Firestore

Firebase AI Logic packages Google Cloud's Gemini model capabilities into an SDK suitable for direct client-side invocation, with built-in API Key management, security rules integration, and linkage with the Firebase ecosystem such as Firestore and App Check.

Cloud Firestore is a NoSQL document database where single-field queries are automatically indexed, but composite queries involving multi-field filtering or sorting must have composite indexes created manually.

Firestore's default test mode allows anyone to freely read and write all data, and misconfigured Security Rules can lead to data leaks or high bills.

RAG first retrieves segments relevant to the user's question from its own data sources, then stitches these segments into the prompt as context for Gemini to generate an answer, which differs from fine-tuning that fixes knowledge into the model weights.

After integrating Firestore, the overall data flow is: Firestore data → app logic → Firebase AI Logic → Gemini → AI response.

A typical complete request flow is: the user initiates a request, AI Logic calls Gemini, Firestore provides the data, Gemini generates a response, and the app processes the result and ultimately presents it to the user.

In RAG design, the scale of retrieval results must be controlled: stuffing in too many documents drives up token costs and dilutes key information; and retrieval must occur within the scope of data the user has permission to access to avoid indirect leakage of unauthorized data.

In the Firestore scenario, the retrieval step of RAG is usually implemented with vector search or ordinary queries filtered by field.

Budget Lover's tech stack includes Flutter and Dart, Provider for state management, Firebase Authentication and Firestore, Firebase AI Logic with Gemini, and Flutter's PDF and printing packages.

The free quotas of Firestore and Realtime Database are each 1GB of data storage, and notification and analytics services are basically unlimited; at the initial stage no payment is needed, but the free quotas have limits.

Both Firestore and Realtime Database support real-time data synchronization, but Realtime Database has lower latency and near-instant synchronization, while Firestore is more suitable for scenarios with complex structures.

The course recommends using Firestore for apps with complex data and many fields such as e-commerce and bookkeeping apps, and using Realtime Database for scenarios requiring zero-latency push such as real-time chat, online status, real-time location and notifications.

Firestore's Production Mode denies all unauthenticated read and write requests by default, making it more secure than test mode.

Firebase's core product Firestore uses a NoSQL document model; clients can subscribe to data changes via the SDK, and the server pushes updates without requiring the client to actively poll.

Firestore real-time listeners must be manually unsubscribed when a component unmounts to avoid memory leaks.

Firestore database has two modes—Native mode and Datastore mode—and frontend applications should select Native mode.

When creating Firestore, a data storage region (such as asia-east1 or us-central1) must be selected; this region affects read/write latency and cannot be changed after creation.

Firestore's initial security rules default to test mode, which allows all reads and writes for 30 days.

Firestore's data model organizes data in a three-level structure of Collection → Document → Field, where each document is a JSON object that can nest sub-collections.

CRUD operations in the Firebase SDK are implemented through asynchronous functions: addDoc/setDoc for writing, getDoc/getDocs for reading, updateDoc for updating, and deleteDoc for deleting.