Using files

# With Gemini-2 we're launching a new SDK, see this doc for details.
# https://ai.google.dev/gemini-api/docs/migrate
README.md

// Make sure to include these imports:
// import { GoogleAIFileManager } from "@google/generative-ai/server";
// import { GoogleGenerativeAI } from "@google/generative-ai";
const fileManager = new GoogleAIFileManager(process.env.API_KEY);

const uploadResult = await fileManager.uploadFile(
  `${mediaPath}/jetpack.jpg`,
  {
    mimeType: "image/jpeg",
    displayName: "Jetpack drawing",
  },
);
// View the response.
console.log(
  `Uploaded file ${uploadResult.file.displayName} as: ${uploadResult.file.uri}`,
);

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });
const result = await model.generateContent([
  "Tell me about this image.",
  {
    fileData: {
      fileUri: uploadResult.file.uri,
      mimeType: uploadResult.file.mimeType,
    },
  },
]);
console.log(result.response.text());
files.js

file, err := client.UploadFileFromPath(ctx, filepath.Join(testDataDir, "Cajun_instruments.jpg"), nil)
if err != nil {
	log.Fatal(err)
}
defer client.DeleteFile(ctx, file.Name)

model := client.GenerativeModel("gemini-1.5-flash")
resp, err := model.GenerateContent(ctx,
	genai.FileData{URI: file.URI},
	genai.Text("Can you tell me about the instruments in this photo?"))
if err != nil {
	log.Fatal(err)
}

printResponse(resp)
docs-snippets_test.go

MIME_TYPE=$(file -b --mime-type "${IMG_PATH_2}")
NUM_BYTES=$(wc -c < "${IMG_PATH_2}")
DISPLAY_NAME=TEXT

tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_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: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

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

# Upload the actual bytes.
curl "${upload_url}" \
  -H "Content-Length: ${NUM_BYTES}" \
  -H "X-Goog-Upload-Offset: 0" \
  -H "X-Goog-Upload-Command: upload, finalize" \
  --data-binary "@${IMG_PATH_2}" 2> /dev/null > file_info.json

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

# Now generate content using that file
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Can you tell me about the instruments in this photo?"},
          {"file_data":
            {"mime_type": "image/jpeg", 
            "file_uri": '$file_uri'}
        }]
        }]
       }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json
files.sh

# With Gemini-2 we're launching a new SDK, see this doc for details.
# https://ai.google.dev/gemini-api/docs/migrate
README.md

// Make sure to include these imports:
// import { GoogleAIFileManager, FileState } from "@google/generative-ai/server";
// import { GoogleGenerativeAI } from "@google/generative-ai";
const fileManager = new GoogleAIFileManager(process.env.API_KEY);

const uploadResult = await fileManager.uploadFile(
  `${mediaPath}/samplesmall.mp3`,
  {
    mimeType: "audio/mp3",
    displayName: "Audio sample",
  },
);

let file = await fileManager.getFile(uploadResult.file.name);
while (file.state === FileState.PROCESSING) {
  process.stdout.write(".");
  // Sleep for 10 seconds
  await new Promise((resolve) => setTimeout(resolve, 10_000));
  // Fetch the file from the API again
  file = await fileManager.getFile(uploadResult.file.name);
}

if (file.state === FileState.FAILED) {
  throw new Error("Audio processing failed.");
}

// View the response.
console.log(
  `Uploaded file ${uploadResult.file.displayName} as: ${uploadResult.file.uri}`,
);

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });
const result = await model.generateContent([
  "Tell me about this audio clip.",
  {
    fileData: {
      fileUri: uploadResult.file.uri,
      mimeType: uploadResult.file.mimeType,
    },
  },
]);
console.log(result.response.text());
files.js

file, err := client.UploadFileFromPath(ctx, filepath.Join(testDataDir, "sample.mp3"), nil)
if err != nil {
	log.Fatal(err)
}
defer client.DeleteFile(ctx, file.Name)

model := client.GenerativeModel("gemini-1.5-flash")
resp, err := model.GenerateContent(ctx,
	genai.FileData{URI: file.URI},
	genai.Text("Describe this audio clip"))
if err != nil {
	log.Fatal(err)
}

printResponse(resp)
docs-snippets_test.go

MIME_TYPE=$(file -b --mime-type "${AUDIO_PATH}")
NUM_BYTES=$(wc -c < "${AUDIO_PATH}")
DISPLAY_NAME=AUDIO

tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_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: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

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

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

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

# Now generate content using that file
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Describe this audio clip"},
          {"file_data":{"mime_type": "audio/mp3", "file_uri": '$file_uri'}}]
        }]
       }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json
files.sh

# With Gemini-2 we're launching a new SDK, see this doc for details.
# https://ai.google.dev/gemini-api/docs/migrate
README.md

// Make sure to include these imports:
// import { GoogleAIFileManager } from "@google/generative-ai/server";
// import { GoogleGenerativeAI } from "@google/generative-ai";
const fileManager = new GoogleAIFileManager(process.env.API_KEY);

const uploadResult = await fileManager.uploadFile(`${mediaPath}/a11.txt`, {
  mimeType: "text/plain",
  displayName: "Apollo 11",
});
// View the response.
console.log(
  `Uploaded file ${uploadResult.file.displayName} as: ${uploadResult.file.uri}`,
);

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });
const result = await model.generateContent([
  "Transcribe the first few sentences of this document.",
  {
    fileData: {
      fileUri: uploadResult.file.uri,
      mimeType: uploadResult.file.mimeType,
    },
  },
]);
console.log(result.response.text());
files.js

// Set MIME type explicitly for text files - the service may have difficulty
// distingushing between different MIME types of text files automatically.
file, err := client.UploadFileFromPath(ctx, filepath.Join(testDataDir, "poem.txt"), nil)
if err != nil {
	log.Fatal(err)
}
defer client.DeleteFile(ctx, file.Name)

model := client.GenerativeModel("gemini-1.5-flash")
resp, err := model.GenerateContent(ctx,
	genai.FileData{URI: file.URI},
	genai.Text("Can you add a few more lines to this poem?"))
if err != nil {
	log.Fatal(err)
}

printResponse(resp)
docs-snippets_test.go

MIME_TYPE=$(file -b --mime-type "${TEXT_PATH}")
NUM_BYTES=$(wc -c < "${TEXT_PATH}")
DISPLAY_NAME=TEXT

tmp_header_file=upload-header.tmp

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_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: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

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

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

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

# Now generate content using that file
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Can you add a few more lines to this poem?"},
          {"file_data":{"mime_type": "text/plain", "file_uri": '$file_uri'}}]
        }]
       }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json

name=$(jq ".file.name" file_info.json)
# Get the file of interest to check state
curl https://generativelanguage.googleapis.com/v1beta/files/$name > file_info.json
# Print some information about the file you got
name=$(jq ".file.name" file_info.json)
echo name=$name
file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

curl --request "DELETE" https://generativelanguage.googleapis.com/v1beta/files/$name?key=$GOOGLE_API_KEY
files.sh

# With Gemini-2 we're launching a new SDK, see this doc for details.
# https://ai.google.dev/gemini-api/docs/migrate
README.md

// Make sure to include these imports:
// import { GoogleAIFileManager, FileState } from "@google/generative-ai/server";
// import { GoogleGenerativeAI } from "@google/generative-ai";
const fileManager = new GoogleAIFileManager(process.env.API_KEY);

const uploadResult = await fileManager.uploadFile(
  `${mediaPath}/Big_Buck_Bunny.mp4`,
  {
    mimeType: "video/mp4",
    displayName: "Big Buck Bunny",
  },
);

let file = await fileManager.getFile(uploadResult.file.name);
while (file.state === FileState.PROCESSING) {
  process.stdout.write(".");
  // Sleep for 10 seconds
  await new Promise((resolve) => setTimeout(resolve, 10_000));
  // Fetch the file from the API again
  file = await fileManager.getFile(uploadResult.file.name);
}

if (file.state === FileState.FAILED) {
  throw new Error("Video processing failed.");
}

// View the response.
console.log(
  `Uploaded file ${uploadResult.file.displayName} as: ${uploadResult.file.uri}`,
);

const genAI = new GoogleGenerativeAI(process.env.API_KEY);
const model = genAI.getGenerativeModel({ model: "gemini-1.5-flash" });
const result = await model.generateContent([
  "Tell me about this video.",
  {
    fileData: {
      fileUri: uploadResult.file.uri,
      mimeType: uploadResult.file.mimeType,
    },
  },
]);
console.log(result.response.text());
files.js

file, err := client.UploadFileFromPath(ctx, filepath.Join(testDataDir, "earth.mp4"), nil)
if err != nil {
	log.Fatal(err)
}
defer client.DeleteFile(ctx, file.Name)

// Videos need to be processed before you can use them.
for file.State == genai.FileStateProcessing {
	log.Printf("processing %s", file.Name)
	time.Sleep(5 * time.Second)
	var err error
	if file, err = client.GetFile(ctx, file.Name); err != nil {
		log.Fatal(err)
	}
}
if file.State != genai.FileStateActive {
	log.Fatalf("uploaded file has state %s, not active", file.State)
}

model := client.GenerativeModel("gemini-1.5-flash")
resp, err := model.GenerateContent(ctx,
	genai.FileData{URI: file.URI},
	genai.Text("Describe this video clip"))
if err != nil {
	log.Fatal(err)
}

printResponse(resp)
docs-snippets_test.go

MIME_TYPE=$(file -b --mime-type "${VIDEO_PATH}")
NUM_BYTES=$(wc -c < "${VIDEO_PATH}")
DISPLAY_NAME=VIDEO_PATH

# Initial resumable request defining metadata.
# The upload url is in the response headers dump them to a file.
curl "${BASE_URL}/upload/v1beta/files?key=${GOOGLE_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: ${MIME_TYPE}" \
  -H "Content-Type: application/json" \
  -d "{'file': {'display_name': '${DISPLAY_NAME}'}}" 2> /dev/null

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

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

file_uri=$(jq ".file.uri" file_info.json)
echo file_uri=$file_uri

state=$(jq ".file.state" file_info.json)
echo state=$state

# Ensure the state of the video is 'ACTIVE'
while [[ "($state)" = *"PROCESSING"* ]];
do
  echo "Processing video..."
  sleep 5
  # Get the file of interest to check state
  curl https://generativelanguage.googleapis.com/v1beta/files/$name > file_info.json
  state=$(jq ".file.state" file_info.json)
done

# Now generate content using that file
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-flash:generateContent?key=$GOOGLE_API_KEY" \
    -H 'Content-Type: application/json' \
    -X POST \
    -d '{
      "contents": [{
        "parts":[
          {"text": "Describe this video clip"},
          {"file_data":{"mime_type": "video/mp4", "file_uri": '$file_uri'}}]
        }]
       }' 2> /dev/null > response.json

cat response.json
echo

jq ".candidates[].content.parts[].text" response.json
files.sh

# With Gemini-2 we're launching a new SDK, see this doc for details.
# https://ai.google.dev/gemini-api/docs/migrate
README.md