O Gemini 4 Argon já está disponível. Faça um teste.

O Google usa tecnologia de IA na tradução de conteúdos para seu idioma de preferência. As traduções com IA podem ter erros.

Pesquisa de arquivos

A API Gemini permite a geração aumentada por recuperação ("RAG") com a ferramenta de pesquisa de arquivos. A Pesquisa de Arquivos importa, divide e indexa seus dados para permitir a recuperação rápida de informações relevantes com base em um comando fornecido. Essas informações recuperadas são usadas como contexto para o modelo, permitindo que ele forneça respostas mais precisas e relevantes. A pesquisa de arquivos também pode oferecer recursos multimodais com embeddings de texto compatíveis com gemini-embedding-001 e embeddings de imagem/multimodais compatíveis com gemini-embedding-2.

O armazenamento de arquivos e a geração de embeddings no momento da consulta são sem custo financeiro. Você só paga pela criação de embeddings quando indexa seus arquivos pela primeira vez e pelo custo normal dos tokens de entrada / saída do modelo do Gemini. Esse novo paradigma de faturamento torna a ferramenta de pesquisa de arquivos mais fácil e econômica de criar e dimensionar. Consulte a seção de preços para mais detalhes.

Fazer upload diretamente para a loja da Pesquisa de arquivos

Este exemplo mostra como fazer upload de um arquivo diretamente para o armazenamento de pesquisa de arquivos:

Python

from google import genai
from google.genai import types
import time

client = genai.Client()

file_search_store = client.file_search_stores.create(
    config={
        'display_name': 'your-fileSearchStore-name',
        'embedding_model': 'models/gemini-embedding-2'
    }
)

operation = client.file_search_stores.upload_to_file_search_store(
  file='sample.txt',
  file_search_store_name=file_search_store.name,
  config={
      'display_name' : 'display-file-name',
  }
)

while not operation.done:
    time.sleep(5)
    operation = client.operations.get(operation)

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Can you tell me about [insert question]",
    tools=[{
        "type": "file_search",
        "file_search_store_names": [file_search_store.name]
    }]
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)
                if content_block.annotations:
                    print("\nSources:")
                    for annotation in content_block.annotations:
                        if annotation.type == "file_citation":
                            print(f"  - {annotation.file_name}: {annotation.source}")

JavaScript

import { GoogleGenAI } from '@google/genai';

const ai = new GoogleGenAI({});

async function run() {
  const fileSearchStore = await ai.fileSearchStores.create({
    config: {
      displayName: 'your-fileSearchStore-name',
      embeddingModel: 'models/gemini-embedding-2'
    }
  });

  let operation = await ai.fileSearchStores.uploadToFileSearchStore({
    file: 'file.txt',
    fileSearchStoreName: fileSearchStore.name,
    config: {
      displayName: 'file-name',
    }
  });

  while (!operation.done) {
    await new Promise(resolve => setTimeout(resolve, 5000));
    operation = await ai.operations.get({ operation });
  }

  const interaction = await ai.interactions.create({
    model: "gemini-3.8-flash",
    input: "Can you tell me about [insert question]",
    tools: [{
      type: "file_search",
      file_search_store_names: [fileSearchStore.name]
    }]
  });

  for (const step of interaction.steps) {
    if (step.type === 'model_output') {
      for (const contentBlock of step.content) {
        if (contentBlock.type === 'text') {
          console.log(contentBlock.text);
          if (contentBlock.annotations) {
            console.log("\nSources:");
            for (const annotation of contentBlock.annotations) {
              if (annotation.type === 'file_citation') {
                console.log(`  - ${annotation.file_name}: ${annotation.source}`);
              }
            }
          }
        }
      }
    }
  }
}

run();

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Annotation;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.FileCitation;
import com.google.genai.gaos.models.interactions.FileSearch;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.types.CreateFileSearchStoreConfig;
import com.google.genai.types.FileSearchStore;
import com.google.genai.types.UploadToFileSearchStoreConfig;
import com.google.genai.types.UploadToFileSearchStoreOperation;
import java.util.Arrays;

Client client = new Client();

FileSearchStore fileSearchStore =
    client.fileSearchStores.create(
        CreateFileSearchStoreConfig.builder()
            .displayName("your-fileSearchStore-name")
            .embeddingModel("models/gemini-embedding-2")
            .build());

UploadToFileSearchStoreOperation operation =
    client.fileSearchStores.uploadToFileSearchStore(
        fileSearchStore.name().get(),
        "sample.txt",
        UploadToFileSearchStoreConfig.builder().displayName("display-file-name").build());

while (!operation.done().orElse(false)) {
  Thread.sleep(5000);
  operation = client.operations.get(operation, null);
}

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("Can you tell me about [insert question]"))
        .tools(
            Arrays.asList(
                FileSearch.builder()
                    .fileSearchStoreNames(Arrays.asList(fileSearchStore.name().get()))
                    .build()))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.steps().isPresent()) {
  for (Step step : interaction.steps().get()) {
    if (step instanceof ModelOutputStep) {
      ModelOutputStep outputStep = (ModelOutputStep) step;
      if (outputStep.content().isPresent()) {
        for (Content contentBlock : outputStep.content().get()) {
          if (contentBlock instanceof TextContent) {
            TextContent textContent = (TextContent) contentBlock;
            System.out.println(textContent.text().orElse(""));
            if (textContent.annotations().isPresent()
                && !textContent.annotations().get().isEmpty()) {
              System.out.println("\nSources:");
              for (Annotation annotation : textContent.annotations().get()) {
                if (annotation instanceof FileCitation) {
                  FileCitation citation = (FileCitation) annotation;
                  System.out.printf(
                      "  - %s: %s%n",
                      citation.fileName().orElse(""), citation.source().orElse(""));
                }
              }
            }
          }
        }
      }
    }
  }
}

Go

package main

import (
    "context"
    "fmt"
    "log"
    "time"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    fileSearchStore, err := client.FileSearchStores.Create(ctx, &genai.CreateFileSearchStoreConfig{
        DisplayName:    "your-fileSearchStore-name",
        EmbeddingModel: "models/gemini-embedding-2",
    })
    if err != nil {
        log.Fatal(err)
    }

    operation, err := client.FileSearchStores.UploadToFileSearchStoreFromPath(
        ctx,
        "sample.txt",
        fileSearchStore.Name,
        &genai.UploadToFileSearchStoreConfig{
            DisplayName: "display-file-name",
        },
    )
    if err != nil {
        log.Fatal(err)
    }

    for !operation.Done {
        time.Sleep(5 * time.Second)
        operation, err = client.Operations.GetUploadToFileSearchStoreOperation(ctx, operation, nil)
        if err != nil {
            log.Fatal(err)
        }
    }

    resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(
            interactions.CreateModelInteraction{
                Model: interactions.Model("gemini-3.8-flash"),
                Input: interactions.NewInteractionsInput("Can you tell me about [insert question]"),
                Tools: []interactions.Tool{
                    interactions.NewTool(interactions.FileSearch{
                        FileSearchStoreNames: []string{fileSearchStore.Name},
                    }),
                },
            },
        ),
    })
    if err != nil {
        log.Fatal(err)
    }

    for _, step := range resp.Interaction.Steps {
        if step.ModelOutputStep != nil {
            for _, content := range step.ModelOutputStep.Content {
                if content.TextContent != nil {
                    fmt.Println(content.TextContent.Text)
                    if len(content.TextContent.Annotations) > 0 {
                        fmt.Println("\nSources:")
                        for _, annotation := range content.TextContent.Annotations {
                            if annotation.FileCitation != nil {
                                c := annotation.FileCitation
                                fileName := ""
                                if c.FileName != nil {
                                    fileName = *c.FileName
                                }
                                source := ""
                                if c.Source != nil {
                                    source = *c.Source
                                }
                                fmt.Printf("  - %s: %s\n", fileName, source)
                            }
                        }
                    }
                }
            }
        }
    }
}

REST

# 1. Create a File Search store
curl -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=$GEMINI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "displayName": "your-file-search-store-name",
      "embeddingModel": "models/gemini-embedding-2"
    }' > store_res.json

FILE_SEARCH_STORE_NAME=$(jq -r ".name" store_res.json)

# 2. Upload directly to File Search store using resumable upload
NUM_BYTES=$(wc -c < "sample.txt")
curl "https://generativelanguage.googleapis.com/upload/v1beta/fileSearchStores/$FILE_SEARCH_STORE_NAME:uploadToFileSearchStore?key=$GEMINI_API_KEY" \
    -D upload-header.tmp \
    -H "X-Goog-Upload-Protocol: resumable" \
    -H "X-Goog-Upload-Command: start" \
    -H "X-Goog-Upload-Header-Content-Length: $NUM_BYTES" \
    -H "X-Goog-Upload-Header-Content-Type: text/plain" \
    -H "Content-Type: application/json" \
    -d '{"displayName": "sample.txt"}' 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " upload-header.tmp | cut -d" " -f2 | tr -d "\r")
rm upload-header.tmp

curl "${upload_url}" \
    -H "Content-Length: $NUM_BYTES" \
    -H "X-Goog-Upload-Offset: 0" \
    -H "X-Goog-Upload-Command: upload, finalize" \
    --data-binary "@sample.txt" 2> /dev/null > upload_response.json

cat upload_response.json

# 3. Query using the File Search store
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gemini-3.8-flash",
      "input": "Can you tell me about [insert question]",
      "tools": [{
        "type": "file_search",
        "file_search_store_names": ["'"$FILE_SEARCH_STORE_NAME"'"]
      }]
    }'

Consulte a referência da API para uploadToFileSearchStore para mais informações.

Como importar arquivos

Como alternativa, você pode fazer upload de um arquivo e importá-lo para o repositório de pesquisa de arquivos:

Python

from google import genai
from google.genai import types
import time

client = genai.Client()

sample_file = client.files.upload(file='sample.txt', config={'display_name': 'display_file_name'})

file_search_store = client.file_search_stores.create(
    config={
        'display_name': 'your-fileSearchStore-name',
        'embedding_model': 'models/gemini-embedding-2'
    }
)

operation = client.file_search_stores.import_file(
    file_search_store_name=file_search_store.name,
    file_name=sample_file.name
)

while not operation.done:
    time.sleep(5)
    operation = client.operations.get(operation)

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Can you tell me about [insert question]",
    tools=[{
        "type": "file_search",
        "file_search_store_names": [file_search_store.name]
    }]
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)

JavaScript

import { GoogleGenAI } from '@google/genai';

const ai = new GoogleGenAI({});

async function run() {
  const sampleFile = await ai.files.upload({
    file: 'sample.txt',
    config: { displayName: 'file-name' }
  });

  const fileSearchStore = await ai.fileSearchStores.create({
    config: {
      displayName: 'your-fileSearchStore-name',
      embeddingModel: 'models/gemini-embedding-2'
    }
  });

  let operation = await ai.fileSearchStores.importFile({
    fileSearchStoreName: fileSearchStore.name,
    fileName: sampleFile.name
  });

  while (!operation.done) {
    await new Promise(resolve => setTimeout(resolve, 5000));
    operation = await ai.operations.get({ operation: operation });
  }

  const interaction = await ai.interactions.create({
    model: "gemini-3.8-flash",
    input: "Can you tell me about [insert question]",
    tools: [{
      type: "file_search",
      file_search_store_names: [fileSearchStore.name]
    }]
  });

  for (const step of interaction.steps) {
    if (step.type === 'model_output') {
      for (const contentBlock of step.content) {
        if (contentBlock.type === 'text') {
          console.log(contentBlock.text);
        }
      }
    }
  }
}

run();

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.FileSearch;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.types.CreateFileSearchStoreConfig;
import com.google.genai.types.File;
import com.google.genai.types.FileSearchStore;
import com.google.genai.types.ImportFileOperation;
import com.google.genai.types.UploadFileConfig;
import java.util.Arrays;

Client client = new Client();

File sampleFile =
    client.files.upload(
        "sample.txt", UploadFileConfig.builder().displayName("display_file_name").build());

FileSearchStore fileSearchStore =
    client.fileSearchStores.create(
        CreateFileSearchStoreConfig.builder()
            .displayName("your-fileSearchStore-name")
            .embeddingModel("models/gemini-embedding-2")
            .build());

ImportFileOperation operation =
    client.fileSearchStores.importFile(
        fileSearchStore.name().get(), sampleFile.name().get(), null);

while (!operation.done().orElse(false)) {
  Thread.sleep(5000);
  operation = client.operations.get(operation, null);
}

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("Can you tell me about [insert question]"))
        .tools(
            Arrays.asList(
                FileSearch.builder()
                    .fileSearchStoreNames(Arrays.asList(fileSearchStore.name().get()))
                    .build()))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.steps().isPresent()) {
  for (Step step : interaction.steps().get()) {
    if (step instanceof ModelOutputStep) {
      ModelOutputStep outputStep = (ModelOutputStep) step;
      if (outputStep.content().isPresent()) {
        for (Content contentBlock : outputStep.content().get()) {
          if (contentBlock instanceof TextContent) {
            TextContent textContent = (TextContent) contentBlock;
            System.out.println(textContent.text().orElse(""));
          }
        }
      }
    }
  }
}

Go

package main

import (
    "context"
    "fmt"
    "log"
    "time"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    sampleFile, err := client.Files.UploadFromPath(ctx, "sample.txt", &genai.UploadFileConfig{
        DisplayName: "display_file_name",
    })
    if err != nil {
        log.Fatal(err)
    }

    fileSearchStore, err := client.FileSearchStores.Create(ctx, &genai.CreateFileSearchStoreConfig{
        DisplayName:    "your-fileSearchStore-name",
        EmbeddingModel: "models/gemini-embedding-2",
    })
    if err != nil {
        log.Fatal(err)
    }

    operation, err := client.FileSearchStores.ImportFile(ctx, fileSearchStore.Name, sampleFile.Name, nil)
    if err != nil {
        log.Fatal(err)
    }

    for !operation.Done {
        time.Sleep(5 * time.Second)
        operation, err = client.Operations.GetImportFileOperation(ctx, operation, nil)
        if err != nil {
            log.Fatal(err)
        }
    }

    resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(
            interactions.CreateModelInteraction{
                Model: interactions.Model("gemini-3.8-flash"),
                Input: interactions.NewInteractionsInput("Can you tell me about [insert question]"),
                Tools: []interactions.Tool{
                    interactions.NewTool(interactions.FileSearch{
                        FileSearchStoreNames: []string{fileSearchStore.Name},
                    }),
                },
            },
        ),
    })
    if err != nil {
        log.Fatal(err)
    }

    for _, step := range resp.Interaction.Steps {
        if step.ModelOutputStep != nil {
            for _, content := range step.ModelOutputStep.Content {
                if content.TextContent != nil {
                    fmt.Println(content.TextContent.Text)
                }
            }
        }
    }
}

REST

# 1. Upload file using the Files API
NUM_BYTES=$(wc -c < "sample.txt")
curl "https://generativelanguage.googleapis.com/upload/v1beta/files?key=$GEMINI_API_KEY" \
    -D upload-header.tmp \
    -H "X-Goog-Upload-Protocol: resumable" \
    -H "X-Goog-Upload-Command: start" \
    -H "X-Goog-Upload-Header-Content-Length: $NUM_BYTES" \
    -H "X-Goog-Upload-Header-Content-Type: text/plain" \
    -H "Content-Type: application/json" \
    -d '{"file": {"displayName": "sample.txt"}}' 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " upload-header.tmp | cut -d" " -f2 | tr -d "\r")
rm upload-header.tmp

curl "${upload_url}" \
    -H "Content-Length: $NUM_BYTES" \
    -H "X-Goog-Upload-Offset: 0" \
    -H "X-Goog-Upload-Command: upload, finalize" \
    --data-binary "@sample.txt" 2> /dev/null > file_info.json

FILE_NAME=$(jq -r ".file.name" file_info.json)

# 2. Create a File Search store
curl -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=$GEMINI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "displayName": "your-file-search-store-name",
      "embeddingModel": "models/gemini-embedding-2"
    }' > store_res.json

FILE_SEARCH_STORE_NAME=$(jq -r ".name" store_res.json)

# 3. Import the file into the File Search store
curl -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores/$FILE_SEARCH_STORE_NAME:importFile?key=$GEMINI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{"fileName": "'"$FILE_NAME"'"}'

# 4. Query using the File Search store
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gemini-3.8-flash",
      "input": "Can you tell me about [insert question]",
      "tools": [{
        "type": "file_search",
        "file_search_store_names": ["'"$FILE_SEARCH_STORE_NAME"'"]
      }]
    }'

Consulte a referência da API para importFile para mais informações.

Configuração de divisão em blocos

Quando você importa um arquivo para um repositório da Pesquisa de Arquivos, ele é automaticamente dividido em partes, incorporado, indexado e enviado para o repositório. Se você precisar de mais controle sobre a estratégia de divisão, especifique uma configuração chunking_config para definir um número máximo de tokens por parte e um número máximo de tokens sobrepostos.

Python

from google import genai
from google.genai import types
import time

client = genai.Client()

operation = client.file_search_stores.upload_to_file_search_store(
    file_search_store_name=file_search_store.name,
    file='sample.txt',
    config={
        'chunking_config': {
          'white_space_config': {
            'max_tokens_per_chunk': 200,
            'max_overlap_tokens': 20
          }
        }
    }
)

while not operation.done:
    time.sleep(5)
    operation = client.operations.get(operation)

print("Custom chunking complete.")

JavaScript

import { GoogleGenAI } from '@google/genai';

const ai = new GoogleGenAI({});

let operation = await ai.fileSearchStores.uploadToFileSearchStore({
  file: 'file.txt',
  fileSearchStoreName: fileSearchStore.name,
  config: {
    displayName: 'file-name',
    chunkingConfig: {
      whiteSpaceConfig: {
        maxTokensPerChunk: 200,
        maxOverlapTokens: 20
      }
    }
  }
});

while (!operation.done) {
  await new Promise(resolve => setTimeout(resolve, 5000));
  operation = await ai.operations.get({ operation });
}
console.log("Custom chunking complete.");

Java

import com.google.genai.Client;
import com.google.genai.types.ChunkingConfig;
import com.google.genai.types.UploadToFileSearchStoreConfig;
import com.google.genai.types.UploadToFileSearchStoreOperation;
import com.google.genai.types.WhiteSpaceConfig;

Client client = new Client();

UploadToFileSearchStoreOperation operation =
    client.fileSearchStores.uploadToFileSearchStore(
        "fileSearchStores/my-file-search-store",
        "sample.txt",
        UploadToFileSearchStoreConfig.builder()
            .displayName("file-name")
            .chunkingConfig(
                ChunkingConfig.builder()
                    .whiteSpaceConfig(
                        WhiteSpaceConfig.builder()
                            .maxTokensPerChunk(200)
                            .maxOverlapTokens(20)
                            .build())
                    .build())
            .build());

while (!operation.done().orElse(false)) {
  Thread.sleep(5000);
  operation = client.operations.get(operation, null);
}

System.out.println("Custom chunking complete.");

Go

package main

import (
    "context"
    "fmt"
    "log"
    "time"

    "google.golang.org/genai"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    operation, err := client.FileSearchStores.UploadToFileSearchStoreFromPath(
        ctx,
        "sample.txt",
        "fileSearchStores/my-file-search-store",
        &genai.UploadToFileSearchStoreConfig{
            DisplayName: "file-name",
            ChunkingConfig: &genai.ChunkingConfig{
                WhiteSpaceConfig: &genai.WhiteSpaceConfig{
                    MaxTokensPerChunk: genai.Ptr(int32(200)),
                    MaxOverlapTokens:  genai.Ptr(int32(20)),
                },
            },
        },
    )
    if err != nil {
        log.Fatal(err)
    }

    for !operation.Done {
        time.Sleep(5 * time.Second)
        operation, err = client.Operations.GetUploadToFileSearchStoreOperation(ctx, operation, nil)
        if err != nil {
            log.Fatal(err)
        }
    }

    fmt.Println("Custom chunking complete.")
}

REST

NUM_BYTES=$(wc -c < "sample.txt")
curl "https://generativelanguage.googleapis.com/upload/v1beta/fileSearchStores/$FILE_SEARCH_STORE_NAME:uploadToFileSearchStore?key=$GEMINI_API_KEY" \
    -D upload-header.tmp \
    -H "X-Goog-Upload-Protocol: resumable" \
    -H "X-Goog-Upload-Command: start" \
    -H "X-Goog-Upload-Header-Content-Length: $NUM_BYTES" \
    -H "X-Goog-Upload-Header-Content-Type: text/plain" \
    -H "Content-Type: application/json" \
    -d '{
      "displayName": "sample.txt",
      "chunkingConfig": {
        "whiteSpaceConfig": {
          "maxTokensPerChunk": 200,
          "maxOverlapTokens": 20
        }
      }
    }' 2> /dev/null

upload_url=$(grep -i "x-goog-upload-url: " upload-header.tmp | cut -d" " -f2 | tr -d "\r")
rm upload-header.tmp

curl "${upload_url}" \
    -H "Content-Length: $NUM_BYTES" \
    -H "X-Goog-Upload-Offset: 0" \
    -H "X-Goog-Upload-Command: upload, finalize" \
    --data-binary "@sample.txt" 2> /dev/null > upload_response.json

cat upload_response.json

Para usar o armazenamento da Pesquisa de Arquivos, transmita-o como uma ferramenta para o método interactions.create, conforme mostrado nos exemplos de Upload e Importação.

Como funciona

A Pesquisa de arquivos usa uma técnica chamada pesquisa semântica para encontrar informações relevantes para o comando do usuário. Ao contrário da pesquisa padrão baseada em palavras-chave, a pesquisa semântica entende o significado e o contexto da consulta.

Quando você importa um arquivo, ele é convertido em representações numéricas chamadas embeddings, que capturam o significado semântico do conteúdo enviado. Esses embeddings são armazenados em um banco de dados especializado da Pesquisa de arquivos. Quando você faz uma consulta, ela também é convertida em um embedding. Em seguida, o sistema realiza uma pesquisa de arquivos para encontrar os trechos de documentos mais semelhantes e relevantes no repositório de pesquisa de arquivos.

Não há time to live (TTL) para embeddings. Eles persistem até serem excluídos manualmente ou quando o modelo é descontinuado. mas os arquivos são excluídos após 48 horas.

Confira os detalhes do processo de uso da API File Search uploadToFileSearchStore:

Criar um repositório de pesquisa de arquivos: um repositório de pesquisa de arquivos contém os dados processados dos seus arquivos. É o contêiner persistente para os embeddings em que a pesquisa semântica vai operar.
Fazer upload de um arquivo e importar para uma loja da Pesquisa de arquivos: faça upload de um arquivo e importe os resultados para sua loja da Pesquisa de arquivos ao mesmo tempo. Isso cria um objeto File temporário, que é uma referência ao documento bruto. Esses dados são divididos em partes, convertidos em embeddings da pesquisa de arquivos e indexados. O objeto File é excluído após 48 horas, enquanto a importação de dados para o armazenamento da Pesquisa de Arquivos fica armazenada indefinidamente até que você decida excluí-los.
Consulta com a Pesquisa de arquivos: por fim, use a ferramenta FileSearch em uma chamada generateContent. Na configuração da ferramenta, especifique um FileSearchRetrievalResource, que aponta para o FileSearchStore que você quer pesquisar. Isso instrui o modelo a realizar uma pesquisa semântica nesse repositório específico de pesquisa de arquivos para encontrar informações relevantes que embasem a resposta.

O processo de indexação e consulta da Pesquisa de Arquivos — O processo de indexação e consulta da Pesquisa de arquivos

Neste diagrama, a linha pontilhada de Documentos para Modelo de embedding (usando gemini-embedding-001) representa a API uploadToFileSearchStore (ignorando o Armazenamento de arquivos). Caso contrário, usar a API Files para criar e importar arquivos separadamente move o processo de indexação de Documentos para Armazenamento de arquivos e, em seguida, para Modelo de embedding.

Armazenamentos da Pesquisa de arquivos

Um repositório de pesquisa de arquivos é um contêiner para os embeddings de documentos. Os arquivos brutos enviados pela API File são excluídos após 48 horas, mas os dados importados para um repositório da Pesquisa de Arquivos são armazenados indefinidamente até que você os exclua manualmente. É possível criar vários armazenamentos de pesquisa de arquivos para organizar seus documentos. A API FileSearchStore permite criar, listar, receber e excluir para gerenciar seus repositórios de pesquisa de arquivos. Os nomes dos repositórios da Pesquisa de Arquivos têm escopo global.

Confira alguns exemplos de como gerenciar suas lojas de pesquisa de arquivos:

Python

file_search_store = client.file_search_stores.create(
    config={
        'display_name': 'myfilesearchstore123',
        'embedding_model': 'models/gemini-embedding-2'
    }
)

for store in client.file_search_stores.list():
    print(store)

my_file_search_store = client.file_search_stores.get(name=file_search_store.name)

client.file_search_stores.delete(name=file_search_store.name, config={'force': True})

JavaScript

const fileSearchStore = await ai.fileSearchStores.create({
  config: {
    displayName: 'myfilesearchstore123',
    embeddingModel: 'models/gemini-embedding-2'
  }
});

const fileSearchStores = await ai.fileSearchStores.list();
for await (const store of fileSearchStores) {
  console.log(store);
}

const myFileSearchStore = await ai.fileSearchStores.get({
  name: fileSearchStore.name
});

await ai.fileSearchStores.delete({
  name: fileSearchStore.name,
  config: { force: true }
});

Java

import com.google.genai.Client;
import com.google.genai.types.CreateFileSearchStoreConfig;
import com.google.genai.types.DeleteFileSearchStoreConfig;
import com.google.genai.types.FileSearchStore;

Client client = new Client();

FileSearchStore fileSearchStore =
    client.fileSearchStores.create(
        CreateFileSearchStoreConfig.builder()
            .displayName("myfilesearchstore123")
            .embeddingModel("models/gemini-embedding-2")
            .build());

for (FileSearchStore store : client.fileSearchStores.list(null)) {
  System.out.println(store);
}

FileSearchStore myFileSearchStore =
    client.fileSearchStores.get(fileSearchStore.name().get(), null);

client.fileSearchStores.delete(
    fileSearchStore.name().get(), DeleteFileSearchStoreConfig.builder().force(true).build());

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    fileSearchStore, err := client.FileSearchStores.Create(ctx, &genai.CreateFileSearchStoreConfig{
        DisplayName:    "myfilesearchstore123",
        EmbeddingModel: "models/gemini-embedding-2",
    })
    if err != nil {
        log.Fatal(err)
    }

    for store, err := range client.FileSearchStores.All(ctx) {
        if err != nil {
            log.Fatal(err)
        }
        fmt.Println(store)
    }

    myFileSearchStore, err := client.FileSearchStores.Get(ctx, fileSearchStore.Name, nil)
    if err != nil {
        log.Fatal(err)
    }
    _ = myFileSearchStore

    err = client.FileSearchStores.Delete(ctx, fileSearchStore.Name, &genai.DeleteFileSearchStoreConfig{
        Force: genai.Ptr(true),
    })
    if err != nil {
        log.Fatal(err)
    }
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=${GEMINI_API_KEY}" \
    -H "Content-Type: application/json" \
    -d '{ "displayName": "My Store", "embedding_model": "models/gemini-embedding-2" }'

curl "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=${GEMINI_API_KEY}"

curl "https://generativelanguage.googleapis.com/v1beta/fileSearchStores/myfilesearchstore123?key=${GEMINI_API_KEY}"

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/fileSearchStores/myfilesearchstore123?key=${GEMINI_API_KEY}"

Pesquisar documentos de arquivos

É possível gerenciar documentos individuais nos seus repositórios de arquivos com a API File Search Documents para list cada documento em um repositório de pesquisa de arquivos, get informações sobre um documento e delete um documento por nome.

Python

for document_in_store in client.file_search_stores.documents.list(parent='fileSearchStores/myfilesearchstore123'):
  print(document_in_store)

file_search_document = client.file_search_stores.documents.get(name='fileSearchStores/myfilesearchstore123/documents/sampletxt123')
print(file_search_document)

client.file_search_stores.documents.delete(name='fileSearchStores/myfilesearchstore123/documents/sampletxt123', config={'force': True})

JavaScript

const documents = await ai.fileSearchStores.documents.list({
  parent: 'fileSearchStores/myfilesearchstore123'
});
for await (const doc of documents) {
  console.log(doc);
}

const fileSearchDocument = await ai.fileSearchStores.documents.get({
  name: 'fileSearchStores/myfilesearchstore123/documents/sampletxt123'
});

await ai.fileSearchStores.documents.delete({
  name: 'fileSearchStores/myfilesearchstore123/documents/sampletxt123',
  config: { force: true }
});

Java

import com.google.genai.Client;
import com.google.genai.types.DeleteDocumentConfig;
import com.google.genai.types.Document;

Client client = new Client();

for (Document documentInStore :
    client.fileSearchStores.documents.list("fileSearchStores/myfilesearchstore123", null)) {
  System.out.println(documentInStore);
}

Document fileSearchDocument =
    client.fileSearchStores.documents.get(
        "fileSearchStores/myfilesearchstore123/documents/sampletxt123", null);
System.out.println(fileSearchDocument);

client.fileSearchStores.documents.delete(
    "fileSearchStores/myfilesearchstore123/documents/sampletxt123",
    DeleteDocumentConfig.builder().force(true).build());

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    for documentInStore, err := range client.FileSearchStores.Documents.All(ctx, "fileSearchStores/myfilesearchstore123") {
        if err != nil {
            log.Fatal(err)
        }
        fmt.Println(documentInStore)
    }

    fileSearchDocument, err := client.FileSearchStores.Documents.Get(ctx, "fileSearchStores/myfilesearchstore123/documents/sampletxt123", nil)
    if err != nil {
        log.Fatal(err)
    }
    fmt.Println(fileSearchDocument)

    err = client.FileSearchStores.Documents.Delete(ctx, "fileSearchStores/myfilesearchstore123/documents/sampletxt123", &genai.DeleteDocumentConfig{
        Force: genai.Ptr(true),
    })
    if err != nil {
        log.Fatal(err)
    }
}

REST

curl "https://generativelanguage.googleapis.com/v1beta/fileSearchStores/myfilesearchstore123/documents?key=${GEMINI_API_KEY}"

curl "https://generativelanguage.googleapis.com/v1beta/fileSearchStores/myfilesearchstore123/documents/sampletxt123?key=${GEMINI_API_KEY}"

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/fileSearchStores/myfilesearchstore123/documents/sampletxt123?key=${GEMINI_API_KEY}&force=true"

Metadados do arquivo

É possível adicionar metadados personalizados aos arquivos para ajudar a filtrá-los ou fornecer contexto adicional. Os metadados são um conjunto de pares de chave-valor.

Python

op = client.file_search_stores.import_file(
    file_search_store_name=file_search_store.name,
    file_name=sample_file.name,
    config={
        'custom_metadata': [
            {"key": "author", "string_value": "Robert Graves"},
            {"key": "year", "numeric_value": 1934}
        ]
    }
)

JavaScript

let operation = await ai.fileSearchStores.importFile({
  fileSearchStoreName: fileSearchStore.name,
  fileName: sampleFile.name,
  config: {
    customMetadata: [
      { key: "author", stringValue: "Robert Graves" },
      { key: "year", numericValue: 1934 }
    ]
  }
});

Java

import com.google.genai.Client;
import com.google.genai.types.CustomMetadata;
import com.google.genai.types.ImportFileConfig;
import com.google.genai.types.ImportFileOperation;
import java.util.Arrays;

Client client = new Client();

ImportFileOperation op =
    client.fileSearchStores.importFile(
        "fileSearchStores/myfilesearchstore123",
        "files/samplefile123",
        ImportFileConfig.builder()
            .customMetadata(
                Arrays.asList(
                    CustomMetadata.builder().key("author").stringValue("Robert Graves").build(),
                    CustomMetadata.builder().key("year").numericValue(1934f).build()))
            .build());

Go

package main

import (
    "context"
    "log"

    "google.golang.org/genai"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    op, err := client.FileSearchStores.ImportFile(
        ctx,
        "fileSearchStores/myfilesearchstore123",
        "files/samplefile123",
        &genai.ImportFileConfig{
            CustomMetadata: []*genai.CustomMetadata{
                {Key: "author", StringValue: "Robert Graves"},
                {Key: "year", NumericValue: genai.Ptr(float32(1934))},
            },
        },
    )
    if err != nil {
        log.Fatal(err)
    }
    _ = op
}

Isso é útil quando você tem vários documentos em um repositório de pesquisa de arquivos e quer pesquisar apenas um subconjunto deles.

Python

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Tell me about the book 'I, Claudius'",
    tools=[{
        "type": "file_search",
        "file_search_store_names": [file_search_store.name],
        "metadata_filter": 'author="Robert Graves"',
    }]
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.type == "text":
                print(content_block.text)

JavaScript

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: "Tell me about the book 'I, Claudius'",
  tools: [{
    type: "file_search",
    file_search_store_names: [fileSearchStore.name],
    metadata_filter: 'author="Robert Graves"',
  }]
});

for (const step of interaction.steps) {
  if (step.type === 'model_output') {
    for (const contentBlock of step.content) {
      if (contentBlock.type === 'text') {
        console.log(contentBlock.text);
      }
    }
  }
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.FileSearch;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("Tell me about the book 'I, Claudius'"))
        .tools(
            Arrays.asList(
                FileSearch.builder()
                    .fileSearchStoreNames(Arrays.asList("fileSearchStores/myfilesearchstore123"))
                    .metadataFilter("author=\"Robert Graves\"")
                    .build()))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.steps().isPresent()) {
  for (Step step : interaction.steps().get()) {
    if (step instanceof ModelOutputStep) {
      ModelOutputStep outputStep = (ModelOutputStep) step;
      if (outputStep.content().isPresent()) {
        for (Content contentBlock : outputStep.content().get()) {
          if (contentBlock instanceof TextContent) {
            TextContent textContent = (TextContent) contentBlock;
            System.out.println(textContent.text().orElse(""));
          }
        }
      }
    }
  }
}

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(
            interactions.CreateModelInteraction{
                Model: interactions.Model("gemini-3.8-flash"),
                Input: interactions.NewInteractionsInput("Tell me about the book 'I, Claudius'"),
                Tools: []interactions.Tool{
                    interactions.NewTool(interactions.FileSearch{
                        FileSearchStoreNames: []string{"fileSearchStores/myfilesearchstore123"},
                        MetadataFilter:       genai.Ptr(`author="Robert Graves"`),
                    }),
                },
            },
        ),
    })
    if err != nil {
        log.Fatal(err)
    }

    for _, step := range resp.Interaction.Steps {
        if step.ModelOutputStep != nil {
            for _, content := range step.ModelOutputStep.Content {
                if content.TextContent != nil {
                    fmt.Println(content.TextContent.Text)
                }
            }
        }
    }
}

REST

curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
            "model": "gemini-3.8-flash",
            "input": [{"type": "text", "text": "Tell me about the book I, Claudius"}],
            "tools": [{
                "type": "file_search",
                "file_search_store_names": ["'$STORE_NAME'"],
                "metadata_filter": "author = \"Robert Graves\""
            }]
        }' 2> /dev/null > response.json

cat response.json

Confira orientações sobre como implementar a sintaxe de filtro de lista para metadata_filter em google.aip.dev/160.

Pesquisa de arquivos multimodal

A Pesquisa Multimodal de Arquivos permite incorporar e pesquisar imagens de forma nativa, permitindo aplicativos RAG multimodais avançados.

Configurar o modelo de embedding

Ao criar um FileSearchStore, é necessário substituir o modelo de embedding padrão somente de texto para usar um modelo multimodal. Use models/gemini-embedding-2 para processar textos e imagens.

Python

store = client.file_search_stores.create(
    config={
        "display_name": "Multimodal Catalog",
        "embedding_model": "models/gemini-embedding-2",
    }
)

JavaScript

const fileSearchStore = await ai.fileSearchStores.create({
  config: {
    displayName: "Multimodal Catalog",
    embeddingModel: "models/gemini-embedding-2",
  },
});

Java

import com.google.genai.Client;
import com.google.genai.types.CreateFileSearchStoreConfig;
import com.google.genai.types.FileSearchStore;

Client client = new Client();

FileSearchStore store =
    client.fileSearchStores.create(
        CreateFileSearchStoreConfig.builder()
            .displayName("Multimodal Catalog")
            .embeddingModel("models/gemini-embedding-2")
            .build());

Go

package main

import (
    "context"
    "log"

    "google.golang.org/genai"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    store, err := client.FileSearchStores.Create(ctx, &genai.CreateFileSearchStoreConfig{
        DisplayName:    "Multimodal Catalog",
        EmbeddingModel: "models/gemini-embedding-2",
    })
    if err != nil {
        log.Fatal(err)
    }
    _ = store
}

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=$GEMINI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "display_name": "Multimodal Catalog",
      "embedding_model": "models/gemini-embedding-2"
    }'

Fazer upload de imagens

Depois de criar o armazenamento com um modelo de embedding multimodal, é possível fazer upload de arquivos de imagem diretamente usando as mesmas APIs de upload descritas em Fazer upload diretamente para o armazenamento da Pesquisa de arquivos ou Importar arquivos.

Requisitos do arquivo de imagem:

Os arquivos de imagem precisam ter uma resolução máxima de 4K x 4K pixels.
Os formatos aceitos são PNG e JPEG.

Citações

Ao usar a Pesquisa de arquivos, a resposta do modelo pode incluir citações que especificam quais partes dos documentos enviados foram usadas para gerar a resposta. Isso ajuda na checagem de fatos e na verificação.

É possível acessar as informações de citação pelo atributo annotations dentro dos blocos content da etapa model_output da resposta.

Python

for step in interaction.steps:
    if step.type == 'model_output':
        for content in step.content:
            if content.type == 'text' and content.annotations:
                print(content.annotations)

JavaScript

for (const step of interaction.steps) {
  if (step.type === 'model_output') {
    for (const contentBlock of step.content) {
      if (contentBlock.type === 'text' && contentBlock.annotations) {
        console.log(JSON.stringify(contentBlock.annotations, null, 2));
      }
    }
  }
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.FileSearch;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("Can you tell me about [insert question]"))
        .tools(
            Arrays.asList(
                FileSearch.builder()
                    .fileSearchStoreNames(Arrays.asList("fileSearchStores/myfilesearchstore123"))
                    .build()))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.steps().isPresent()) {
  for (Step step : interaction.steps().get()) {
    if (step instanceof ModelOutputStep) {
      ModelOutputStep outputStep = (ModelOutputStep) step;
      if (outputStep.content().isPresent()) {
        for (Content content : outputStep.content().get()) {
          if (content instanceof TextContent) {
            TextContent textContent = (TextContent) content;
            if (textContent.annotations().isPresent()) {
              System.out.println(textContent.annotations().get());
            }
          }
        }
      }
    }
  }
}

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(
            interactions.CreateModelInteraction{
                Model: interactions.Model("gemini-3.8-flash"),
                Input: interactions.NewInteractionsInput("Can you tell me about [insert question]"),
                Tools: []interactions.Tool{
                    interactions.NewTool(interactions.FileSearch{
                        FileSearchStoreNames: []string{"fileSearchStores/myfilesearchstore123"},
                    }),
                },
            },
        ),
    })
    if err != nil {
        log.Fatal(err)
    }

    for _, step := range resp.Interaction.Steps {
        if step.ModelOutputStep != nil {
            for _, content := range step.ModelOutputStep.Content {
                if content.TextContent != nil && len(content.TextContent.Annotations) > 0 {
                    fmt.Println(content.TextContent.Annotations)
                }
            }
        }
    }
}

REST

{
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "...",
          "annotations": [
            {
              "type": "file_citation",
              "file_name": "sample.txt",
              "source": "..."
            }
          ]
        }
      ]
    }
  ]
}

Para informações detalhadas sobre a estrutura das citações, consulte a referência da API Interactions.

Números de página

Quando você usa a Pesquisa de arquivos com documentos que têm páginas (como PDFs), a resposta do modelo pode incluir o número da página em que as informações foram encontradas. É possível acessar essas informações pelo atributo page_number de uma anotação file_citation.

Python

for step in interaction.steps:
    if step.type == "model_output":
        for content in step.content:
            if content.type == "text" and content.annotations:
                for annotation in content.annotations:
                    if annotation.type == "file_citation" and annotation.page_number:
                        print(f"Cited Page: {annotation.page_number}")

JavaScript

for (const step of interaction.steps) {
  if (step.type === 'model_output') {
    for (const block of step.content) {
      if (block.type === 'text' && block.annotations) {
        for (const annotation of block.annotations) {
          if (annotation.type === 'file_citation' && annotation.pageNumber) {
            console.log(`Cited Page: ${annotation.pageNumber}`);
          }
        }
      }
    }
  }
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Annotation;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.FileCitation;
import com.google.genai.gaos.models.interactions.FileSearch;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("Can you tell me about [insert question]"))
        .tools(
            Arrays.asList(
                FileSearch.builder()
                    .fileSearchStoreNames(Arrays.asList("fileSearchStores/myfilesearchstore123"))
                    .build()))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.steps().isPresent()) {
  for (Step step : interaction.steps().get()) {
    if (step instanceof ModelOutputStep) {
      ModelOutputStep outputStep = (ModelOutputStep) step;
      if (outputStep.content().isPresent()) {
        for (Content content : outputStep.content().get()) {
          if (content instanceof TextContent) {
            TextContent textContent = (TextContent) content;
            if (textContent.annotations().isPresent()) {
              for (Annotation annotation : textContent.annotations().get()) {
                if (annotation instanceof FileCitation) {
                  FileCitation citation = (FileCitation) annotation;
                  if (citation.pageNumber().isPresent()) {
                    System.out.println("Cited Page: " + citation.pageNumber().get());
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(
            interactions.CreateModelInteraction{
                Model: interactions.Model("gemini-3.8-flash"),
                Input: interactions.NewInteractionsInput("Can you tell me about [insert question]"),
                Tools: []interactions.Tool{
                    interactions.NewTool(interactions.FileSearch{
                        FileSearchStoreNames: []string{"fileSearchStores/myfilesearchstore123"},
                    }),
                },
            },
        ),
    })
    if err != nil {
        log.Fatal(err)
    }

    for _, step := range resp.Interaction.Steps {
        if step.ModelOutputStep != nil {
            for _, content := range step.ModelOutputStep.Content {
                if content.TextContent != nil {
                    for _, annotation := range content.TextContent.Annotations {
                        if annotation.FileCitation != nil && annotation.FileCitation.PageNumber != nil {
                            fmt.Println("Cited Page:", *annotation.FileCitation.PageNumber)
                        }
                    }
                }
            }
        }
    }
}

REST

{
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "...",
          "annotations": [
            {
              "type": "file_citation",
              "file_name": "document.pdf",
              "page_number": 1,
              "source": "..."
            }
          ]
        }
      ]
    }
  ]
}

Citações de mídia

Quando o modelo faz referência a um bloco de imagem durante a geração, a API retorna uma anotação do tipo file_citation nas anotações que incluem um media_id. É possível usar esse ID para baixar o trecho exato da imagem referenciado pelo modelo. Esse media_id é persistente em várias chamadas de pesquisa, o que permite recuperar de forma confiável a mesma imagem ou armazená-la em cache usando o ID.

O snippet a seguir é um exemplo de etapa de resposta REST:

{
  "type": "model_output",
  "content": [
    {
      "type": "text",
      "text": "...",
      "annotations": [
        {
          "type": "file_citation",
          "file_name": "product_image",
          "media_id": "fileSearchStores/my-store-123/media/BlobId-456"
        }
      ]
    }
  ]
}

Os snippets de código abaixo demonstram como recuperar o media_id e fazer o download da mídia:

Python

for step in interaction.steps:
    if step.type == "model_output":
        for content in step.content:
            if content.type == "text" and content.annotations:
                for annotation in content.annotations:
                    if annotation.type == "file_citation" and annotation.media_id:
                        print(f"Cited Media ID: {annotation.media_id}")
                        blob_content = client.file_search_stores.download_media(
                            media_id=annotation.media_id
                        )

JavaScript

for (const step of interaction.steps) {
  if (step.type === 'model_output') {
    for (const block of step.content) {
      if (block.type === 'text' && block.annotations) {
        for (const annotation of block.annotations) {
          if (annotation.type === 'file_citation' && annotation.mediaId) {
            console.log(`Cited Media ID: ${annotation.mediaId}`);
            const blobContent = await ai.fileSearchStores.downloadMedia(annotation.mediaId);
          }
        }
      }
    }
  }
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Annotation;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.FileCitation;
import com.google.genai.gaos.models.interactions.FileSearch;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("Can you tell me about [insert question]"))
        .tools(
            Arrays.asList(
                FileSearch.builder()
                    .fileSearchStoreNames(Arrays.asList("fileSearchStores/myfilesearchstore123"))
                    .build()))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.steps().isPresent()) {
  for (Step step : interaction.steps().get()) {
    if (step instanceof ModelOutputStep) {
      ModelOutputStep outputStep = (ModelOutputStep) step;
      if (outputStep.content().isPresent()) {
        for (Content content : outputStep.content().get()) {
          if (content instanceof TextContent) {
            TextContent textContent = (TextContent) content;
            if (textContent.annotations().isPresent()) {
              for (Annotation annotation : textContent.annotations().get()) {
                if (annotation instanceof FileCitation) {
                  FileCitation citation = (FileCitation) annotation;
                  if (citation.mediaId().isPresent()) {
                    System.out.println("Cited Media ID: " + citation.mediaId().get());
                    byte[] blobContent =
                        client.fileSearchStores.downloadMedia(citation.mediaId().get(), null);
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(
            interactions.CreateModelInteraction{
                Model: interactions.Model("gemini-3.8-flash"),
                Input: interactions.NewInteractionsInput("Can you tell me about [insert question]"),
                Tools: []interactions.Tool{
                    interactions.NewTool(interactions.FileSearch{
                        FileSearchStoreNames: []string{"fileSearchStores/myfilesearchstore123"},
                    }),
                },
            },
        ),
    })
    if err != nil {
        log.Fatal(err)
    }

    for _, step := range resp.Interaction.Steps {
        if step.ModelOutputStep != nil {
            for _, content := range step.ModelOutputStep.Content {
                if content.TextContent != nil {
                    for _, annotation := range content.TextContent.Annotations {
                        if annotation.FileCitation != nil && annotation.FileCitation.MediaID != nil {
                            fmt.Println("Cited Media ID:", *annotation.FileCitation.MediaID)
                            blobContent, err := client.FileSearchStores.DownloadMedia(ctx, *annotation.FileCitation.MediaID, nil)
                            if err != nil {
                                log.Fatal(err)
                            }
                            _ = blobContent
                        }
                    }
                }
            }
        }
    }
}

REST

curl -X GET "https://generativelanguage.googleapis.com/v1/fileSearchStores/my-store-123/media/BlobId-456" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

Metadados personalizados

Se você adicionou metadados personalizados aos seus arquivos, é possível acessar essas informações nas anotações da resposta do modelo. Isso é útil para transmitir contexto adicional (como URLs, números de página ou autores) dos documentos de origem para a lógica do aplicativo. Cada anotação de citação do tipo file_citation contém esses metadados personalizados.

Python

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Tell me about [insert question]",
    tools=[{
        "type": "file_search",
        "file_search_store_names": [file_search_store.name]
    }]
)

for step in interaction.steps:
    if step.type == "model_output":
        for content_block in step.content:
            if content_block.annotations:
                for annotation in content_block.annotations:
                    print(annotation)

JavaScript

const interaction = await ai.interactions.create({
  model: "gemini-3.8-flash",
  input: "Tell me about [insert question]",
  tools: [{
    type: "file_search",
    file_search_store_names: [fileSearchStore.name]
  }]
});

for (const step of interaction.steps) {
  if (step.type === 'model_output') {
    for (const contentBlock of step.content) {
      if (contentBlock.annotations) {
        contentBlock.annotations.forEach((annotation) => {
          console.log(annotation);
        });
      }
    }
  }
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Annotation;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.FileSearch;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ModelOutputStep;
import com.google.genai.gaos.models.interactions.Step;
import com.google.genai.gaos.models.interactions.TextContent;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("Tell me about [insert question]"))
        .tools(
            Arrays.asList(
                FileSearch.builder()
                    .fileSearchStoreNames(Arrays.asList("fileSearchStores/myfilesearchstore123"))
                    .build()))
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

if (interaction.steps().isPresent()) {
  for (Step step : interaction.steps().get()) {
    if (step instanceof ModelOutputStep) {
      ModelOutputStep outputStep = (ModelOutputStep) step;
      if (outputStep.content().isPresent()) {
        for (Content contentBlock : outputStep.content().get()) {
          if (contentBlock instanceof TextContent) {
            TextContent textContent = (TextContent) contentBlock;
            if (textContent.annotations().isPresent()) {
              for (Annotation annotation : textContent.annotations().get()) {
                System.out.println(annotation);
              }
            }
          }
        }
      }
    }
  }
}

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(
            interactions.CreateModelInteraction{
                Model: interactions.Model("gemini-3.8-flash"),
                Input: interactions.NewInteractionsInput("Tell me about [insert question]"),
                Tools: []interactions.Tool{
                    interactions.NewTool(interactions.FileSearch{
                        FileSearchStoreNames: []string{"fileSearchStores/myfilesearchstore123"},
                    }),
                },
            },
        ),
    })
    if err != nil {
        log.Fatal(err)
    }

    for _, step := range resp.Interaction.Steps {
        if step.ModelOutputStep != nil {
            for _, content := range step.ModelOutputStep.Content {
                if content.TextContent != nil {
                    for _, annotation := range content.TextContent.Annotations {
                        fmt.Println(annotation)
                    }
                }
            }
        }
    }
}

REST

{
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "...",
          "annotations": [
            {
              "file_name": "...",
              "source": "...",
              "custom_metadata": [
                {
                  "key": "author",
                  "string_value": "Robert Graves"
                },
                {
                  "key": "year",
                  "numeric_value": 1934
                }
              ]
            }
          ]
        }
      ]
    }
  ]
}

Resposta estruturada

A partir dos modelos do Gemini 3, é possível combinar a ferramenta de pesquisa de arquivos com saídas estruturadas.

Python

from pydantic import BaseModel, Field

class Money(BaseModel):
    amount: str = Field(description="The numerical part of the amount.")
    currency: str = Field(description="The currency of amount.")

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="What is the minimum hourly wage in Tokyo right now?",
    tools=[{
        "type": "file_search",
        "file_search_store_names": [file_search_store.name]
    }],
    response_format={
        "type": "text",
        "mime_type": "application/json",
        "schema": Money.model_json_schema()
    },
)
result = Money.model_validate_json(interaction.output_text)
print(result)

JavaScript

import { z } from "zod";

const moneyJsonSchema = {
  type: "object",
  properties: {
    amount: { type: "string", description: "The numerical part of the amount." },
    currency: { type: "string", description: "The currency of amount." }
  },
  required: ["amount", "currency"]
};

const moneySchema = z.fromJSONSchema(moneyJsonSchema);

async function run() {
  const interaction = await ai.interactions.create({
    model: "gemini-3.8-flash",
    input: "What is the minimum hourly wage in Tokyo right now?",
    tools: [{
      type: "file_search",
      file_search_store_names: [fileSearchStore.name],
    }],
    response_format: {
      type: 'text',
      mime_type: 'application/json',
      schema: moneyJsonSchema
    },
  });

  const result = moneySchema.parse(JSON.parse(interaction.output_text));
  console.log(result);
}

run();

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.CreateModelInteractionResponseFormat;
import com.google.genai.gaos.models.interactions.FileSearch;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Model;
import com.google.genai.gaos.models.interactions.ResponseFormat;
import com.google.genai.gaos.models.interactions.TextResponseFormat;
import com.google.genai.gaos.models.interactions.TextResponseFormatMimeType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.Arrays;
import java.util.HashMap;
import java.util.Map;

Client client = new Client();

Map<String, Object> properties = new HashMap<>();

Map<String, Object> amountProp = new HashMap<>();
amountProp.put("type", "string");
amountProp.put("description", "The numerical part of the amount.");
properties.put("amount", amountProp);

Map<String, Object> currencyProp = new HashMap<>();
currencyProp.put("type", "string");
currencyProp.put("description", "The currency of amount.");
properties.put("currency", currencyProp);

Map<String, Object> moneyJsonSchema = new HashMap<>();
moneyJsonSchema.put("type", "object");
moneyJsonSchema.put("properties", properties);
moneyJsonSchema.put("required", Arrays.asList("amount", "currency"));

CreateModelInteractionResponseFormat format =
    CreateModelInteractionResponseFormat.of(
        ResponseFormat.of(
            TextResponseFormat.builder()
                .mimeType(TextResponseFormatMimeType.APPLICATION_JSON)
                .schema(moneyJsonSchema)
                .build()));

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model(Model.of("gemini-3.8-flash"))
        .input(InteractionsInput.of("What is the minimum hourly wage in Tokyo right now?"))
        .tools(
            Arrays.asList(
                FileSearch.builder()
                    .fileSearchStoreNames(Arrays.asList("fileSearchStores/myfilesearchstore123"))
                    .build()))
        .responseFormat(format)
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();

System.out.println(interaction.outputText().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    moneyJsonSchema := map[string]any{
        "type": "object",
        "properties": map[string]any{
            "amount": map[string]any{
                "type":        "string",
                "description": "The numerical part of the amount.",
            },
            "currency": map[string]any{
                "type":        "string",
                "description": "The currency of amount.",
            },
        },
        "required": []string{"amount", "currency"},
    }

    format := interactions.NewCreateModelInteractionResponseFormat(
        interactions.NewResponseFormat(interactions.TextResponseFormat{
            MimeType: interactions.TextResponseFormatMimeTypeApplicationJSON.ToPointer(),
            Schema:   moneyJsonSchema,
        }),
    )

    resp, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(
            interactions.CreateModelInteraction{
                Model: interactions.Model("gemini-3.8-flash"),
                Input: interactions.NewInteractionsInput("What is the minimum hourly wage in Tokyo right now?"),
                Tools: []interactions.Tool{
                    interactions.NewTool(interactions.FileSearch{
                        FileSearchStoreNames: []string{"fileSearchStores/myfilesearchstore123"},
                    }),
                },
                ResponseFormat: &format,
            },
        ),
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Println(resp.Interaction.GetOutputText())
}

REST

curl "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H 'Content-Type: application/json' \
  -X POST \
  -d '{
    "model": "gemini-3.8-flash",
    "input": "What is the minimum hourly wage in Tokyo right now?",
    "tools": [{
      "type": "file_search",
      "file_search_store_names": ["$FILE_SEARCH_STORE_NAME"]
    }],
    "response_format": {
      "type": "text",
      "mime_type": "application/json",
      "schema": {
        "type": "object",
        "properties": {
          "amount": {"type": "string", "description": "The numerical part of the amount."},
          "currency": {"type": "string", "description": "The currency of amount."}
        },
        "required": ["amount", "currency"]
      }
    }
  }'

Modelos compatíveis

Os seguintes modelos são compatíveis com a Pesquisa de Arquivos:

Modelo	Pesquisa de arquivos
Gemini 4 Argon	✔️
Gemini 3.8 Flash	✔️
Gemini 3.6 Flash	✔️
Gemini 3.5 Flash-Lite	✔️
Pré-lançamento do Gemini 3.1 Pro	✔️
Gemini 3.1 Flash-Lite	✔️
Pré-lançamento do Gemini 3 Flash	✔️

Combinações de ferramentas compatíveis

Os modelos Gemini 4 e Gemini 3 permitem combinar ferramentas integradas (como a Pesquisa de Arquivos) com ferramentas personalizadas (chamada de função). Saiba mais na página de combinações de ferramentas.

Tipos de arquivo compatíveis

A Pesquisa de arquivos é compatível com vários formatos de arquivo, listados nas seções a seguir.

Tipos de arquivo de aplicativo

application/dart
application/ecmascript
application/json
application/ms-java
application/msword
application/pdf
application/sql
application/typescript
application/vnd.curl
application/vnd.dart
application/vnd.ibm.secure-container
application/vnd.jupyter
application/vnd.ms-excel
application/vnd.oasis.opendocument.text
application/vnd.openxmlformats-officedocument.presentationml.presentation
application/vnd.openxmlformats-officedocument.spreadsheetml.sheet
application/vnd.openxmlformats-officedocument.wordprocessingml.document
application/vnd.openxmlformats-officedocument.wordprocessingml.template
application/x-csh
application/x-hwp
application/x-hwp-v5
application/x-latex
application/x-php
application/x-powershell
application/x-sh
application/x-shellscript
application/x-tex
application/x-zsh
application/xml
application/zip

Tipos de arquivo de texto

text/1d-interleaved-parityfec
text/RED
text/SGML
text/cache-manifest
text/calendar
text/cql
text/cql-extension
text/cql-identifier
text/css
text/csv
text/csv-schema
text/dns
text/encaprtp
text/enriched
text/example
text/fhirpath
text/flexfec
text/fwdred
text/gff3
text/grammar-ref-list
text/hl7v2
text/html
text/javascript
text/jcr-cnd
text/jsx
text/markdown
text/mizar
text/n3
text/parameters
text/parityfec
text/php
text/plain
text/provenance-notation
text/prs.fallenstein.rst
text/prs.lines.tag
text/prs.prop.logic
text/raptorfec
text/rfc822-headers
text/rtf
text/rtp-enc-aescm128
text/rtploopback
text/rtx
text/sgml
text/shaclc
text/shex
text/spdx
text/strings
text/t140
text/tab-separated-values
text/texmacs
text/troff
text/tsv
text/tsx
text/turtle
text/ulpfec
text/uri-list
text/vcard
text/vnd.DMClientScript
text/vnd.IPTC.NITF
text/vnd.IPTC.NewsML
text/vnd.a
text/vnd.abc
text/vnd.ascii-art
text/vnd.curl
text/vnd.debian.copyright
text/vnd.dvb.subtitle
text/vnd.esmertec.theme-descriptor
text/vnd.exchangeable
text/vnd.familysearch.gedcom
text/vnd.ficlab.flt
text/vnd.fly
text/vnd.fmi.flexstor
text/vnd.gml
text/vnd.graphviz
text/vnd.hans
text/vnd.hgl
text/vnd.in3d.3dml
text/vnd.in3d.spot
text/vnd.latex-z
text/vnd.motorola.reflex
text/vnd.ms-mediapackage
text/vnd.net2phone.commcenter.command
text/vnd.radisys.msml-basic-layout
text/vnd.senx.warpscript
text/vnd.sosi
text/vnd.sun.j2me.app-descriptor
text/vnd.trolltech.linguist
text/vnd.wap.si
text/vnd.wap.sl
text/vnd.wap.wml
text/vnd.wap.wmlscript
text/vtt
text/wgsl
text/x-asm
text/x-bibtex
text/x-boo
text/x-c
text/x-c++hdr
text/x-c++src
text/x-cassandra
text/x-chdr
text/x-coffeescript
text/x-component
text/x-csh
text/x-csharp
text/x-csrc
text/x-cuda
text/x-d
text/x-diff
text/x-dsrc
text/x-emacs-lisp
text/x-erlang
text/x-gff3
text/x-go
text/x-haskell
text/x-java
text/x-java-properties
text/x-java-source
text/x-kotlin
text/x-lilypond
text/x-lisp
text/x-literate-haskell
text/x-lua
text/x-moc
text/x-objcsrc
text/x-pascal
text/x-pcs-gcd
text/x-perl
text/x-perl-script
text/x-python
text/x-python-script
text/x-r-markdown
text/x-rsrc
text/x-rst
text/x-ruby-script
text/x-rust
text/x-sass
text/x-scala
text/x-scheme
text/x-script.python
text/x-scss
text/x-setext
text/x-sfv
text/x-sh
text/x-siesta
text/x-sos
text/x-sql
text/x-swift
text/x-tcl
text/x-tex
text/x-vbasic
text/x-vcalendar
text/xml
text/xml-dtd
text/xml-external-parsed-entity
text/yaml

Limitações

API Live:a Pesquisa de Arquivos não é compatível com a API Live.
Incompatibilidade de ferramentas:as ferramentas de embasamento integradas não podem ser combinadas. Por exemplo, a Pesquisa de Arquivos não pode ser usada simultaneamente com o embasamento com a Pesquisa Google ou o contexto de URL na mesma solicitação.

Limites de taxas

A API File Search tem os seguintes limites para garantir a estabilidade do serviço:

Tamanho máximo do arquivo / limite por documento: 100 MB
Tamanho total dos repositórios de pesquisa de arquivos do projeto (com base no nível do usuário):
- Sem custo financeiro: 1 GB
- Nível 1: 10 GB
- Nível 2: 100 GB
- Nível 3: 1 TB
Recomendação: limite o tamanho de cada armazenamento da Pesquisa de Arquivos a menos de 20 GB para garantir latências de recuperação ideais.

Preços

As incorporações são cobradas no momento da indexação com base nos preços de incorporação atuais.
O armazenamento não tem custo financeiro.
Os embeddings de tempo de consulta não têm custo financeiro.
Os tokens de documento recuperados são cobrados como tokens de contexto normais.

A seguir

Acesse a referência da API para File Search Stores e Documents do File Search.