Die Gemini API kann mithilfe von Gemini-Modellen Textausgaben aus verschiedenen Eingaben generieren, darunter Text, Bilder, Video und Audio.
Hier ein einfaches Beispiel mit einer einzelnen Textzeile:
Python
from google import genai
client = genai.Client(api_key="GEMINI_API_KEY")
response = client.models.generate_content(
model="gemini-2.0-flash",
contents=["How does AI work?"]
)
print(response.text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });
async function main() {
const response = await ai.models.generateContent({
model: "gemini-2.0-flash",
contents: "How does AI work?",
});
console.log(response.text);
}
await main();
Ok
package main
import (
"context"
"fmt"
"os"
"google.golang.org/genai"
)
func main() {
ctx := context.Background()
client, _ := genai.NewClient(ctx, &genai.ClientConfig{
APIKey: os.Getenv("GEMINI_API_KEY"),
Backend: genai.BackendGeminiAPI,
})
result, _ := client.Models.GenerateContent(
ctx,
"gemini-2.0-flash",
genai.Text("Explain how AI works in a few words"),
nil,
)
fmt.Println(result.Text())
}
REST
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d '{
"contents": [
{
"parts": [
{
"text": "How does AI work?"
}
]
}
]
}'
Apps Script
// See https://developers.google.com/apps-script/guides/properties
// for instructions on how to set the API key.
const apiKey = PropertiesService.getScriptProperties().getProperty('GEMINI_API_KEY');
function main() {
const payload = {
contents: [
{
parts: [
{ text: 'How AI does work?' },
],
},
],
};
const url = `https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=${apiKey}`;
const options = {
method: 'POST',
contentType: 'application/json',
payload: JSON.stringify(payload)
};
const response = UrlFetchApp.fetch(url, options);
const data = JSON.parse(response);
const content = data['candidates'][0]['content']['parts'][0]['text'];
console.log(content);
}
Systemanweisungen und ‑konfigurationen
Mit Systemanweisungen können Sie das Verhalten von Gemini-Modellen steuern. Übergeben Sie dazu ein GenerateContentConfig
-Objekt.
Python
from google import genai
from google.genai import types
client = genai.Client(api_key="GEMINI_API_KEY")
response = client.models.generate_content(
model="gemini-2.0-flash",
config=types.GenerateContentConfig(
system_instruction="You are a cat. Your name is Neko."),
contents="Hello there"
)
print(response.text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });
async function main() {
const response = await ai.models.generateContent({
model: "gemini-2.0-flash",
contents: "Hello there",
config: {
systemInstruction: "You are a cat. Your name is Neko.",
},
});
console.log(response.text);
}
await main();
Ok
package main
import (
"context"
"fmt"
"os"
"google.golang.org/genai"
)
func main() {
ctx := context.Background()
client, _ := genai.NewClient(ctx, &genai.ClientConfig{
APIKey: os.Getenv("GEMINI_API_KEY"),
Backend: genai.BackendGeminiAPI,
})
config := &genai.GenerateContentConfig{
SystemInstruction: genai.NewContentFromText("You are a cat. Your name is Neko.", genai.RoleUser),
}
result, _ := client.Models.GenerateContent(
ctx,
"gemini-2.0-flash",
genai.Text("Hello there"),
config,
)
fmt.Println(result.Text())
}
REST
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
"system_instruction": {
"parts": [
{
"text": "You are a cat. Your name is Neko."
}
]
},
"contents": [
{
"parts": [
{
"text": "Hello there"
}
]
}
]
}'
Apps Script
// See https://developers.google.com/apps-script/guides/properties
// for instructions on how to set the API key.
const apiKey = PropertiesService.getScriptProperties().getProperty('GEMINI_API_KEY');
function main() {
const systemInstruction = {
parts: [{
text: 'You are a cat. Your name is Neko.'
}]
};
const payload = {
systemInstruction,
contents: [
{
parts: [
{ text: 'Hello there' },
],
},
],
};
const url = `https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=${apiKey}`;
const options = {
method: 'POST',
contentType: 'application/json',
payload: JSON.stringify(payload)
};
const response = UrlFetchApp.fetch(url, options);
const data = JSON.parse(response);
const content = data['candidates'][0]['content']['parts'][0]['text'];
console.log(content);
}
Mit dem Objekt GenerateContentConfig
können Sie auch Standardgenerierungsparameter wie temperature überschreiben.
Python
from google import genai
from google.genai import types
client = genai.Client(api_key="GEMINI_API_KEY")
response = client.models.generate_content(
model="gemini-2.0-flash",
contents=["Explain how AI works"],
config=types.GenerateContentConfig(
max_output_tokens=500,
temperature=0.1
)
)
print(response.text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });
async function main() {
const response = await ai.models.generateContent({
model: "gemini-2.0-flash",
contents: "Explain how AI works",
config: {
maxOutputTokens: 500,
temperature: 0.1,
},
});
console.log(response.text);
}
await main();
Ok
package main
import (
"context"
"fmt"
"os"
"google.golang.org/genai"
)
func main() {
ctx := context.Background()
client, _ := genai.NewClient(ctx, &genai.ClientConfig{
APIKey: os.Getenv("GEMINI_API_KEY"),
Backend: genai.BackendGeminiAPI,
})
temp := float32(0.9)
topP := float32(0.5)
topK := float32(20.0)
maxOutputTokens := int32(100)
config := &genai.GenerateContentConfig{
Temperature: &temp,
TopP: &topP,
TopK: &topK,
MaxOutputTokens: maxOutputTokens,
ResponseMIMEType: "application/json",
}
result, _ := client.Models.GenerateContent(
ctx,
"gemini-2.0-flash",
genai.Text("What is the average size of a swallow?"),
config,
)
fmt.Println(result.Text())
}
REST
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY \
-H 'Content-Type: application/json' \
-X POST \
-d '{
"contents": [
{
"parts": [
{
"text": "Explain how AI works"
}
]
}
],
"generationConfig": {
"stopSequences": [
"Title"
],
"temperature": 1.0,
"maxOutputTokens": 800,
"topP": 0.8,
"topK": 10
}
}'
Apps Script
// See https://developers.google.com/apps-script/guides/properties
// for instructions on how to set the API key.
const apiKey = PropertiesService.getScriptProperties().getProperty('GEMINI_API_KEY');
function main() {
const generationConfig = {
temperature: 1,
topP: 0.95,
topK: 40,
maxOutputTokens: 8192,
responseMimeType: 'text/plain',
};
const payload = {
generationConfig,
contents: [
{
parts: [
{ text: 'Explain how AI works in a few words' },
],
},
],
};
const url = `https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=${apiKey}`;
const options = {
method: 'POST',
contentType: 'application/json',
payload: JSON.stringify(payload)
};
const response = UrlFetchApp.fetch(url, options);
const data = JSON.parse(response);
const content = data['candidates'][0]['content']['parts'][0]['text'];
console.log(content);
}
Eine vollständige Liste der konfigurierbaren Parameter und ihre Beschreibungen findest du in der API-Referenz unter GenerateContentConfig
.
Multimodale Eingaben
Die Gemini API unterstützt multimodale Eingaben, sodass Sie Text mit Mediendateien kombinieren können. Das folgende Beispiel zeigt, wie ein Bild bereitgestellt wird:
Python
from PIL import Image
from google import genai
client = genai.Client(api_key="GEMINI_API_KEY")
image = Image.open("/path/to/organ.png")
response = client.models.generate_content(
model="gemini-2.0-flash",
contents=[image, "Tell me about this instrument"]
)
print(response.text)
JavaScript
import {
GoogleGenAI,
createUserContent,
createPartFromUri,
} from "@google/genai";
const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });
async function main() {
const image = await ai.files.upload({
file: "/path/to/organ.png",
});
const response = await ai.models.generateContent({
model: "gemini-2.0-flash",
contents: [
createUserContent([
"Tell me about this instrument",
createPartFromUri(image.uri, image.mimeType),
]),
],
});
console.log(response.text);
}
await main();
Ok
package main
import (
"context"
"fmt"
"os"
"google.golang.org/genai"
)
func main() {
ctx := context.Background()
client, _ := genai.NewClient(ctx, &genai.ClientConfig{
APIKey: os.Getenv("GEMINI_API_KEY"),
Backend: genai.BackendGeminiAPI,
})
imagePath := "/path/to/organ.jpg"
imgData, _ := os.ReadFile(imagePath)
parts := []*genai.Part{
genai.NewPartFromText("Tell me about this instrument"),
&genai.Part{
InlineData: &genai.Blob{
MIMEType: "image/jpeg",
Data: imgData,
},
},
}
contents := []*genai.Content{
genai.NewContentFromParts(parts, genai.RoleUser),
}
result, _ := client.Models.GenerateContent(
ctx,
"gemini-2.0-flash",
contents,
nil,
)
fmt.Println(result.Text())
}
REST
# Use a temporary file to hold the base64 encoded image data
TEMP_B64=$(mktemp)
trap 'rm -f "$TEMP_B64"' EXIT
base64 $B64FLAGS $IMG_PATH > "$TEMP_B64"
# Use a temporary file to hold the JSON payload
TEMP_JSON=$(mktemp)
trap 'rm -f "$TEMP_JSON"' EXIT
cat > "$TEMP_JSON" << EOF
{
"contents": [
{
"parts": [
{
"text": "Tell me about this instrument"
},
{
"inline_data": {
"mime_type": "image/jpeg",
"data": "$(cat "$TEMP_B64")"
}
}
]
}
]
}
EOF
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY" \
-H 'Content-Type: application/json' \
-X POST \
-d "@$TEMP_JSON"
Apps Script
// See https://developers.google.com/apps-script/guides/properties
// for instructions on how to set the API key.
const apiKey = PropertiesService.getScriptProperties().getProperty('GEMINI_API_KEY');
function main() {
const imageUrl = 'http://image/url';
const image = getImageData(imageUrl);
const payload = {
contents: [
{
parts: [
{ image },
{ text: 'Tell me about this instrument' },
],
},
],
};
const url = `https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=${apiKey}`;
const options = {
method: 'POST',
contentType: 'application/json',
payload: JSON.stringify(payload)
};
const response = UrlFetchApp.fetch(url, options);
const data = JSON.parse(response);
const content = data['candidates'][0]['content']['parts'][0]['text'];
console.log(content);
}
function getImageData(url) {
const blob = UrlFetchApp.fetch(url).getBlob();
return {
mimeType: blob.getContentType(),
data: Utilities.base64Encode(blob.getBytes())
};
}
Informationen zu alternativen Methoden zum Bereitstellen von Bildern und zur erweiterten Bildverarbeitung finden Sie in unserem Leitfaden zum Verstehen von Bildern. Die API unterstützt auch Dokumente, Videos und Audioinhalte.
Streamingantworten
Standardmäßig gibt das Modell eine Antwort erst zurück, wenn der gesamte Generierungsprozess abgeschlossen ist.
Für flüssigere Interaktionen kannst du Streaming verwenden, um GenerateContentResponse
-Instanzen nach und nach zu empfangen, sobald sie generiert werden.
Python
from google import genai
client = genai.Client(api_key="GEMINI_API_KEY")
response = client.models.generate_content_stream(
model="gemini-2.0-flash",
contents=["Explain how AI works"]
)
for chunk in response:
print(chunk.text, end="")
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });
async function main() {
const response = await ai.models.generateContentStream({
model: "gemini-2.0-flash",
contents: "Explain how AI works",
});
for await (const chunk of response) {
console.log(chunk.text);
}
}
await main();
Ok
package main
import (
"context"
"fmt"
"os"
"google.golang.org/genai"
)
func main() {
ctx := context.Background()
client, _ := genai.NewClient(ctx, &genai.ClientConfig{
APIKey: os.Getenv("GEMINI_API_KEY"),
Backend: genai.BackendGeminiAPI,
})
stream := client.Models.GenerateContentStream(
ctx,
"gemini-2.0-flash",
genai.Text("Write a story about a magic backpack."),
nil,
)
for chunk, _ := range stream {
part := chunk.Candidates[0].Content.Parts[0]
fmt.Print(part.Text)
}
}
REST
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse&key=${GEMINI_API_KEY}" \
-H 'Content-Type: application/json' \
--no-buffer \
-d '{
"contents": [
{
"parts": [
{
"text": "Explain how AI works"
}
]
}
]
}'
Apps Script
// See https://developers.google.com/apps-script/guides/properties
// for instructions on how to set the API key.
const apiKey = PropertiesService.getScriptProperties().getProperty('GEMINI_API_KEY');
function main() {
const payload = {
contents: [
{
parts: [
{ text: 'Explain how AI works' },
],
},
],
};
const url = `https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?key=${apiKey}`;
const options = {
method: 'POST',
contentType: 'application/json',
payload: JSON.stringify(payload)
};
const response = UrlFetchApp.fetch(url, options);
const data = JSON.parse(response);
const content = data['candidates'][0]['content']['parts'][0]['text'];
console.log(content);
}
Unterhaltungen mit mehreren Antworten (Chat)
Unsere SDKs bieten Funktionen, mit denen Sie mehrere Prompts und Antworten in einem Chat erfassen können. So können Sie den Gesprächsverlauf ganz einfach im Blick behalten.
Python
from google import genai
client = genai.Client(api_key="GEMINI_API_KEY")
chat = client.chats.create(model="gemini-2.0-flash")
response = chat.send_message("I have 2 dogs in my house.")
print(response.text)
response = chat.send_message("How many paws are in my house?")
print(response.text)
for message in chat.get_history():
print(f'role - {message.role}',end=": ")
print(message.parts[0].text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });
async function main() {
const chat = ai.chats.create({
model: "gemini-2.0-flash",
history: [
{
role: "user",
parts: [{ text: "Hello" }],
},
{
role: "model",
parts: [{ text: "Great to meet you. What would you like to know?" }],
},
],
});
const response1 = await chat.sendMessage({
message: "I have 2 dogs in my house.",
});
console.log("Chat response 1:", response1.text);
const response2 = await chat.sendMessage({
message: "How many paws are in my house?",
});
console.log("Chat response 2:", response2.text);
}
await main();
Ok
package main
import (
"context"
"fmt"
"os"
"google.golang.org/genai"
)
func main() {
ctx := context.Background()
client, _ := genai.NewClient(ctx, &genai.ClientConfig{
APIKey: os.Getenv("GEMINI_API_KEY"),
Backend: genai.BackendGeminiAPI,
})
history := []*genai.Content{
genai.NewContentFromText("Hi nice to meet you! I have 2 dogs in my house.", genai.RoleUser),
genai.NewContentFromText("Great to meet you. What would you like to know?", genai.RoleModel),
}
chat, _ := client.Chats.Create(ctx, "gemini-2.0-flash", nil, history)
res, _ := chat.SendMessage(ctx, genai.Part{Text: "How many paws are in my house?"})
if len(res.Candidates) > 0 {
fmt.Println(res.Candidates[0].Content.Parts[0].Text)
}
}
REST
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=$GEMINI_API_KEY \
-H 'Content-Type: application/json' \
-X POST \
-d '{
"contents": [
{
"role": "user",
"parts": [
{
"text": "Hello"
}
]
},
{
"role": "model",
"parts": [
{
"text": "Great to meet you. What would you like to know?"
}
]
},
{
"role": "user",
"parts": [
{
"text": "I have two dogs in my house. How many paws are in my house?"
}
]
}
]
}'
Apps Script
// See https://developers.google.com/apps-script/guides/properties
// for instructions on how to set the API key.
const apiKey = PropertiesService.getScriptProperties().getProperty('GEMINI_API_KEY');
function main() {
const payload = {
contents: [
{
role: 'user',
parts: [
{ text: 'Hello' },
],
},
{
role: 'model',
parts: [
{ text: 'Great to meet you. What would you like to know?' },
],
},
{
role: 'user',
parts: [
{ text: 'I have two dogs in my house. How many paws are in my house?' },
],
},
],
};
const url = `https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent?key=${apiKey}`;
const options = {
method: 'POST',
contentType: 'application/json',
payload: JSON.stringify(payload)
};
const response = UrlFetchApp.fetch(url, options);
const data = JSON.parse(response);
const content = data['candidates'][0]['content']['parts'][0]['text'];
console.log(content);
}
Streaming kann auch für Unterhaltungen mit mehreren Antworten verwendet werden.
Python
from google import genai
client = genai.Client(api_key="GEMINI_API_KEY")
chat = client.chats.create(model="gemini-2.0-flash")
response = chat.send_message_stream("I have 2 dogs in my house.")
for chunk in response:
print(chunk.text, end="")
response = chat.send_message_stream("How many paws are in my house?")
for chunk in response:
print(chunk.text, end="")
for message in chat.get_history():
print(f'role - {message.role}', end=": ")
print(message.parts[0].text)
JavaScript
import { GoogleGenAI } from "@google/genai";
const ai = new GoogleGenAI({ apiKey: "GEMINI_API_KEY" });
async function main() {
const chat = ai.chats.create({
model: "gemini-2.0-flash",
history: [
{
role: "user",
parts: [{ text: "Hello" }],
},
{
role: "model",
parts: [{ text: "Great to meet you. What would you like to know?" }],
},
],
});
const stream1 = await chat.sendMessageStream({
message: "I have 2 dogs in my house.",
});
for await (const chunk of stream1) {
console.log(chunk.text);
console.log("_".repeat(80));
}
const stream2 = await chat.sendMessageStream({
message: "How many paws are in my house?",
});
for await (const chunk of stream2) {
console.log(chunk.text);
console.log("_".repeat(80));
}
}
await main();
Ok
package main
import (
"context"
"fmt"
"os"
"google.golang.org/genai"
)
func main() {
ctx := context.Background()
client, _ := genai.NewClient(ctx, &genai.ClientConfig{
APIKey: os.Getenv("GEMINI_API_KEY"),
Backend: genai.BackendGeminiAPI,
})
history := []*genai.Content{
genai.NewContentFromText("Hi nice to meet you! I have 2 dogs in my house.", genai.RoleUser),
genai.NewContentFromText("Great to meet you. What would you like to know?", genai.RoleModel),
}
chat, _ := client.Chats.Create(ctx, "gemini-2.0-flash", nil, history)
stream := chat.SendMessageStream(ctx, genai.Part{Text: "How many paws are in my house?"})
for chunk, _ := range stream {
part := chunk.Candidates[0].Content.Parts[0]
fmt.Print(part.Text)
}
}
REST
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?alt=sse&key=$GEMINI_API_KEY \
-H 'Content-Type: application/json' \
-X POST \
-d '{
"contents": [
{
"role": "user",
"parts": [
{
"text": "Hello"
}
]
},
{
"role": "model",
"parts": [
{
"text": "Great to meet you. What would you like to know?"
}
]
},
{
"role": "user",
"parts": [
{
"text": "I have two dogs in my house. How many paws are in my house?"
}
]
}
]
}'
Apps Script
// See https://developers.google.com/apps-script/guides/properties
// for instructions on how to set the API key.
const apiKey = PropertiesService.getScriptProperties().getProperty('GEMINI_API_KEY');
function main() {
const payload = {
contents: [
{
role: 'user',
parts: [
{ text: 'Hello' },
],
},
{
role: 'model',
parts: [
{ text: 'Great to meet you. What would you like to know?' },
],
},
{
role: 'user',
parts: [
{ text: 'I have two dogs in my house. How many paws are in my house?' },
],
},
],
};
const url = `https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:streamGenerateContent?key=${apiKey}`;
const options = {
method: 'POST',
contentType: 'application/json',
payload: JSON.stringify(payload)
};
const response = UrlFetchApp.fetch(url, options);
const data = JSON.parse(response);
const content = data['candidates'][0]['content']['parts'][0]['text'];
console.log(content);
}
Unterstützte Modelle
Alle Modelle der Gemini-Familie unterstützen die Textgenerierung. Weitere Informationen zu den Modellen und ihren Funktionen finden Sie auf der Seite Modelle.
Best Practices
Tipps zu Prompts
Für die grundlegende Textgenerierung reicht oft ein Zero-Shot-Prompt aus, ohne dass Beispiele, Systemanweisungen oder eine bestimmte Formatierung erforderlich sind.
Für individuellere Ergebnisse:
- Verwenden Sie Systemanweisungen, um das Modell zu steuern.
- Geben Sie einige Beispielinputs und ‑outputs an, um das Modell zu steuern. Dies wird oft als Few-Shot-Prompting bezeichnet.
- Für erweiterte Anwendungsfälle können Sie eine Feinabstimmung vornehmen.
Weitere Tipps finden Sie in unserem Leitfaden für Prompt-Entwicklung.
Strukturierte Ausgabe
In einigen Fällen benötigen Sie möglicherweise eine strukturierte Ausgabe, z. B. JSON. Weitere Informationen finden Sie in unserem Leitfaden zu strukturierten Datenausgaben.
Nächste Schritte
- Erste Schritte mit der Gemini API in Colab
- Hier finden Sie Informationen zu den Funktionen von Gemini für das Bild, Video, Audio und Dokumentverständnis.
- Weitere Informationen zu Strategien für multimodale Dateiprompts