### How this function works This function will label (classify) from any jpg, jpeg, or png images uploaded to Cloud Storage and write the labels to Firestore. ### Prerequisites - You must have previous knowledge of **Firestore**. - You must have previous knowledge of **Firebase Storage**. - You must have previous knowledge of **Cloud Vision API**. ### Function details In order to complete the installation process, you must add the required info to the form: - **Bucket Name**: The name of the bucket that you'd like this function to listen to for changes to the object, e.g., 'images'. - **LABELS_COLLECTION_PATH**: The collection path where the extracted labels will be stored. > Note that you must enter a valid bucket name. Invalid bucket names can cause the installation to fail. ### Using this function Upload images to the configured Storage bucket. Then a new document with the extracted labels will appear in the Firestore collection within a few seconds. The document will have the name of the file that was uploaded as shown in the following example: ``` { file: "gs://default-bucket/test.png", labels: ["Sky", "Cloud", "Water", "Plant", "Blue"] } ``` > Labels are returned in English only. ### Resources - [Detect labels in images documentation](https://cloud.google.com/vision/docs/labels) - [Cloud Vision API](https://cloud.google.com/vision/docs/reference/rest?hl=en)