Kompatibilität mit OpenAI

Sie können auf Gemini-Modelle mit den OpenAI-Bibliotheken (Python und TypeScript/JavaScript) und der REST API zugreifen. Dazu müssen Sie drei Codezeilen aktualisieren und Ihren Gemini API-Schlüssel verwenden. Wenn Sie noch keine OpenAI-Bibliotheken nutzen, sollten Sie die Gemini API direkt aufrufen.

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
    model="gemini-1.5-flash",
    n=1,
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {
            "role": "user",
            "content": "Explain to me how AI works"
        }
    ]
)

print(response.choices[0].message)

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

const response = await openai.chat.completions.create({
    model: "gemini-1.5-flash",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        {
            role: "user",
            content: "Explain to me how AI works",
        },
    ],
});

console.log(response.choices[0].message);

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer GEMINI_API_KEY" \
-d '{
    "model": "gemini-1.5-flash",
    "messages": [
        {"role": "user", "content": "Explain to me how AI works"}
    ]
    }'

Streaming

Die Gemini API unterstützt Streamingantworten.

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.chat.completions.create(
  model="gemini-1.5-flash",
  messages=[
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  stream=True
)

for chunk in response:
    print(chunk.choices[0].delta)

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
  const completion = await openai.chat.completions.create({
    model: "gemini-1.5-flash",
    messages: [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    stream: true,
  });

  for await (const chunk of completion) {
    console.log(chunk.choices[0].delta.content);
  }
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer GEMINI_API_KEY" \
-d '{
    "model": "gemini-1.5-flash",
    "messages": [
        {"role": "user", "content": "Explain to me how AI works"}
    ],
    "stream": true
  }'

Funktionsaufrufe

Mit Funktionsaufrufen können Sie einfacher strukturierte Datenausgaben aus generativen Modellen abrufen. Diese Funktion wird von der Gemini API unterstützt.

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

tools = [
  {
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get the weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. Chicago, IL",
          },
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
        },
        "required": ["location"],
      },
    }
  }
]

messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}]
response = client.chat.completions.create(
  model="gemini-1.5-flash",
  messages=messages,
  tools=tools,
  tool_choice="auto"
)

print(response)

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
  const messages = [{"role": "user", "content": "What's the weather like in Chicago today?"}];
  const tools = [
      {
        "type": "function",
        "function": {
          "name": "get_weather",
          "description": "Get the weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. Chicago, IL",
              },
              "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location"],
          },
        }
      }
  ];

  const response = await openai.chat.completions.create({
    model: "gemini-1.5-flash",
    messages: messages,
    tools: tools,
    tool_choice: "auto",
  });

  console.log(response);
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer GEMINI_API_KEY" \
-d '{
  "model": "gemini-1.5-flash",
  "messages": [
    {
      "role": "user",
      "content": "What'\''s the weather like in Chicago today?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "object",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. Chicago, IL"
            },
            "unit": {
              "type": "string",
              "enum": ["celsius", "fahrenheit"]
            }
          },
          "required": ["location"]
        }
      }
    }
  ],
  "tool_choice": "auto"
}'

Bildverständnis

Gemini-Modelle sind nativ multimodal und bieten bei vielen gängigen Aufgaben im Bereich Computer Vision eine erstklassige Leistung.

Python

import base64
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

# Function to encode the image
def encode_image(image_path):
  with open(image_path, "rb") as image_file:
    return base64.b64encode(image_file.read()).decode('utf-8')

# Getting the base64 string
base64_image = encode_image("Path/to/agi/image.jpeg")

response = client.chat.completions.create(
  model="gemini-1.5-flash",
  messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?",
        },
        {
          "type": "image_url",
          "image_url": {
            "url":  f"data:image/jpeg;base64,{base64_image}"
          },
        },
      ],
    }
  ],
)

print(response.choices[0])

Node.js

import OpenAI from "openai";
import fs from 'fs/promises';

const openai = new OpenAI({
  apiKey: "GEMINI_API_KEY",
  baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function encodeImage(imagePath) {
  try {
    const imageBuffer = await fs.readFile(imagePath);
    return imageBuffer.toString('base64');
  } catch (error) {
    console.error("Error encoding image:", error);
    return null;
  }
}

async function main() {
  const imagePath = "Path/to/agi/image.jpeg";
  const base64Image = await encodeImage(imagePath);

  const messages = [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?",
        },
        {
          "type": "image_url",
          "image_url": {
            "url": `data:image/jpeg;base64,${base64Image}`
          },
        },
      ],
    }
  ];

  try {
    const response = await openai.chat.completions.create({
      model: "gemini-1.5-flash",
      messages: messages,
    });

    console.log(response.choices[0]);
  } catch (error) {
    console.error("Error calling Gemini API:", error);
  }
}

main();

REST

bash -c '
  base64_image=$(base64 -i "Path/to/agi/image.jpeg");
  curl "https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" \
    -H "Content-Type: application/json" \
    -H "Authorization: Bearer GEMINI_API_KEY" \
    -d "{
      \"model\": \"gemini-1.5-flash\",
      \"messages\": [
        {
          \"role\": \"user\",
          \"content\": [
            { \"type\": \"text\", \"text\": \"What is in this image?\" },
            {
              \"type\": \"image_url\",
              \"image_url\": { \"url\": \"data:image/jpeg;base64,${base64_image}\" }
            }
          ]
        }
      ]
    }"
'

Strukturierte Ausgabe

Gemini-Modelle können JSON-Objekte in einer beliebigen von Ihnen definierten Struktur ausgeben.

Python

from pydantic import BaseModel
from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

class CalendarEvent(BaseModel):
    name: str
    date: str
    participants: list[str]

completion = client.beta.chat.completions.parse(
    model="gemini-1.5-flash",
    messages=[
        {"role": "system", "content": "Extract the event information."},
        {"role": "user", "content": "John and Susan are going to an AI conference on Friday."},
    ],
    response_format=CalendarEvent,
)

print(completion.choices[0].message.parsed)

Node.js

import OpenAI from "openai";
import { zodResponseFormat } from "openai/helpers/zod";
import { z } from "zod";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai"
});

const CalendarEvent = z.object({
  name: z.string(),
  date: z.string(),
  participants: z.array(z.string()),
});

const completion = await openai.beta.chat.completions.parse({
  model: "gemini-1.5-flash",
  messages: [
    { role: "system", content: "Extract the event information." },
    { role: "user", content: "John and Susan are going to an AI conference on Friday" },
  ],
  response_format: zodResponseFormat(CalendarEvent, "event"),
});

const event = completion.choices[0].message.parsed;
console.log(event);

Einbettungen

Mithilfe von Texteinbettungen wird die Ähnlichkeit von Textstrings gemessen. Sie können mit der Gemini API generiert werden.

Python

from openai import OpenAI

client = OpenAI(
    api_key="GEMINI_API_KEY",
    base_url="https://generativelanguage.googleapis.com/v1beta/openai/"
)

response = client.embeddings.create(
    input="Your text string goes here",
    model="text-embedding-004"
)

print(response.data[0].embedding)

Node.js

import OpenAI from "openai";

const openai = new OpenAI({
    apiKey: "GEMINI_API_KEY",
    baseURL: "https://generativelanguage.googleapis.com/v1beta/openai/"
});

async function main() {
  const embedding = await openai.embeddings.create({
    model: "text-embedding-004",
    input: "Your text string goes here",
  });

  console.log(embedding);
}

main();

REST

curl "https://generativelanguage.googleapis.com/v1beta/openai/embeddings" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer GEMINI_API_KEY" \
-d '{
    "input": "Your text string goes here",
    "model": "text-embedding-004"
  }'

Aktuelle Beschränkungen

Die Unterstützung für die OpenAI-Bibliotheken befindet sich noch in der Betaphase, während wir die Funktionsunterstützung ausweiten.

Wenn Sie Fragen zu unterstützten Parametern, anstehenden Funktionen oder Problemen beim Einstieg in Gemini haben, können Sie sich im Entwicklerforum an uns wenden.