檔案搜尋

Gemini API 可透過檔案搜尋工具啟用檢索增強生成 (RAG) 功能。檔案搜尋會匯入、分塊及建立資料索引,以便根據使用者的提示快速擷取相關資訊。接著,這項資訊會做為模型的背景資訊,讓模型提供更準確且相關的答案。

您可以使用 uploadToFileSearchStore API 直接將現有檔案上傳至檔案搜尋商店,或分開上傳,然後 importFile,以便同時建立檔案。

直接上傳至檔案搜尋商店

以下範例說明如何直接將檔案上傳至檔案儲存空間:

Python

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

client = genai.Client()

# Create the File Search store with an optional display name
file_search_store = client.file_search_stores.create(config={'display_name': 'your-fileSearchStore-name'})

# Upload and import a file into the File Search store, supply a file name which will be visible in citations
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',
  }
)

# Wait until import is complete
while not operation.done:
    time.sleep(5)
    operation = client.operations.get(operation)

# Ask a question about the file
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="""Can you tell me about Robert Graves""",
    config=types.GenerateContentConfig(
        tools=[
            file_search=(
                  file_search_store_names=[file_search_store.name]
            )
        ]
    )
)

print(response.text)

JavaScript

const { GoogleGenAI } = require('@google/genai');

const ai = new GoogleGenAI({});

async function run() {
  // Create the File Search store with an optional display name
  const fileSearchStore = await ai.fileSearchStores.create({
    config: { displayName: 'your-fileSearchStore-name' }
  });

  // Upload and import a file into the File Search store, supply a file name which will be visible in citations
  let operation = await ai.fileSearchStores.uploadToFileSearchStore({
    file: 'file.txt',
    fileSearchStoreName: fileSearchStore.name,
    config: {
      displayName: 'file-name',
    }
  });

  // Wait until import is complete
  while (!operation.done) {
    await new Promise(resolve => setTimeout(resolve, 5000));
    operation = await ai.operations.get({ operation });
  }

  // Ask a question about the file
  const response = await ai.models.generateContent({
    model: "gemini-2.5-flash",
    contents: "Can you tell me about Robert Graves",
    config: {
      tools: [
        {
          fileSearch: {
            fileSearchStoreNames: [fileSearchStore.name]
          }
        }
      ]
    }
  });

  console.log(response.text);
}

run();

REST

FILE_PATH="path/to/sample.pdf"
MIME_TYPE=$(file -b --mime-type "${FILE_PATH}")
NUM_BYTES=$(wc -c < "${FILE_PATH}")

# Create a FileSearchStore
STORE_RESPONSE=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=${GEMINI_API_KEY}" \
    -H "Content-Type: application/json" \
    -d '{ "displayName": "My Store" }')

# Extract the store name (format: fileSearchStores/xxxxxxx)
STORE_NAME=$(echo $STORE_RESPONSE | jq -r '.name')

# Initiate Resumable Upload to the Store
TMP_HEADER="upload-header.tmp"

curl -s -D "${TMP_HEADER}" \ "https://generativelanguage.googleapis.com/upload/v1beta/${STORE_NAME}:uploadToFileSearchStore?key=${GEMINI_API_KEY}" \
  -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: ${MIME_TYPE}" \
  -H "Content-Type: application/json" > /dev/null

# Extract upload_url from headers
UPLOAD_URL=$(grep -i "x-goog-upload-url: " "${TMP_HEADER}" | cut -d" " -f2 | tr -d "\r")
rm "${TMP_HEADER}"

# --- Upload the actual bytes ---
curl "${UPLOAD_URL}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${FILE_PATH}" 2> /dev/null

# Generate content using the FileSearchStore
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
            "contents": [{
                "parts":[{"text": "What does the research say about ..."}]          
            }],
            "tools": [{
                "file_search": { "file_search_store_names":["'$STORE_NAME'"] }
            }]
        }' 2> /dev/null > response.json

cat response.json

詳情請參閱 uploadToFileSearchStore 的 API 參考資料。

匯入檔案

或者,你也可以上傳現有檔案,然後匯入檔案儲存空間:

Python

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

client = genai.Client()

# Upload the file using the Files API, supply a file name which will be visible in citations
sample_file = client.files.upload(file='sample.txt', config={'name': 'display_file_name'})

# Create the File Search store with an optional display name
file_search_store = client.file_search_stores.create(config={'display_name': 'your-fileSearchStore-name'})

# Import the file into the File Search store
operation = client.file_search_stores.import_file(
    file_search_store_name=file_search_store.name,
    file_name=sample_file.name
)

# Wait until import is complete
while not operation.done:
    time.sleep(5)
    operation = client.operations.get(operation)

# Ask a question about the file
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="""Can you tell me about Robert Graves""",
    config=types.GenerateContentConfig(
        tools=[
            file_search=(
                  file_search_store_names=[file_search_store.name]
            )
        ]
    )
)

print(response.text)

JavaScript

const { GoogleGenAI } = require('@google/genai');

const ai = new GoogleGenAI({});

async function run() {
  // Upload the file using the Files API, supply a file name which will be visible in citations
  const sampleFile = await ai.files.upload({
    file: 'sample.txt',
    config: { name: 'file-name' }
  });

  // Create the File Search store with an optional display name
  const fileSearchStore = await ai.fileSearchStores.create({
    config: { displayName: 'your-fileSearchStore-name' }
  });

  // Import the file into the File Search store
  let operation = await ai.fileSearchStores.importFile({
    fileSearchStoreName: fileSearchStore.name,
    fileName: sampleFile.name
  });

  // Wait until import is complete
  while (!operation.done) {
    await new Promise(resolve => setTimeout(resolve, 5000));
    operation = await ai.operations.get({ operation: operation });
  }

  // Ask a question about the file
  const response = await ai.models.generateContent({
    model: "gemini-2.5-flash",
    contents: "Can you tell me about Robert Graves",
    config: {
      tools: [
        {
          fileSearch: {
            fileSearchStoreNames: [fileSearchStore.name]
          }
        }
      ]
    }
  });

  console.log(response.text);
}

run();

REST

FILE_PATH="path/to/sample.pdf"
MIME_TYPE=$(file -b --mime-type "${FILE_PATH}")
NUM_BYTES=$(wc -c < "${FILE_PATH}")

# Create a FileSearchStore
STORE_RESPONSE=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=${GEMINI_API_KEY}" \
    -H "Content-Type: application/json" \
    -d '{ "displayName": "My Store" }')

STORE_NAME=$(echo $STORE_RESPONSE | jq -r '.name')

# Initiate Resumable Upload to the Store
TMP_HEADER="upload-header.tmp"

curl -s -X POST "https://generativelanguage.googleapis.com/upload/v1beta/files?key=${GEMINI_API_KEY}" \
  -D "${TMP_HEADER}" \
  -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: ${MIME_TYPE}" \
  -H "Content-Type: application/json" 2> /dev/null

UPLOAD_URL=$(grep -i "x-goog-upload-url: " "${TMP_HEADER}" | cut -d" " -f2 | tr -d "\r")
rm "${TMP_HEADER}"

# Upload the actual bytes.
curl -s -X POST "${UPLOAD_URL}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${FILE_PATH}" 2> /dev/null > file_info.json

file_uri=$(jq ".file.name" file_info.json)

# Import files into the file search store
operation_name=$(curl "https://generativelanguage.googleapis.com/v1beta/${STORE_NAME}:importFile?key=${GEMINI_API_KEY}" \
  -H "Content-Type: application/json" \
  -X POST \
  -d '{
        "file_name":'$file_uri'
    }' | jq -r .name)

# Wait for long running operation to complete
while true; do
  # Get the full JSON status and store it in a variable.
  status_response=$(curl -s -H "x-goog-api-key: $GEMINI_API_KEY" "https://generativelanguage.googleapis.com/v1beta/${operation_name}")

  # Check the "done" field from the JSON stored in the variable.
  is_done=$(echo "${status_response}" | jq .done)

  if [ "${is_done}" = "true" ]; then
    break
  fi
  # Wait for 10 seconds before checking again.
  sleep 10
done

# Generate content using the FileSearchStore
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=${GEMINI_API_KEY}" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
            "contents": [{
                "parts":[{"text": "What does the research say about ..."}]          
            }],
            "tools": [{
                "file_search": { "file_search_store_names":["'$STORE_NAME'"] }
            }]
        }' 2> /dev/null > response.json

cat response.json

詳情請參閱 importFile 的 API 參考資料。

分塊設定

將檔案匯入檔案搜尋商店時,系統會自動將檔案分成多個區塊、嵌入、建立索引,然後上傳至檔案搜尋商店。如要進一步控管分塊策略,可以指定 chunking_config 設定,為每個分塊設定詞元數量上限,以及重疊詞元數量上限。

Python

# Upload and import and upload the file into the File Search store with a custom chunking configuration
operation = client.file_search_stores.upload_to_file_search_store(
    file_search_store_name=file_search_store.name,
    file_name=sample_file.name,
    config={
        'chunking_config': {
          'white_space_config': {
            'max_tokens_per_chunk': 200,
            'max_overlap_tokens': 20
          }
        }
    }
)

JavaScript

// Upload and import and upload the file into the File Search store with a custom chunking configuration
let operation = await ai.fileSearchStores.uploadToFileSearchStore({
  file: 'file.txt',
  fileSearchStoreName: fileSearchStore.name,
  config: {
    displayName: 'file-name',
    chunkingConfig: {
      whiteSpaceConfig: {
        maxTokensPerChunk: 200,
        maxOverlapTokens: 20
      }
    }
  }
});

REST

FILE_PATH="path/to/sample.pdf"
MIME_TYPE=$(file -b --mime-type "${FILE_PATH}")
NUM_BYTES=$(wc -c < "${FILE_PATH}")

# Create a FileSearchStore
STORE_RESPONSE=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=${GEMINI_API_KEY}" \
    -H "Content-Type: application/json" \
    -d '{ "displayName": "My Store" }')

# Extract the store name (format: fileSearchStores/xxxxxxx)
STORE_NAME=$(echo $STORE_RESPONSE | jq -r '.name')

# Initiate Resumable Upload to the Store
TMP_HEADER="upload-header.tmp"

curl -s -D "${TMP_HEADER}" \ "https://generativelanguage.googleapis.com/upload/v1beta/${STORE_NAME}:uploadToFileSearchStore?key=${GEMINI_API_KEY}" \
  -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: ${MIME_TYPE}" \
  -H "Content-Type: application/json" > /dev/null
  -d '{
        "chunking_config": {
          "white_space_config": {
            "max_tokens_per_chunk": 200,
            "max_overlap_tokens": 20
          }
        }
    }'

# Extract upload_url from headers
UPLOAD_URL=$(grep -i "x-goog-upload-url: " "${TMP_HEADER}" | cut -d" " -f2 | tr -d "\r")
rm "${TMP_HEADER}"

# --- Upload the actual bytes ---
curl "${UPLOAD_URL}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${FILE_PATH}" 2> /dev/null

如要使用檔案搜尋商店,請將其做為工具傳遞至 generateContent 方法,如「上傳」和「匯入」範例所示。

運作方式

檔案搜尋功能會使用語意搜尋技術,找出與使用者提示相關的資訊。與傳統的關鍵字搜尋不同,語意搜尋會解讀查詢的意義和脈絡。

匯入檔案時,系統會將檔案轉換為稱為「嵌入」的數值表示形式,擷取文字的語意。這些嵌入內容會儲存在專門的檔案搜尋資料庫中。 查詢時,系統也會將查詢內容轉換為嵌入。接著,系統會執行檔案搜尋,從檔案搜尋儲存空間找出最相似且相關的文件區塊。

以下說明使用 File Search uploadToFileSearchStore API 的程序:

  1. 建立檔案搜尋商店:檔案搜尋商店包含檔案中經過處理的資料。這是語意搜尋運作時使用的嵌入項目永久容器。

  2. 上傳檔案並匯入檔案搜尋商店:同時上傳檔案並將結果匯入檔案搜尋商店。這會建立暫時的 File 物件,也就是原始文件的參照。然後將資料分塊、轉換為檔案搜尋嵌入,並建立索引。File 物件會在 48 小時後刪除,而匯入檔案搜尋儲存區的資料則會無限期保留,直到您選擇刪除為止。

  3. 使用檔案搜尋查詢:最後,您會在 generateContent 呼叫中使用 FileSearch 工具。在工具設定中,您會指定 FileSearchRetrievalResource,指向要搜尋的 FileSearchStore。這會指示模型對該特定「檔案搜尋」商店執行語意搜尋,找出相關資訊做為回覆內容的依據。

檔案搜尋的索引和查詢程序
檔案搜尋的索引和查詢程序

在此圖表中,從「文件」到「嵌入模型」(使用 gemini-embedding-001) 的虛線代表 uploadToFileSearchStore API (略過「檔案儲存空間」)。否則,使用 Files API 分別建立及匯入檔案,會將索引程序從「文件」移至「檔案儲存空間」,然後移至「嵌入模型」

檔案搜尋商店

檔案搜尋商店是文件嵌入的容器。透過 File API 上傳的原始檔案會在 48 小時後刪除,但匯入檔案搜尋商店的資料會無限期儲存,直到您手動刪除為止。你可以建立多個檔案搜尋商店來整理文件。您可以使用 FileSearchStore API 建立、列出、取得及刪除檔案,藉此管理檔案搜尋商店。檔案搜尋商店名稱的範圍為全球。

以下列舉幾個管理檔案搜尋商店的例子:

Python

# Create a File Search store (including optional display_name for easier reference)
file_search_store = client.file_search_stores.create(config={'display_name': 'my-file_search-store-123'})

# List all your File Search stores
for file_search_store in client.file_search_stores.list():
    print(file_search_store)

# Get a specific File Search store by name
my_file_search_store = client.file_search_stores.get(name='fileSearchStores/my-file_search-store-123')

# Delete a File Search store
client.file_search_stores.delete(name='fileSearchStores/my-file_search-store-123', config={'force': True})

JavaScript

// Create a File Search store (including optional display_name for easier reference)
const fileSearchStore = await ai.fileSearchStores.create({
  config: { displayName: 'my-file_search-store-123' }
});

// List all your File Search stores
const fileSearchStores = await ai.fileSearchStores.list();
for await (const store of fileSearchStores) {
  console.log(store);
}

// Get a specific File Search store by name
const myFileSearchStore = await ai.fileSearchStores.get({
  name: 'fileSearchStores/my-file_search-store-123'
});

// Delete a File Search store
await ai.fileSearchStores.delete({
  name: 'fileSearchStores/my-file_search-store-123',
  config: { force: true }
});

REST

# Create a File Search store (including optional display_name for easier reference)
curl -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=${GEMINI_API_KEY}" \
    -H "Content-Type: application/json" 
    -d '{ "displayName": "My Store" }'

# List all your File Search stores
curl "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=${GEMINI_API_KEY}" \

# Get a specific File Search store by name
curl "https://generativelanguage.googleapis.com/v1beta/fileSearchStores/my-file_search-store-123?key=${GEMINI_API_KEY}"

# Delete a File Search store
curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/fileSearchStores/my-file_search-store-123?key=${GEMINI_API_KEY}"

檔案搜尋文件 API 參考資料,說明與管理檔案儲存庫中文件相關的方法和欄位。

檔案中繼資料

您可以為檔案新增自訂中繼資料,以便篩選檔案或提供額外背景資訊。中繼資料是一組鍵/值組合。

Python

# Import the file into the File Search store with custom metadata
op = client.file_search_stores.import_file(
    file_search_store_name=file_search_store.name,
    file_name=sample_file.name,
    custom_metadata=[
        {"key": "author", "string_value": "Robert Graves"},
        {"key": "year", "numeric_value": 1934}
    ]
)

JavaScript

// Import the file into the File Search store with custom metadata
let operation = await ai.fileSearchStores.importFile({
  fileSearchStoreName: fileSearchStore.name,
  fileName: sampleFile.name,
  config: {
    customMetadata: [
      { key: "author", stringValue: "Robert Graves" },
      { key: "year", numericValue: 1934 }
    ]
  }
});

REST

FILE_PATH="path/to/sample.pdf"
MIME_TYPE=$(file -b --mime-type "${FILE_PATH}")
NUM_BYTES=$(wc -c < "${FILE_PATH}")

# Create a FileSearchStore
STORE_RESPONSE=$(curl -s -X POST "https://generativelanguage.googleapis.com/v1beta/fileSearchStores?key=${GEMINI_API_KEY}" \
    -H "Content-Type: application/json" \
    -d '{ "displayName": "My Store" }')

# Extract the store name (format: fileSearchStores/xxxxxxx)
STORE_NAME=$(echo $STORE_RESPONSE | jq -r '.name')

# Initiate Resumable Upload to the Store
TMP_HEADER="upload-header.tmp"

curl -s -D "${TMP_HEADER}" \
  "https://generativelanguage.googleapis.com/upload/v1beta/${STORE_NAME}:uploadToFileSearchStore?key=${GEMINI_API_KEY}" \
  -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: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d '{
        "custom_metadata": [
          {"key": "author", "string_value": "Robert Graves"},
          {"key": "year", "numeric_value": 1934}
        ]
    }' > /dev/null

# Extract upload_url from headers
UPLOAD_URL=$(grep -i "x-goog-upload-url: " "${TMP_HEADER}" | cut -d" " -f2 | tr -d "\r")
rm "${TMP_HEADER}"

# --- Upload the actual bytes ---
curl "${UPLOAD_URL}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${FILE_PATH}" 2> /dev/null

如果檔案搜尋商店中有多個文件,且您只想搜尋其中一部分,這項功能就非常實用。

Python

# Use the metadata filter to search within a subset of documents
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="Tell me about the book 'I, Claudius'",
    config=types.GenerateContentConfig(
        tools=[
            types.Tool(
                file_search=types.FileSearch(
                    file_search_store_names=[file_search_store.name],
                    metadata_filter="author=Robert Graves",
                )
            )
        ]
    )
)

print(response.text)

JavaScript

// Use the metadata filter to search within a subset of documents
const response = await ai.models.generateContent({
  model: "gemini-2.5-flash",
  contents: "Tell me about the book 'I, Claudius'",
  config: {
    tools: [
      {
        fileSearch: {
          fileSearchStoreNames: [fileSearchStore.name],
          metadataFilter: 'author="Robert Graves"',
        }
      }
    ]
  }
});

console.log(response.text);

REST

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=${GEMINI_API_KEY}" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
            "contents": [{
                "parts":[{"text": "Tell me about the book I, Claudius"}]          
            }],
            "tools": [{
                "file_search": { 
                    "file_search_store_names":["'$STORE_NAME'"],
                    "metadata_filter": "author = \"Robert Graves\""
                }
            }]
        }' 2> /dev/null > response.json

cat response.json

如需實作 metadata_filter 清單篩選器語法的指引,請參閱 google.aip.dev/160

參考資料

使用檔案搜尋功能時,模型的回覆可能會包含引文,指出生成答案時使用了上傳文件的哪些部分。有助於事實查核和驗證。

您可以透過回應的 grounding_metadata 屬性存取引文資訊。

Python

print(response.candidates[0].grounding_metadata)

JavaScript

console.log(JSON.stringify(response.candidates?.[0]?.groundingMetadata, null, 2));

支援的模型

下列模型支援檔案搜尋:

支援的檔案類型

檔案搜尋支援多種檔案格式,詳列於下列各節。

應用程式檔案類型

  • 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

文字檔案類型

  • 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

頻率限制

為確保服務穩定性,File Search API 設有下列限制:

  • 檔案大小上限 / 每份文件限制:100 MB
  • 專案檔案搜尋儲存空間總大小 (依使用者層級而定):
    • 免費:1 GB
    • 第 1 級:10 GB
    • 第 2 級:100 GB
    • 第 3 級:1 TB
  • 建議:將每個檔案搜尋商店的大小限制在 20 GB 以下,確保最佳的擷取延遲時間。

定價

  • 系統會在建立索引時,根據現有的嵌入定價 (每 100 萬個權杖 $0.15 美元) 向開發人員收取嵌入費用。
  • 儲存空間免費。
  • 查詢時嵌入作業不會產生費用。
  • 系統會將擷取的文件權杖視為一般內容權杖計費。

後續步驟