এম্বেডিং

from google import genai

client = genai.Client()

result = client.models.embed_content(
        model="gemini-embedding-2",
        contents="What is the meaning of life?"
)

print(result.embeddings)

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

async function main() {

    const ai = new GoogleGenAI({});

    const response = await ai.models.embedContent({
        model: 'gemini-embedding-2',
        contents: 'What is the meaning of life?',
    });

    console.log(response.embeddings);
}

main();

package main

import (
    "context"
    "encoding/json"
    "fmt"
    "log"

    "google.golang.org/genai"
)

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

    contents := []*genai.Content{
        genai.NewContentFromText("What is the meaning of life?", genai.RoleUser),
    }
    result, err := client.Models.EmbedContent(ctx,
        "gemini-embedding-2",
        contents,
        nil,
    )
    if err != nil {
        log.Fatal(err)
    }

    embeddings, err := json.MarshalIndent(result.Embeddings, "", "  ")
    if err != nil {
        log.Fatal(err)
    }
    fmt.Println(string(embeddings))
}

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent" \
    -H "Content-Type: application/json" \
    -H "x-goog-api-key: ${GEMINI_API_KEY}" \
    -d '{
        "model": "models/gemini-embedding-2",
        "content": {
        "parts": [{
            "text": "What is the meaning of life?"
        }]
        }
    }'

# Generate embedding for a task's query. Use your correct task here:
def prepare_query(query):
    # return f"task: question answering | query: {query}"
    # return f"task: fact checking | query: {query}"
    # return f"task: code retrieval | query: {query}"
    return f"task: search result | query: {query}"

# Generate embedding for document of an asymmetric retrieval task:
def prepare_document(content, title=None):
    if title is None:
        title = "none"
    return f"title: {title} | text: {content}"

# Generate embedding for query & document of your task.
def prepare_query_and_document(content):
    # return f'task: clustering | query: {content}'
    # return f'task: sentence similarity | query: {content}'
    return f'task: classification | query: {content}'

from google import genai
from google.genai import types
import pandas as pd
from sklearn.metrics.pairwise import cosine_similarity

client = genai.Client()

texts = [
    "What is the meaning of life?",
    "What is the purpose of existence?",
    "How do I bake a cake?",
]

result = client.models.embed_content(
    model="gemini-embedding-001",
    contents=texts,
    config=types.EmbedContentConfig(task_type="SEMANTIC_SIMILARITY")
)

# Create a 3x3 table to show the similarity matrix
df = pd.DataFrame(
    cosine_similarity([e.values for e in result.embeddings]),
    index=texts,
    columns=texts,
)

print(df)

import { GoogleGenAI } from "@google/genai";
// npm i compute-cosine-similarity
import * as cosineSimilarity from "compute-cosine-similarity";

async function main() {
    const ai = new GoogleGenAI({});

    const texts = [
        "What is the meaning of life?",
        "What is the purpose of existence?",
        "How do I bake a cake?",
    ];

    const response = await ai.models.embedContent({
        model: 'gemini-embedding-001',
        contents: texts,
        config: { taskType: 'SEMANTIC_SIMILARITY' },
    });

    const embeddings = response.embeddings.map(e => e.values);

    for (let i = 0; i < texts.length; i++) {
        for (let j = i + 1; j < texts.length; j++) {
            const text1 = texts[i];
            const text2 = texts[j];
            const similarity = cosineSimilarity(embeddings[i], embeddings[j]);
            console.log(`Similarity between '${text1}' and '${text2}': ${similarity.toFixed(4)}`);
        }
    }
}

main();

package main

import (
    "context"
    "fmt"
    "log"
    "math"

    "google.golang.org/genai"
)

// cosineSimilarity calculates the similarity between two vectors.
func cosineSimilarity(a, b []float32) (float64, error) {
    if len(a) != len(b) {
        return 0, fmt.Errorf("vectors must have the same length")
    }

    var dotProduct, aMagnitude, bMagnitude float64
    for i := 0; i < len(a); i++ {
        dotProduct += float64(a[i] * b[i])
        aMagnitude += float64(a[i] * a[i])
        bMagnitude += float64(b[i] * b[i])
    }

    if aMagnitude == 0 || bMagnitude == 0 {
        return 0, nil
    }

    return dotProduct / (math.Sqrt(aMagnitude) * math.Sqrt(bMagnitude)), nil
}

func main() {
    ctx := context.Background()
    client, _ := genai.NewClient(ctx, nil)
    defer client.Close()

    texts := []string{
        "What is the meaning of life?",
        "What is the purpose of existence?",
        "How do I bake a cake?",
    }

    var contents []*genai.Content
    for _, text := range texts {
        contents = append(contents, genai.NewContentFromText(text, genai.RoleUser))
    }

    result, _ := client.Models.EmbedContent(ctx,
        "gemini-embedding-001",
        contents,
        &genai.EmbedContentRequest{TaskType: genai.TaskTypeSemanticSimilarity},
    )

    embeddings := result.Embeddings

    for i := 0; i < len(texts); i++ {
        for j := i + 1; j < len(texts); j++ {
            similarity, _ := cosineSimilarity(embeddings[i].Values, embeddings[j].Values)
            fmt.Printf("Similarity between '%s' and '%s': %.4f\n", texts[i], texts[j], similarity)
        }
    }
}

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-001:embedContent" \
    -H "Content-Type: application/json" \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -d '{
    "taskType": "SEMANTIC_SIMILARITY",
    "content": {
        "parts": [
        {
            "text": "What is the meaning of life?"
        },
        {
            "text": "How much wood would a woodchuck chuck?"
        },
        {
            "text": "How does the brain work?"
        }
        ]
    }
    }'

from google import genai
from google.genai import types

client = genai.Client()

result = client.models.embed_content(
    model="gemini-embedding-2",
    contents="What is the meaning of life?",
    config=types.EmbedContentConfig(output_dimensionality=768)
)

[embedding_obj] = result.embeddings
embedding_length = len(embedding_obj.values)

print(f"Length of embedding: {embedding_length}")

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

async function main() {
    const ai = new GoogleGenAI({});

    const response = await ai.models.embedContent({
        model: 'gemini-embedding-2',
        contents: 'What is the meaning of life?',
        config: { outputDimensionality: 768 },
    });

    const embeddingLength = response.embeddings[0].values.length;
    console.log(`Length of embedding: ${embeddingLength}`);
}

main();

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
)

func main() {
    ctx := context.Background()
    // The client uses Application Default Credentials.
    // Authenticate with 'gcloud auth application-default login'.
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }
    defer client.Close()

    contents := []*genai.Content{
        genai.NewContentFromText("What is the meaning of life?", genai.RoleUser),
    }

    result, err := client.Models.EmbedContent(ctx,
        "gemini-embedding-2",
        contents,
        &genai.EmbedContentRequest{OutputDimensionality: 768},
    )
    if err != nil {
        log.Fatal(err)
    }

    embedding := result.Embeddings[0]
    embeddingLength := len(embedding.Values)
    fmt.Printf("Length of embedding: %d\n", embeddingLength)
}

curl -X POST "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent" \
    -H 'Content-Type: application/json' \
    -H "x-goog-api-key: $GEMINI_API_KEY" \
    -d '{
        "content": {"parts":[{ "text": "What is the meaning of life?"}]},
        "output_dimensionality": 768
    }'

import numpy as np
from numpy.linalg import norm

# Only for embeddings from `gemini-embedding-001`
embedding_values_np = np.array(embedding_obj.values)
normed_embedding = embedding_values_np / np.linalg.norm(embedding_values_np)

print(f"Normed embedding length: {len(normed_embedding)}")
print(f"Norm of normed embedding: {np.linalg.norm(normed_embedding):.6f}") # Should be very close to 1

from google import genai
from google.genai import types

with open('example.png', 'rb') as f:
    image_bytes = f.read()

client = genai.Client()

result = client.models.embed_content(
    model='gemini-embedding-2',
    contents=[
        types.Part.from_bytes(
            data=image_bytes,
            mime_type='image/png',
        ),
    ]
)

print(result.embeddings)

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

async function main() {
    const ai = new GoogleGenAI({});

    const imgBase64 = fs.readFileSync("example.png", { encoding: "base64" });

    const response = await ai.models.embedContent({
        model: 'gemini-embedding-2',
        contents: [{
            inlineData: {
                mimeType: 'image/png',
                data: imgBase64,
            },
        }],
    });

    console.log(response.embeddings);
}

main();

IMG_PATH="/path/to/your/image.png"
IMG_BASE64=$(base64 -w0 "${IMG_PATH}")

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent" \
    -H "Content-Type: application/json" \
    -H "x-goog-api-key: ${GEMINI_API_KEY}" \
    -d '{
        "content": {
            "parts": [{
                "inline_data": {
                    "mime_type": "image/png",
                    "data": "'"${IMG_BASE64}"'"
                }
            }]
        }
    }'

from google import genai
from google.genai import types

client = genai.Client()

with open('dog.png', 'rb') as f:
    image_bytes = f.read()

result = client.models.embed_content(
    model='gemini-embedding-2',
    contents=[
        "An image of a dog",
        types.Part.from_bytes(
            data=image_bytes,
            mime_type='image/png',
        ),
    ]
)

# This produces one embedding
for embedding in result.embeddings:
    print(embedding.values)

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

async function main() {
    const ai = new GoogleGenAI({});

    const imgBase64 = fs.readFileSync("dog.png", { encoding: "base64" });

    const response = await ai.models.embedContent({
        model: 'gemini-embedding-2',
        contents: [
            'An image of a dog',
            {
                inlineData: {
                    mimeType: 'image/png',
                    data: imgBase64,
                },
            },
        ],
    });

    // This produces one embedding
    for (const embedding of response.embeddings) {
        console.log(embedding.values);
    }
}

main();

IMG_PATH="/path/to/your/dog.png"
IMG_BASE64=$(base64 -w0 "${IMG_PATH}")

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent" \
    -H "Content-Type: application/json" \
    -H "x-goog-api-key: ${GEMINI_API_KEY}" \
    -d '{
        "content": {
            "parts": [
                {"text": "An image of a dog"},
                {
                    "inline_data": {
                        "mime_type": "image/png",
                        "data": "'"${IMG_BASE64}"'"
                    }
                }
            ]
        }
    }'

from google import genai
from google.genai import types

client = genai.Client()

with open('dog.png', 'rb') as f:
    image_bytes = f.read()

result = client.models.embed_content(
    model="gemini-embedding-2",
    contents=[
        types.Content(parts=[types.Part.from_text(text="An image of a dog")]),
        types.Content(
            parts=[
                types.Part.from_bytes(
                    data=image_bytes,
                    mime_type="image/png",
                ),
            ]
        ),
    ],
)

# This produces two embeddings
for embedding in result.embeddings:
    print(embedding.values)

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

async function main() {
    const ai = new GoogleGenAI({});

    const imgBase64 = fs.readFileSync("dog.png", { encoding: "base64" });

    const response = await ai.models.embedContent({
        model: 'gemini-embedding-2',
        contents: [
            { parts: [{ text: 'An image of a dog' }] },
            {
                parts: [{
                    inlineData: {
                        mimeType: 'image/png',
                        data: imgBase64,
                    },
                }],
            },
        ],
    });

    // This produces two embeddings
    for (const embedding of response.embeddings) {
        console.log(embedding.values);
    }
}

main();

IMG_PATH="/path/to/your/dog.png"
IMG_BASE64=$(base64 -w0 "${IMG_PATH}")

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:batchEmbedContents" \
    -H "Content-Type: application/json" \
    -H "x-goog-api-key: ${GEMINI_API_KEY}" \
    -d '{
        "requests": [
            {
                "model": "models/gemini-embedding-2",
                "content": {"parts": [{"text": "An image of a dog"}]}
            },
            {
                "model": "models/gemini-embedding-2",
                "content": {"parts": [{"inline_data": {"mime_type": "image/png", "data": "'"${IMG_BASE64}"'"}}]}
            }
        ]
    }'

from google import genai
from google.genai import types

with open('example.mp3', 'rb') as f:
    audio_bytes = f.read()

client = genai.Client()

result = client.models.embed_content(
    model='gemini-embedding-2',
    contents=[
        types.Part.from_bytes(
            data=audio_bytes,
            mime_type='audio/mpeg',
        ),
    ]
)

print(result.embeddings)

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

async function main() {
    const ai = new GoogleGenAI({});

    const audioBase64 = fs.readFileSync("example.mp3", { encoding: "base64" });

    const response = await ai.models.embedContent({
        model: 'gemini-embedding-2',
        contents: [{
            inlineData: {
                mimeType: 'audio/mpeg',
                data: audioBase64,
            },
        }],
    });

    console.log(response.embeddings);
}

main();

AUDIO_PATH="/path/to/your/example.mp3"
AUDIO_BASE64=$(base64 -w0 "${AUDIO_PATH}")

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent" \
    -H "Content-Type: application/json" \
    -H "x-goog-api-key: ${GEMINI_API_KEY}" \
    -d '{
        "content": {
            "parts": [{
                "inline_data": {
                    "mime_type": "audio/mpeg",
                    "data": "'"${AUDIO_BASE64}"'"
                }
            }]
        }
    }'

from google import genai
from google.genai import types

client = genai.Client()

with open('example.mp4', 'rb') as f:
    video_bytes = f.read()

result = client.models.embed_content(
    model='gemini-embedding-2',
    contents=[
        types.Part.from_bytes(
            data=video_bytes,
            mime_type='video/mp4',
        ),
    ]
)

print(result.embeddings[0].values)

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

async function main() {
    const ai = new GoogleGenAI({});

    const videoBase64 = fs.readFileSync("example.mp4", { encoding: "base64" });

    const response = await ai.models.embedContent({
        model: 'gemini-embedding-2',
        contents: [{
            inlineData: {
                mimeType: 'video/mp4',
                data: videoBase64,
            },
        }],
    });

    console.log(response.embeddings);
}

main();

VIDEO_PATH="/path/to/your/video.mp4"
VIDEO_BASE64=$(base64 -w0 "${VIDEO_PATH}")

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent" \
    -H "Content-Type: application/json" \
    -H "x-goog-api-key: ${GEMINI_API_KEY}" \
    -d '{
        "content": {
            "parts": [{
                "inline_data": {
                    "mime_type": "video/mp4",
                    "data": "'"${VIDEO_BASE64}"'"
                }
            }]
        }
    }'

from google import genai
from google.genai import types

with open('example.pdf', 'rb') as f:
    pdf_bytes = f.read()

client = genai.Client()

result = client.models.embed_content(
    model='gemini-embedding-2',
    contents=[
        types.Part.from_bytes(
            data=pdf_bytes,
            mime_type='application/pdf',
        ),
    ]
)

print(result.embeddings)

import { GoogleGenAI } from "@google/genai";
import * as fs from "node:fs";

async function main() {
    const ai = new GoogleGenAI({});

    const pdfBase64 = fs.readFileSync("example.pdf", { encoding: "base64" });

    const response = await ai.models.embedContent({
        model: 'gemini-embedding-2',
        contents: [{
            inlineData: {
                mimeType: 'application/pdf',
                data: pdfBase64,
            },
        }],
    });

    console.log(response.embeddings);
}

main();

PDF_PATH="/path/to/your/example.pdf"
PDF_BASE64=$(base64 -w0 "${PDF_PATH}")

curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-embedding-2:embedContent" \
    -H "Content-Type: application/json" \
    -H "x-goog-api-key: ${GEMINI_API_KEY}" \
    -d '{
        "content": {
            "parts": [{
                "inline_data": {
                    "mime_type": "application/pdf",
                    "data": "'"${PDF_BASE64}"'"
                }
            }]
        }
    }'