# Cloud Storage Published articles for Cloud Storage. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## Backblaze B2 and WEKA NeuralMesh Validated as a Two-Tier AI Storage Pipeline, With Snap-to-Object Checkpoints in B2 DevFeed: [Backblaze B2 and WEKA NeuralMesh Validated as a Two-Tier AI Storage Pipeline, With Snap-to-Object Checkpoints in B2]() Original publisher: [Read original article]() Author: Harold Fritts Published: 2026-09-10T20:40:57Z Content type: news Language: en Sources: [StorageReview.com]() Topics: [AI Infrastructure](), [cloud-infrastructure](), [Cloud](), [data-processing](), [model-deployment]() Tags: [accelerators](), [ai](), [ai-infrastructure](), [cloud](), [cloud-storage](), [data](), [datasets](), [enterprise](), [inference](), [infrastructure](), [integration](), [performance](), [snapshots](), [storage]() ### AI overview Backblaze and WEKA validated a two-tier AI storage pipeline that uses WEKA NeuralMesh as the high-performance tier for GPU workloads and Backblaze B2 Cloud Storage as the capacity tier. Raw data, training sets, media, source files, checkpoints, and other assets can move between the tiers according to access needs. NeuralMesh's Snap-to-Object feature was also tested with B2 for storing consistent filesystem snapshots and supporting recovery. ### Source excerpt Backblaze and WEKA have validated their two platforms together for AI pipelines, pairing WEKA NeuralMesh as the performance tier that feeds GPUs with Backblaze B2 Cloud Storage as the capacity tier that holds everything else. The integration, sizing, tuning, and testing are already done, so an AI infrastructure team can deploy a proven two-tier layout The post Backblaze B2 and WEKA NeuralMesh Validated as a Two-Tier AI Storage Pipeline, With Snap-to-Object Checkpoints in B2 appeared first on StorageReview.com. ## Backblaze B2 x Suite Studios: S3 Native File Streaming Turns B2 Cloud Storage Into a High-Performance Drive DevFeed: [Backblaze B2 x Suite Studios: S3 Native File Streaming Turns B2 Cloud Storage Into a High-Performance Drive]() Original publisher: [Read original article]() Author: Dave Simon Published: 2026-09-10T14:04:38Z Content type: article Language: en Sources: [Backblaze Blog | Cloud Storage & Cloud Backup]() Topics: [Amazon S3](), [Cloud](), [Streaming](), [Filesystems](), [mount](), [data](), [migration]() Tags: [architecture](), [automation](), [b2cloud](), [cloud](), [cloud-storage](), [data](), [featured](), [featured-cloud-storage](), [media](), [media-workflow](), [migration](), [mount](), [nas](), [object-storage](), [s3](), [storage](), [streaming]() ### AI overview Backblaze B2 integrates with Suite Studios' S3 Native File Streaming to provide drive-like, high-performance access to cloud-stored data. Teams can mount B2 buckets, stream only the file portions applications need, and use standard S3-compatible objects without duplicating or relocating datasets. The integration supports media production and other workflows involving large cloud datasets. ### Source excerpt Backblaze B2 now integrates with Suite Studios S3 Native File Streaming, giving teams high-performance, drive-like access to cloud data. Work directly with standard S3-compatible objects across media, scientific, geospatial, and engineering workflows without duplicating datasets or creating new storage silos. The post Backblaze B2 x Suite Studios: S3 Native File Streaming Turns B2 Cloud Storage Into a High-Performance Drive appeared first on Backblaze Blog | Cloud Storage & Cloud Backup ## Introducing the Backblaze B2 MCP Server DevFeed: [Introducing the Backblaze B2 MCP Server]() Original publisher: [Read original article]() Author: Jeronimo De Leon Published: 2026-09-08T18:13:00Z Content type: article Language: en Sources: [Backblaze Blog | Cloud Storage & Cloud Backup]() Topics: [MCP Server](), [Model Context Protocol](), [Cloud](), [Authorization](), [Open Source]() Tags: [agents](), [ai](), [ai-ml](), [api](), [b2cloud](), [cloud](), [cloud-storage](), [developers](), [featured](), [featured-cloud-storage](), [mcp](), [mcp-server](), [object-storage](), [open-source](), [storage](), [uncategorized]() ### AI overview Backblaze introduces an open-source B2 MCP Server that lets AI agents operate cloud object storage through MCP-compatible clients. Access is constrained by the permissions of the connected B2 application key, including limits on buckets and operations. ### Source excerpt The Backblaze B2 MCP Server gives AI agents a safe, standard way to operate cloud object storage. Connect MCP-compatible clients to scoped B2 application keys, manage files and buckets, move large objects directly, and control destructive actions with configurable safeguards. The post Introducing the Backblaze B2 MCP Server appeared first on Backblaze Blog | Cloud Storage & Cloud Backup ## Four Platforms, One Timeline: Bringing TAMS Workflow to Life on Backblaze B2 DevFeed: [Four Platforms, One Timeline: Bringing TAMS Workflow to Life on Backblaze B2]() Original publisher: [Read original article]() Author: Dave Simon Published: 2026-09-03T14:23:57Z Content type: article Language: en Sources: [Backblaze Blog | Cloud Storage & Cloud Backup]() Topics: [cloud-infrastructure](), [API](), [Kubernetes](), [browser](), [systems]() Tags: [api](), [article](), [b2cloud](), [browser](), [cloud](), [cloud-native](), [cloud-storage](), [featured](), [featured-cloud-storage](), [kubernetes](), [media](), [object-storage](), [storage]() ### AI overview The article explains how Time Addressable Media Store (TAMS) organizes live media by timeline-based, timestamped segments in object storage. It describes a cloud-native, interoperable workflow built around Backblaze B2 and ecosystem partners LiveWyer, CuttingRoom, and Drastic Technologies, enabling ingest, editing, distribution, playback, and archiving through shared access to the same content. ### Source excerpt TAMS organizes live media by time, giving distributed production teams faster access to shared footage. See how Backblaze B2, LiveWyer, CuttingRoom, and Drastic Technologies create an interoperable, cloud-native workflow for ingest, editing, playback, distribution, and archive with economics at scale. The post Four Platforms, One Timeline: Bringing TAMS Workflow to Life on Backblaze B2 appeared first on Backblaze Blog | Cloud Storage & Cloud Backup ## Code42 Is Shutting Down. Is CrashPlan the Safe Choice, or Just the Convenient One? DevFeed: [Code42 Is Shutting Down. Is CrashPlan the Safe Choice, or Just the Convenient One?]() Original publisher: [Read original article]() Author: Kari Wilson Published: 2026-09-01T16:00:37Z Content type: article Language: en Sources: [Backblaze Blog | Cloud Storage & Cloud Backup]() Topics: [migration](), [Tooling](), [data loss prevention]() Tags: [alternatives](), [backing-up](), [backup](), [blog](), [businessbackup](), [cloud](), [cloud-storage](), [evaluation](), [featured](), [featured-backing-up](), [migration](), [post]() ### AI overview The article examines whether CrashPlan is an appropriate replacement for Code42 after Code42 stopped new sales in 2025 and plans to end support in 2026, with subsequent deletion of backup archives. It explains that Code42's backup business became a separate CrashPlan company in 2022 and urges IT teams to evaluate alternatives rather than assume CrashPlan is an automatic successor. It highlights migration incentives and a possible 5TB storage cap on some CrashPlan plans. ### Source excerpt Code42 support ends in 2026, but CrashPlan isn't the automatic successor it appears to be. Before migrating, understand the companies' split, CrashPlan's ownership, potential storage limits, evolving positioning, and the questions IT teams should ask when evaluating better backup alternatives. The post Code42 Is Shutting Down. Is CrashPlan the Safe Choice, or Just the Convenient One? appeared first on Backblaze Blog | Cloud Storage & Cloud Backup ## Backblaze B2 To Encrypt New Uploads by Default DevFeed: [Backblaze B2 To Encrypt New Uploads by Default]() Original publisher: [Read original article]() Author: Backblaze Published: 2026-08-27T13:00:00Z Content type: release Language: en Sources: [Backblaze Blog | Cloud Storage & Cloud Backup]() Topics: [Cloud](), [Encryption](), [Security](), [configuration]() Tags: [b2cloud](), [cloud](), [cloud-storage](), [configuration](), [encryption](), [featured](), [featured-cloud-storage](), [secure-by-default](), [security](), [storage](), [uncategorized](), [update]() ### AI overview Backblaze B2 will automatically apply server-side AES-256 encryption to newly uploaded and copied object data at rest. SSE-B2 requires no application changes, added cost, or performance tradeoff, while SSE-C remains available for objects encrypted with customer-provided keys. ### Source excerpt Starting September 14, Backblaze B2 will automatically encrypt every new upload and destination copy at rest with AES-256. Always-on SSE-B2 strengthens security without application changes, added costs, or performance impact, while preserving SSE-C for customer-managed encryption keys when required instead. The post Backblaze B2 To Encrypt New Uploads by Default appeared first on Backblaze Blog | Cloud Storage & Cloud Backup ## How Adobe Reduced GPU Idle Time in Generative AI Training Through Faster Data Access and Checkpointing DevFeed: [How Adobe Reduced GPU Idle Time in Generative AI Training Through Faster Data Access and Checkpointing]() Original publisher: [Read original article]() Author: Maddie Presland Published: 2026-08-25T15:22:30Z Content type: article Language: en Sources: [Backblaze Blog | Cloud Storage & Cloud Backup]() Topics: [GPU](), [Training AI Models](), [cloud-infrastructure](), [networking](), [data]() Tags: [ai-ml](), [ai-training](), [b2cloud](), [cloud](), [cloud-storage](), [compute](), [ethernet](), [featured](), [featured-cloud-storage](), [gpu](), [model-training](), [networking]() ### AI overview Adobe's generative AI training pipeline left roughly two-thirds of GPU time waiting for data. The article attributes the waste to storage and retrieval bottlenecks, networking limits, and checkpointing overhead, and describes Adobe's use of a high-performance networking fabric and fragmented checkpoint storage to reduce delays. ### Source excerpt Adobe's experience reveals why GPUs sit idle during AI model training: slow storage, insufficient throughput, and uneven workloads. Learn how storage bottlenecks and uneven data loading leave expensive GPUs idle--and how always-hot, high-throughput object storage keeps AI training pipelines running efficiently at scale while reducing wasted compute costs. The post Why Your GPU Is Sitting Idle: The Data Pipeline Problem No One Talks About appeared first on Backblaze Blog | Cloud Storage & Cloud Backup ## Results from the Backblaze Generative AI Media Hackathon DevFeed: [Results from the Backblaze Generative AI Media Hackathon]() Original publisher: [Read original article]() Author: Jeronimo De Leon Published: 2026-08-14T15:52:05Z Content type: article Language: en Sources: [Backblaze Blog | Cloud Storage & Cloud Backup]() Topics: [Generative AI](), [Orchestration](), [cloud-infrastructure](), [For the Love of Code](), [Open Source](), [SDKs]() Tags: [2026](), [ai-ml](), [b2cloud](), [cloud](), [cloud-storage](), [developer](), [featured](), [featured-cloud-storage](), [generative](), [hackathon](), [object-storage](), [open-source](), [orchestration](), [sdk](), [tech-lab](), [technical]() ### AI overview The article examines the strongest projects from the Backblaze Generative AI Media Hackathon and argues that production-ready generative media applications depend on more than generating images, video, or audio. It highlights storage design, provenance, verification, correction, deletion protection, and orchestration across multiple providers. ### Source excerpt See what the strongest projects from the Backblaze Generative AI Media Hackathon had in common. These five generative media apps show how storage and orchestration become part of production-ready design. The post Results from the Backblaze Generative AI Media Hackathon appeared first on Backblaze Blog | Cloud Storage & Cloud Backup ## Backblaze Drive Stats: How an Open Dataset Powers Academic and AI/ML Research DevFeed: [Backblaze Drive Stats: How an Open Dataset Powers Academic and AI/ML Research]() Original publisher: [Read original article]() Author: Stephanie Doyle Published: 2026-08-13T15:08:38Z Content type: article Language: en Sources: [Backblaze Blog | Cloud Storage & Cloud Backup]() Topics: [dataset](), [DRIVE](), [Machine learning](), [Transformer](), [Disk image]() Tags: [ai-ml](), [articles](), [b2cloud](), [cloud-storage](), [data](), [drive](), [featured](), [featured-cloud-storage](), [hard-drive-stats](), [ml](), [research](), [source](), [storage]() ### AI overview The article explains how Backblaze Drive Stats evolved from an internal hard-drive reliability tool into an open dataset used in academic and AI/ML research. It describes the dataset's real-world scale, quarterly publication, SMART attributes, labeled failures, broad manufacturer coverage, and use in hard-drive failure prediction research. ### Source excerpt Backblaze Drive Stats has been cited in more than 105 academic papers and AI/ML projects since 2018. Explore the research it powers and download the dataset. The post Backblaze Drive Stats: How an Open Dataset Powers Academic and AI/ML Research appeared first on Backblaze Blog | Cloud Storage & Cloud Backup ## How Redpanda Cloud Topics rethinks Kafka compaction DevFeed: [How Redpanda Cloud Topics rethinks Kafka compaction]() Original publisher: [Read original article]() Author: Willem Kaufmann Published: 2026-06-30T00:00:00Z Content type: article Language: en Sources: [Redpanda]() Topics: [Kafka](), [cloud-infrastructure](), [Cloud](), [Streaming](), [Algorithm]() Tags: [apache](), [apache-kafka](), [architecture](), [cloud-native](), [cloud-storage](), [clusters](), [cpu](), [cycles](), [engineering](), [kafka](), [object-storage](), [reduce](), [retention](), [scale](), [storage](), [streaming]() ### AI overview The article explains how Redpanda Cloud Topics redesigns Kafka log compaction for cloud-native streaming. It describes how the architecture reduces redundant processing and CPU use, lowers cloud storage costs, and preserves Kafka behavior while addressing scaling challenges such as limited memory, tombstone removal, and rewriting large volumes of object storage data. ### Source excerpt Compaction can overwhelm poorly sized Kafka clusters, leading to full disks and maxed-out CPUs. Learn how Redpanda's Cloud Topics architecture redesigns compaction to cut redundant work, reduce cloud storage costs, and preserve the Kafka semantics you rely on. ## ClickPy at 2 Trillion rows: Scaling ingestion and fixing the past DevFeed: [ClickPy at 2 Trillion rows: Scaling ingestion and fixing the past]() Original publisher: [Read original article]() Author: Lionel Palacin Published: 2026-01-21T10:48:32Z Content type: article Language: en Sources: [ClickHouse Blog]() Topics: [clickhouse](), [data](), [Python](), [BigQuery](), [dataset](), [cloud-infrastructure](), [Code](), [Scripting]() Tags: [bigquery](), [blog](), [blog-post](), [clickhouse](), [cloud-storage](), [code](), [data](), [database](), [operational](), [python](), [scale](), [scripting](), [storage]() ### AI overview ClickPy has grown to more than 2 trillion Python package-download rows dating back to 2011. This article describes replacing a custom, cron-based ingestion script with ClickPipes and correcting historical data while keeping the service available and ingestion uninterrupted. ### Source excerpt A look at how ClickPy handles over 2 trillion Python package downloads, from ingestion redesign to fixing historical data at scale. ## How to use Vertex AI Prompt Optimizer with ground truth data DevFeed: [How to use Vertex AI Prompt Optimizer with ground truth data]() Original publisher: [Read original article]() Author: Alexander Nohe; Elena Erbiceanu Tener Published: 2026-01-20T00:00:00Z Content type: tutorial Language: en Sources: [Firebase Blog]() Topics: [Prompt Engineering](), [Artificial Intelligence](), [Ground truth / benchmark quality](), [Google](), [CSV](), [data](), [Firebase]() Tags: [ai](), [cloud-storage](), [data](), [evaluation](), [firebase](), [format](), [gemini](), [google](), [google-cloud](), [how-to](), [learn](), [quality](), [vertex](), [vertex-ai]() ### AI overview This tutorial explains how to use Vertex AI Prompt Optimizer with ground truth data to iteratively tune prompts and evaluate output quality. It describes preparing scripts and target descriptions in a Google Sheet, exporting the data as CSV, uploading it to Google Cloud Storage, and configuring optimization in a Colab Enterprise notebook. ### Source excerpt Learn how to use the Vertex AI Prompt Optimizer to automatically tune your prompts to get better results by iterating on your prompts and then running an evaluation on the outputs assessing their quality to see if it has improved. ## Streaming IoT and event data into Snowflake and ClickHouse DevFeed: [Streaming IoT and event data into Snowflake and ClickHouse]() Original publisher: [Read original article]() Author: Mdu Sibisi Published: 2025-12-09T00:00:00Z Content type: tutorial Language: en Sources: [Redpanda]() Topics: [Internet of things](), [Streaming](), [Redpanda-Connect](), [clickhouse](), [data observability](), [Compression](), [data-governance](), [DataOps](), [Database]() Tags: [clickhouse](), [cloud-storage](), [compliance](), [data](), [data-governance](), [event](), [iot](), [pipelines](), [redpanda-connect](), [streaming]() ### AI overview A guide to streaming IoT and event data through Redpanda and Redpanda Connect into Snowflake and ClickHouse. It compares ClickHouse for real-time analysis with Snowflake for scalable cloud storage, historical reporting, and querying, while discussing governance, compression, data freshness, and robust pipeline design. ### Source excerpt Learn how to stream IoT and event data into Snowflake and ClickHouse using Redpanda ## Moving Thanos from GCS to Huawei OBS, and fixing a multipart upload bug on the way DevFeed: [Moving Thanos from GCS to Huawei OBS, and fixing a multipart upload bug on the way]() Original publisher: [Read original article]() Published: 2025-10-20T00:00:00Z Content type: article Language: en Sources: [Andika Ahmad Ramadhan -- Blog]() Topics: [huawei](), [migration](), [bug](), [Cloud](), [Google Cloud Platform (GCP)](), [Code]() Tags: [bug](), [cloud](), [cloud-storage](), [code](), [google](), [google-cloud](), [huawei](), [migration]() ### AI overview This article describes migrating Thanos object storage from Google Cloud Storage to Huawei Cloud OBS. The migration exposed two multipart upload bugs in the OBS provider: a zero-value part size and a content-length mismatch. A patch addressed both issues, although the upstream change was still under review when the article was written. ### Source excerpt What broke when Thanos blocks started landing in Huawei Cloud OBS instead of Google Cloud Storage, and the objstore patch that fixed it. ## 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. ## Firebase MCP Server DevFeed: [Firebase MCP Server]() Original publisher: [Read original article]() Author: Michael Bleigh Published: 2025-05-20T10:47:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [MCP Server](), [Model Context Protocol](), [Firebase CLI](), [Artificial Intelligence]() Tags: [agents](), [ai](), [cloud-messaging](), [cloud-storage](), [experimental](), [explore](), [firebase](), [firebase-cli](), [firestore](), [google-i-o](), [launch](), [mcp](), [mcp-server](), [security-rules]() ### AI overview Firebase announces an experimental Firebase MCP Server, integrated with the Firebase CLI, that lets AI assistants and coding agents use standardized tools to configure, build, manage, and observe Firebase applications. The article describes capabilities including project setup, user management, Firestore access, GraphQL queries, security-rule validation, messaging, Remote Config deployment, crash monitoring, and Cloud Storage URL generation. ### Source excerpt News, tutorials, and updates from the Firebase team. ## We're Cutting Storage Costs (Automatically) DevFeed: [We're Cutting Storage Costs (Automatically)]() Original publisher: [Read original article]() Author: Anna Stepanyan Published: 2024-11-21T00:26:43Z Content type: article Language: en Sources: [Blog -- Neon Docs]() Topics: [cloud-infrastructure](), [Database](), [Cache](), [Amazon S3](), [Availability](), [Developer experience](), [Azure]() Tags: [amazon-s3](), [availability](), [azure](), [cache](), [cloud-storage](), [company](), [data](), [developer-experience](), [performance](), [ssd](), [storage]() ### AI overview Neon is reducing storage costs for inactive database branches automatically. Branches that have been idle for at least one day and are older than two weeks are archived by evicting their data from the Pageserver's high-performance SSD cache while retaining it in durable cloud object storage such as Amazon S3 or Azure Blob Storage. When accessed again, a branch is automatically reactivated, with a small first-query delay while its data is reloaded into the cache. ### Source excerpt Starting December 1st, many Neon users will see lower storage costs. Inactive branches--those idle for at least a day and older than 2 weeks--will now be charged at a reduced per-GB rate. If this applies to you, there's nothing you need to do--it all happens automatically. Simply en... ## 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 ## Vertex AI in Firebase is now Generally Available DevFeed: [Vertex AI in Firebase is now Generally Available]() Original publisher: [Read original article]() Author: Miguel Ramos Published: 2024-10-21T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Google AI](), [SDKs](), [API](), [JSON](), [Mobile](), [multimodal](), [Web]() Tags: [ai](), [ai-logic](), [android](), [api](), [app-check](), [cloud-storage](), [firebase](), [flutter](), [function-calling](), [gemini](), [generative-ai](), [ios](), [javascript](), [json](), [launch](), [mobile](), [multimodal](), [remote-config](), [sdks](), [structured-output](), [vertex-ai](), [web]() ### AI overview Firebase announces the general availability of Vertex AI in Firebase, enabling mobile and web apps to access Gemini models through Firebase client SDKs. The release includes support for multimodal prompting, system instructions, function calling, and structured JSON output with schemas. ### Source excerpt Securely add generative AI features to your app using Firebase client SDKs ## Introducing Vertex AI for Firebase DevFeed: [Introducing Vertex AI for Firebase]() Original publisher: [Read original article]() Author: Miguel Ramos; Rachel Saunders Published: 2024-05-14T03:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Google AI](), [SDKs](), [API](), [Mobile](), [Web]() Tags: [ai](), [ai-logic](), [api](), [app-check](), [cloud-storage](), [firebase](), [firebase-remote-config](), [gemini](), [launch](), [machine-learning](), [mobile](), [remote-config](), [sdks](), [vertex](), [vertex-ai](), [web]() ### AI overview Google introduces Vertex AI for Firebase, providing client SDKs that let mobile and web applications use the Vertex AI Gemini API and run inference across Gemini models without requiring a separate backend service layer. ### Source excerpt Build AI features with the Vertex AI Gemini API using Firebase's new client SDKs ## Introducing Workflow History Export DevFeed: [Introducing Workflow History Export]() Original publisher: [Read original article]() Author: Nikitha Suryadevara Published: 2024-03-01T07:00:00Z Content type: release Language: en Sources: [Temporal Blog]() Topics: [Amazon S3](), [AWS CloudFormation](), [Amazon Web Services](), [Cloud](), [audit](), [Command-line interface]() Tags: [audit](), [aws](), [aws-cloudformation](), [aws-s3](), [cli](), [cloud-storage](), [export](), [preview](), [product-news](), [production](), [release](), [s3](), [workflow]() ### AI overview Temporal Cloud has introduced Workflow History Export, allowing users to export closed workflow histories by namespace to an AWS S3 bucket. The feature supports longer-term retention for compliance, auditing, and analysis and is available to all users in Public Preview for production use. ### Source excerpt Workflow History Export in Temporal Cloud allows users to export closed workflow histories on a per-namespace basis to an AWS S3 cloud storage bucket. ## Firebase announces its first Demo Day with 10 demos and technical resources DevFeed: [Firebase announces its first Demo Day with 10 demos and technical resources]() Original publisher: [Read original article]() Author: Annum Munir Published: 2023-11-08T00:00:00Z Content type: release Language: en Sources: [Firebase Blog]() Topics: [Firebase](), [Development](), [Google](), [Flutter](), [Artificial Intelligence]() Tags: [ai](), [android](), [app-distribution](), [authentication](), [cloud-functions](), [cloud-storage](), [crashlytics](), [demo](), [demo-day](), [development](), [event](), [extensions](), [firebase](), [firestore](), [flutter](), [google](), [google-analytics](), [ios](), [kotlin](), [launch](), [palm](), [project-idx](), [python](), [remote-config](), [swift](), [terraform](), [web](), [windows]() ### AI overview Firebase announces its first Demo Day, releasing 10 prerecorded videos and technical resources covering app development, AI workflows, Flutter and Project IDX integrations, security, infrastructure, and Firebase console updates. ### Source excerpt After sharing tons of teasers and behind-the-scenes footage over the past few weeks, we're excited to announce that our very first Demo Day is finally here! [Next page]()