A partire dal 29 aprile 2025, i modelli Gemini 1.5 Pro e Gemini 1.5 Flash non sono disponibili nei progetti che non li hanno mai utilizzati, inclusi i nuovi progetti. Per maggiori dettagli, vedi Versioni e ciclo di vita dei modelli.
Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
Estrai un insieme di entità da un documento e restituiscile in JSON.
Puoi eseguire query direttamente su un modello e testare i risultati restituiti quando utilizzi valori di parametro diversi con la console Cloud o chiamando direttamente l'API Vertex AI.
In qualità di esperto di estrazione di entità dai documenti, analizzi i documenti per identificare e organizzare entità specifiche provenienti da diverse origini in formati strutturati, seguendo linee guida dettagliate per chiarezza e completezza.
Lo schema JSON deve essere seguito durante l'estrazione.
I valori devono includere solo le stringhe di testo presenti nel documento.
Genera un valore null per le entità mancanti.
Risposta
{"earning_item":[{"earning_rate":"20","earning_hours":"80","earning_type":"regular pay","earning_this_period":"1,600.00"}],"direct_deposit_item":[],"current_deduction":"160.00","ytd_deduction":"1,920.00","employee_id":"123456","employee_name":"Janet Doe","employer_name":"The Greatest Company LLC","employer_address":"176 Imaginary Ave\nCambridge, ΜΑ 02138","federal_additional_tax":null,"federal_allowance":null,"federal_marital_status":null,"gross_earnings":"1,600.00","gross_earnings_ytd":"19,200.00","net_pay":"1,060.80","net_pay_ytd":"12,729.60","ssn":"XXX-XX-1234","pay_date":"12/15/17","pay_period_end":"12/12/17","pay_period_start":"11/10/17","state_additional_tax":null,"state_allowance":null,"state_marital_status":null,"tax_item":[{"tax_this_period":"20.80","tax_type":"FICA MED TAX","tax_ytd":"249.60"},{"tax_this_period":"99.20","tax_type":"FICA SS TAX","tax_ytd":"1190.40"},{"tax_this_period":"179.20","tax_type":"FED TAX","tax_ytd":"2150.40"},{"tax_this_period":"80.00","tax_type":"MA ST TAX","tax_ytd":"960.00"}]}
[[["Facile da capire","easyToUnderstand","thumb-up"],["Il problema è stato risolto","solvedMyProblem","thumb-up"],["Altra","otherUp","thumb-up"]],[["Difficile da capire","hardToUnderstand","thumb-down"],["Informazioni o codice di esempio errati","incorrectInformationOrSampleCode","thumb-down"],["Mancano le informazioni o gli esempi di cui ho bisogno","missingTheInformationSamplesINeed","thumb-down"],["Problema di traduzione","translationIssue","thumb-down"],["Altra","otherDown","thumb-down"]],["Ultimo aggiornamento 2025-09-03 UTC."],[],[],null,["Extract a set of entities from a document and return them in JSON.\n\n|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| You can query a model directly and test the results returned when using different parameter values with the Cloud console, or by calling the Vertex AI API directly. - For an example of using the Vertex AI API, see [Quickstart using the Vertex AI API](/vertex-ai/generative-ai/docs/start/quickstarts/api-quickstart). - To view this sample in the Cloud console: [Go to Google Cloud console](https://console.cloud.google.com/vertex-ai/generative/multimodal/prompt-examples/Document%20entity%20extraction) \u003cbr /\u003e ||\n| |----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | **System instructions** | | As an expert in document entity extraction, you parse documents to identify and organize specific entities from diverse sources into structured formats, following detailed guidelines for clarity and completeness. | Prompt Freeform [earnings_statement.pdf](https://storage.mtls.cloud.google.com/cloud-samples-data/generative-ai/pdf/earnings_statement.pdf) You are a document entity extraction specialist. Given a document, your task is to extract the text value of the following entities: ``` { \"earning_item\": [ { \"earning_rate\": \"\", \"earning_hours\": \"\", \"earning_type\": \"\", \"earning_this_period\": \"\" } ], \"direct_deposit_item\": [ { \"direct_deposit\": \"\", \"employee_account_number\": \"\" } ], \"current_deduction\": \"\", \"ytd_deduction\": \"\", \"employee_id\": \"\", \"employee_name\": \"\", \"employer_name\": \"\", \"employer_address\": \"\", \"federal_additional_tax\": \"\", \"federal_allowance\": \"\", \"federal_marital_status\": \"\", \"gross_earnings\": \"\", \"gross_earnings_ytd\": \"\", \"net_pay\": \"\", \"net_pay_ytd\": \"\", \"ssn\": \"\", \"pay_date\": \"\", \"pay_period_end\": \"\", \"pay_period_start\": \"\", \"state_additional_tax\": \"\", \"state_allowance\": \"\", \"state_marital_status\": \"\", \"tax_item\": [ { \"tax_this_period\": \"\", \"tax_type\": \"\", \"tax_ytd\": \"\" } ] } ``` \u003cbr /\u003e - The JSON schema must be followed during the extraction. - The values must only include text strings found in the document. - Generate null for missing entities. Response { \"earning_item\": [ { \"earning_rate\": \"20\", \"earning_hours\": \"80\", \"earning_type\": \"regular pay\", \"earning_this_period\": \"1,600.00\" } ], \"direct_deposit_item\": [], \"current_deduction\": \"160.00\", \"ytd_deduction\": \"1,920.00\", \"employee_id\": \"123456\", \"employee_name\": \"Janet Doe\", \"employer_name\": \"The Greatest Company LLC\", \"employer_address\": \"176 Imaginary Ave\\nCambridge, ΜΑ 02138\", \"federal_additional_tax\": null, \"federal_allowance\": null, \"federal_marital_status\": null, \"gross_earnings\": \"1,600.00\", \"gross_earnings_ytd\": \"19,200.00\", \"net_pay\": \"1,060.80\", \"net_pay_ytd\": \"12,729.60\", \"ssn\": \"XXX-XX-1234\", \"pay_date\": \"12/15/17\", \"pay_period_end\": \"12/12/17\", \"pay_period_start\": \"11/10/17\", \"state_additional_tax\": null, \"state_allowance\": null, \"state_marital_status\": null, \"tax_item\": [ { \"tax_this_period\": \"20.80\", \"tax_type\": \"FICA MED TAX\", \"tax_ytd\": \"249.60\" }, { \"tax_this_period\": \"99.20\", \"tax_type\": \"FICA SS TAX\", \"tax_ytd\": \"1190.40\" }, { \"tax_this_period\": \"179.20\", \"tax_type\": \"FED TAX\", \"tax_ytd\": \"2150.40\" }, { \"tax_this_period\": \"80.00\", \"tax_type\": \"MA ST TAX\", \"tax_ytd\": \"960.00\" } ] } | |------------------------|----------------------| | **Model:** | gemini-1.5-flash-001 | | **Temperature:** | 1 | | **Max output tokens:** | 8192 | | **TopK:** | 40 | | **TopP:** | 0.95 | |"]]
