Admin SDKs DevFeed: [Data Connect: Event Triggers and Generated Admin SDKs]() Original publisher: [Read original article]() Author: Andrea Wu Published: 2025-11-17T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [data](), [SDKs](), [Cloud Functions](), [Firestore](), [Cloud Run](), [Messaging]() Tags: [admin-sdk](), [cloud-functions](), [cloud-run](), [firebase](), [firestore](), [graphql](), [messaging](), [news](), [payload](), [sdks](), [sql-connect](), [updates]() ### AI overview Firebase Data Connect adds event triggers that run server-side code after mutations, along with generated type-safe admin SDKs for privileged environments. The article describes integrations with Cloud Functions for Firebase, Cloud Run, App Hosting, Firestore, external APIs, email, and Firebase Cloud Messaging. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Firestore with MongoDB compatibility is now generally available DevFeed: [Firestore with MongoDB compatibility is now generally available]() Original publisher: [Read original article]() Author: Morgan Chen; Tyler Crowe; Minh Nguyen Published: 2025-08-26T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firestore](), [MongoDB](), [Firebase](), [Databases](), [Cloud]() Tags: [announcement](), [api](), [availability](), [cloud](), [code](), [data](), [database](), [drivers](), [enterprise](), [firebase](), [firebase-cli](), [firebase-console](), [firestore](), [launch](), [mongodb](), [release]() ### AI overview Firestore with MongoDB compatibility has reached general availability in Firebase through the Firestore Enterprise edition. It supports existing MongoDB application code, drivers, libraries, and tools, along with expanded query capabilities, data types, indexes, and performance improvements. ### Source excerpt Announcing the general availability release of Firestore with MongoDB compatibility ## How to integrate Firebase services in Firebase Studio DevFeed: [How to integrate Firebase services in Firebase Studio]() Original publisher: [Read original article]() Author: Yvonne Monterroso; James O'Reilly Published: 2025-07-22T10:05:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Appwrite](), [Authentication](), [Firestore](), [MCP Server](), [Vibe coding](), [Cloud]() Tags: [ai](), [app](), [authentication](), [backend](), [cloud](), [cloud-storage](), [firebase](), [firebase-studio](), [firestore](), [gemini](), [generate](), [mcp](), [mcp-server](), [prototyping](), [tutorials](), [vibe-coding]() ### AI overview This tutorial explains two ways to connect Firebase Authentication, Firestore, and Cloud Storage to apps built in Firebase Studio: generating an integrated application with the App Prototyping agent or using the Firebase MCP server in interactive chat. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Fueld.AI's nutrition coach with Firebase and Google Cloud DevFeed: [Fueld.AI's nutrition coach with Firebase and Google Cloud]() Original publisher: [Read original article]() Author: Raïssa Tona Published: 2025-06-25T00:00:00Z Content type: article Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Google Cloud Platform (GCP)](), [Artificial Intelligence](), [Cloud Functions](), [Firestore](), [Genkit]() Tags: [ai](), [authentication](), [case-study](), [cloud-functions](), [cloud-logging](), [cloud-storage](), [firebase](), [firestore](), [gemini](), [genkit](), [google-analytics](), [google-cloud](), [hosting](), [news](), [vertex-ai]() ### AI overview Fueld.AI used Firebase and Google Cloud services to build a health and nutrition app that analyzes meal photos, provides AI coaching, and securely shares data with health professionals. The article describes its use of Authentication, Cloud Storage, Cloud Functions, Genkit, Gemini, Cloud Firestore, Hosting, Analytics, and Cloud Logging. ### Source excerpt News, tutorials, and updates from the Firebase team. ## What's new in Firebase at I/O 2025 DevFeed: [What's new in Firebase at I/O 2025]() Original publisher: [Read original article]() Author: Aja Hammerly; Seba Gnagnarella Published: 2025-05-20T10:51:00Z Content type: news Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Artificial Intelligence](), [Google](), [Figma](), [Firestore](), [Authentication](), [ui]() Tags: [2025](), [ai](), [ai-logic](), [app-check](), [app-development](), [app-hosting](), [authentication](), [cloud](), [code](), [data](), [database](), [design](), [development](), [emulator-suite](), [figma](), [firebase](), [firebase-ai-logic](), [firebase-studio](), [firestore](), [gemini](), [genkit](), [google](), [google-i-o](), [launch](), [mcp](), [news](), [phone-number-verification](), [postgresql](), [remote-config](), [sql-connect](), [terraform](), [unity](), [updates](), [vertex-ai]() ### AI overview Firebase's I/O 2025 updates introduce new Firebase Studio capabilities, including Gemini 2.5 support, Figma design import, image replacement, and automated backend setup with Firebase Authentication and Firestore integrations. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Top Firebase Studio updates from Google I/O 2025 DevFeed: [Top Firebase Studio updates from Google I/O 2025]() Original publisher: [Read original article]() Author: Jess Kuras; Kirupa Chinnathambi Published: 2025-05-20T10:50:00Z Content type: news Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Artificial Intelligence](), [Figma plugin](), [Authentication](), [Firestore](), [hosting]() Tags: [2025](), [ai](), [app-hosting](), [authentication](), [figma-plugin](), [firebase](), [firebase-studio](), [firestore](), [full-stack-development](), [gemini](), [google-i-o](), [launch]() ### AI overview Firebase Studio updates include Gemini 2.5 Pro support, improvements to the App Prototyping agent, bug fixes, Figma design import through the Builder.io plugin, and automated recommendations and provisioning for Firebase Auth and Cloud Firestore backend services. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Building Your First MCP Server with Genkit DevFeed: [Building Your First MCP Server with Genkit]() Original publisher: [Read original article]() Author: Pavel J Published: 2025-04-25T14:09:50Z Content type: tutorial Language: en Sources: [Firebase Developers - Medium]() Topics: [Genkit](), [Model Context Protocol](), [MCP Server](), [backends](), [Firestore](), [Structured-data](), [AI Development](), [Testing](), [developer tooling]() Tags: [ai](), [backends](), [firebase](), [firestore](), [generative-ai](), [generative-ai-tools](), [genkit](), [guides](), [mcp](), [mcp-server](), [schema](), [testing]() ### AI overview This tutorial explains how to build a custom MCP server with Genkit. It covers defining order data schemas with zod, generating optional test data and storing it in Firestore, creating flows to retrieve orders, and exposing tools that can be called by AI models or external clients such as Cline. ### Source excerpt Generative AI Building robust backends for AI applications often involves integrating various components. The Model Context Protocol (MCP) offers a standardized communication layer, and Genkit provides a powerful framework to leverage it. This article guides you through creating a custom MCP server using Genkit, from defining data schemas to interacting with the server using development tools like Cline. This article assumes some familiarity with Genkit concepts like flows and tools. Learn more about Genkit: https://firebase.google.com/docs/genkit If you prefer this tutorial in video format, check out: https://medium.com/media/908bbf0df5ad1306b125a4c7411c203c/href1. Defining Your Data Schema Before building any application, you need to define the structure of your data. In this example, we're building a system to manage website orders for a consulting company. We use zod, a popular schema declaration library, integrated with Genkit. The OrderSchema defines the necessary fields for each order: const OrderSchema = z.object({ id: z.string().describe("Order Id. Format: A-XXX-XXX, ex. A-123-456"), name: z.string().describe("Name of the business"), colorScheme: z.object({ mainColor: z.string().describe("RGB color prefixed with #, ex. #FFAA66"), highlight: z.string().describe("RGB color prefixed with #, ex. #AA6611"), textColor: z.string().describe("RGB color prefixed with #, ex. #224455"), }), email: z.string(), jobDescription: z .string() .describe( "Detailed description of the website they need. Ex. if they are a construction " + "company describe what they want on the home, contact age, testimonials, etc. " + "pages. Not too crazy, usually static website." ), address: z.string(), }); This schema clearly outlines each piece of information associated with an order, including nested details like the colorScheme. 2. Generating Realistic Test Data (optional) During development, you need ways to both populate your system with test data and inspect that data. Manually creatin ## Election 2029: Storage DevFeed: [Election 2029: Storage]() Original publisher: [Read original article]() Author: jonskeet Published: 2025-03-27T11:46:31Z Content type: tutorial Language: en Sources: [Jon Skeet]() Topics: [Firestore](), [Databases](), [JSON](), [Code](), [Development]() Tags: [code](), [database](), [development](), [election-2029](), [firestore](), [json](), [serialization]() ### AI overview The article describes storage for the Election 2029 project, using separate Firestore databases for test, staging, and production alongside JSON files for local development. It introduces an abstraction interface and discusses patterns for serializing data models to JSON or XML, with particular attention to the Firestore implementation. ### Source excerpt Storage Since my last post about the data models, I've simplified things very slightly - basically the improvements that I thought about while writing the post have now been implemented. I won't go into the details of the changes, as they're not really important, but that's just to explain why some examples might look like ... Continue reading Election 2029: Storage -> ## How to Develop Firebase Genkit Flows DevFeed: [How to Develop Firebase Genkit Flows]() Original publisher: [Read original article]() Author: Nozomi Koborinai Published: 2025-03-15T10:00:54Z Content type: tutorial Language: en Sources: [Firebase Developers - Medium]() Topics: [Genkit](), [Firebase](), [Firestore](), [test]() Tags: [ai](), [emulator](), [emulator-suite](), [firebase](), [firestore](), [gemini](), [genkit](), [how-to](), [test](), [testing]() ### AI overview This tutorial explains how to test Firebase Genkit Flows locally. It describes the limitations of the Genkit Developer UI when flows need Firebase services such as Firestore or Cloud Storage, and presents the Firebase Local Emulator Suite as a way to simulate those services for local testing. ### Source excerpt AIHow to Develop Genkit Flows Genkit includes a powerful tool called the Genkit Developer UI that can significantly accelerate the development of Genkit Flows by enabling local testing. However, when integrating with other Firebase products, such as Firestore or Cloud Storage, the Genkit Developer UI may not be sufficient. In this article, I'll walk you through how to enhance your local testing environment by integrating the Firebase Local Emulator Suite to test Genkit Flows more effectively. Genkit Developer UI The Genkit Developer UI is an essential tool that allows you to verify the behavior of Genkit Flows locally before deploying them. (It has a great UI, and it's super exciting to use!!) While the Genkit Developer UI provides a fantastic developer experience, it does have some limitations. The Limitation The challenge comes when you need to integrate other Firebase products. For example, when you create a configuration where Genkit communicates with Firestore, such as the one I discussed in my previous article, "8 Genkit Architectures to Orchestrate Firebase & AI". To clarify this, let's look at two cases. Working with self-contained flowsOK case In this case, the entire processing is self-contained within Genkit, with no need to integrate Firebase products like Firestore or Cloud Storage, so you can run everything locally using the Genkit Developer UI. export const firebaseAuthFlow = onFlow( ai, { name: `firebaseAuthFlow`, outputSchema: z.string(), authPolicy: firebaseAuth((user) => { if (user.firebase?.sign_in_provider !== `anonymous`) { throw new Error(`Only anonymously authenticated users can access this function`) } }), httpsOptions: { secrets: [googleAIapiKey], cors: true, }, }, async () => {} ) Even though this function uses authPolicy with Firebase Authentication, Genkit Developer UI allows you to inject an authentication provider, so local testing is still possible. Working with Flows that require Firebase servicesFurther testing required case In this ## Trippy Wins the Gemini API Developer Competition with a Firebase-Powered Travel App DevFeed: [Trippy Wins the Gemini API Developer Competition with a Firebase-Powered Travel App]() Original publisher: [Read original article]() Author: Lloyd Hightower Published: 2024-11-21T00:00:00Z Content type: news Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Artificial Intelligence](), [API](), [App](), [Cloud Functions](), [Firestore](), [Serverless](), [Authentication](), [Cloud](), [real-time]() Tags: [ai](), [app](), [authentication](), [backend](), [cloud-functions](), [cloud-messaging](), [cloud-storage](), [firebase](), [firestore](), [gemini](), [machine-learning](), [messaging](), [news](), [notifications](), [real-time](), [recognition](), [recommendations](), [serverless](), [storage](), [travel](), [vertex-ai]() ### AI overview Firebase announces Trippy as the winner of its Gemini API Developer Competition. The travel app combines Gemini with Firebase services to provide personalized itineraries, recommendations, multilingual support, games, receipt-based expense tracking, currency conversion, and contextual chat. ### Source excerpt News, tutorials, and updates from the Firebase team. ## Firestore for Image Embeddings DevFeed: [Firestore for Image Embeddings]() Original publisher: [Read original article]() Author: Mete Atamel Published: 2024-10-29T19:13:03Z Content type: tutorial Language: en Sources: [Firebase Developers - Medium]() Topics: [Firestore](), [Embeddings](), [LangChain](), [multimodal](), [Cloud]() Tags: [ai](), [cloud-storage](), [embeddings](), [firestore](), [generative-ai-tools](), [langchain](), [llms](), [multimodal](), [retrieval](), [search](), [software-development](), [web]() ### AI overview A tutorial showing how to use FirestoreVectorStore and LangChain to generate, store, and retrieve image embeddings for similarity search. It covers multimodal embedding models, images from local storage, Google Cloud Storage, and the web, plus text- and image-based queries. ### Source excerpt Powering LLMs with Firestore In my previous post about Firestore for Text Embedding and Similarity Search, I talked about how Firestore and LangChain can help you to store text embeddings and do similarity searches against them. With multimodal embedding models, you can generate embeddings not only for text but for images and video as well. In this post, I will show you how to store image embeddings in Firestore and later use them for similarity search. Image embeddings support in FirestoreVectorStore As a recap from the previous post, the Firestore for LangChain project provides a FirestoreVectorStore which simplifies storage and retrieval of embeddings. Initially, FirestoreVectorStore only supported text embeddings, but we recently added a new add_images method to store image embeddings. Likewise, we added the similarity_search_image method to run similarity searches with image embeddings. Let's take a closer look at how you can use FirestoreVectorStore in LangChain to work with image embeddings. First, you need to create a multimodal embedding model that can embed images: from langchain_google_vertexai import VertexAIEmbeddings embedding = VertexAIEmbeddings( model_name="multimodalembedding", project=PROJECT_ID, location="us-central1" ) Then, you create a Firestore-backed vector store with the embedding model: from langchain_google_firestore import FirestoreVectorStore vector_store = FirestoreVectorStore( collection=COLLECTION_NAME, embedding_service=embedding, ) Now, you can add images stored locally, in Google Cloud Storage, or any image on the web as follows: ids = ["landmark1.png", "landmark2.png", "landmark3.png"] image_paths = [ "gs://your-storage-bucket/landmark1.png", "./images/landmark2.png", "https://your-website/images/landmark3.png", ] vector_store.add_images(image_paths, ids=ids) This creates embeddings for each image and saves them to Firestore. Afterwards, you can perform a similarity search with a text query: vector_store.similarity_search("stadiu ## What's New in the Flutter SDK for Firebase DevFeed: [What's New in the Flutter SDK for Firebase]() Original publisher: [Read original article]() Author: Andrew Peynado; Cynthia Jiang Published: 2024-05-23T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Flutter](), [SDKs](), [Generative AI](), [WebAssembly](), [Firestore](), [Mobile]() Tags: [ai](), [ai-logic](), [firebase](), [firestore](), [flutter](), [gemini](), [generative-ai](), [release](), [sdk](), [vertex-ai](), [web](), [webassembly]() ### AI overview This release update covers new Firebase SDK capabilities for Flutter, including Vertex AI for Firebase SDKs in public preview, WebAssembly support for Flutter web apps, and enhanced Firestore query capabilities. ### Source excerpt The Flutter SDK for Firebase just got better ## Introducing Firebase Genkit DevFeed: [Introducing Firebase Genkit]() Original publisher: [Read original article]() Author: Chris Gill; Peter Friese Published: 2024-05-14T04:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Artificial Intelligence](), [Firebase](), [Framework](), [Node.js](), [JavaScript](), [Tooling](), [Cloud](), [Ollama](), [Firestore](), [PostgreSQL](), [Serverless]() Tags: [agents](), [ai](), [backend](), [build](), [cloud](), [developer-tooling](), [firebase](), [firestore](), [genkit](), [javascript](), [launch](), [node-js](), [ollama](), [postgresql](), [release](), [serverless](), [typescript]() ### AI overview Firebase introduces Genkit in beta, an open-source framework for JavaScript and TypeScript developers building Node.js backends with AI-powered features. It supports integrations with models, data sources, cloud services, and agents, with local tooling and deployment options for Firebase and Google Cloud. ### Source excerpt Build and deploy AI features with ease [Next page]()