Count tokens for Gemini

import (
	"context"
	"fmt"
	"io"
	"mime"
	"path/filepath"

	"cloud.google.com/go/vertexai/genai"
)

// countTokensMultimodal finds the number of tokens for a multimodal prompt (video+text), and writes to w. Then,
// it calls the model with the multimodal prompt and writes token counts from the response metadata to w.
//
// video is a Google Cloud Storage path starting with "gs://"
func countTokensMultimodal(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"
	prompt := "Provide a description of the video."
	video := "gs://cloud-samples-data/generative-ai/video/pixel8.mp4"

	ctx := context.Background()

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	part1 := genai.Text(prompt)

	// Given a video file URL, prepare video file as genai.Part
	part2 := genai.FileData{
		MIMEType: mime.TypeByExtension(filepath.Ext(video)),
		FileURI:  video,
	}

	// Finds the total number of tokens for the 2 parts (text, video) of the multimodal prompt,
	// before actually calling the model for inference.
	resp, err := model.CountTokens(ctx, part1, part2)
	if err != nil {
		return err
	}

	fmt.Fprintf(w, "Number of tokens for the multimodal video prompt: %d\n", resp.TotalTokens)

	res, err := model.GenerateContent(ctx, part1, part2)
	if err != nil {
		return fmt.Errorf("unable to generate contents: %w", err)
	}

	// The token counts are also provided in the model response metadata, after inference.
	fmt.Fprintln(w, "\nModel response")
	md := res.UsageMetadata
	fmt.Fprintf(w, "Prompt Token Count: %d\n", md.PromptTokenCount)
	fmt.Fprintf(w, "Candidates Token Count: %d\n", md.CandidatesTokenCount)
	fmt.Fprintf(w, "Total Token Count: %d\n", md.TotalTokenCount)

	return nil
}

import vertexai
from vertexai.generative_models import GenerativeModel, Part

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"
vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

contents = [
    Part.from_uri(
        "gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
        mime_type="video/mp4",
    ),
    "Provide a description of the video.",
]

# tokens count for user prompt
response = model.count_tokens(contents)
print(f"Prompt Token Count: {response.total_tokens}")
print(f"Prompt Character Count: {response.total_billable_characters}")
# Example response:
#     Prompt Token Count: 16822
#     Prompt Character Count: 30

# Send text to Gemini
response = model.generate_content(contents)
usage_metadata = response.usage_metadata

# tokens count for model response
print(f"Prompt Token Count: {usage_metadata.prompt_token_count}")
print(f"Candidates Token Count: {usage_metadata.candidates_token_count}")
print(f"Total Token Count: {usage_metadata.total_token_count}")
# Example response:
#     Prompt Token Count: 16822
#     Candidates Token Count: 71
#     Total Token Count: 16893