Query's uitvoeren op AI Gateway-eindpunten voor Unity

Belangrijk

Deze functie bevindt zich in de bètaversie. Accountbeheerders kunnen de toegang tot deze functie beheren via de pagina Previews van de accountconsole. Zie Azure Databricks previews beheren.

Op deze pagina wordt beschreven hoe u query's uitvoert op Eindpunten van Unity AI Gateway met behulp van ondersteunde API's.

Requirements

Ondersteunde API's en integraties

Unity AI Gateway ondersteunt de volgende API's en integraties:

Query-eindpunten met geïntegreerde API's

Unified API's bieden een openAI-compatibele interface om query's uit te voeren op modellen op Azure Databricks. Gebruik geïntegreerde API's om naadloos te schakelen tussen modellen van verschillende providers zonder uw code te wijzigen.

Api voor voltooiing van MLflow-chat

Api voor voltooiing van MLflow-chat

Python

from openai import OpenAI
import os

DATABRICKS_TOKEN = os.environ.get('DATABRICKS_TOKEN')

client = OpenAI(
  api_key=DATABRICKS_TOKEN,
  base_url="https://<workspace-url>/ai-gateway/mlflow/v1"
)

chat_completion = client.chat.completions.create(
  messages=[
    {"role": "user", "content": "Hello!"},
    {"role": "assistant", "content": "Hello! How can I assist you today?"},
    {"role": "user", "content": "What is Databricks?"},
  ],
  model="<ai-gateway-endpoint>",
  max_tokens=256
)

print(chat_completion.choices[0].message.content)

REST API

curl \
  -u token:$DATABRICKS_TOKEN \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<ai-gateway-endpoint>",
    "max_tokens": 256,
    "messages": [
      {"role": "user", "content": "Hello!"},
      {"role": "assistant", "content": "Hello! How can I assist you today?"},
      {"role": "user", "content": "What is Databricks?"}
    ]
  }' \
  https://<workspace-url>/ai-gateway/mlflow/v1/chat/completions

Vervang <workspace-url> door de URL van uw Azure Databricks werkruimte en <ai-gateway-endpoint> door de naam van uw Unity AI Gateway-eindpunt.

MLflow Embeddings-API

MLflow Embeddings-API

Python

from openai import OpenAI
import os

DATABRICKS_TOKEN = os.environ.get('DATABRICKS_TOKEN')

client = OpenAI(
  api_key=DATABRICKS_TOKEN,
  base_url="https://<workspace-url>/ai-gateway/mlflow/v1"
)

embeddings = client.embeddings.create(
  input="What is Databricks?",
  model="<ai-gateway-endpoint>"
)

print(embeddings.data[0].embedding)

REST API

curl \
  -u token:$DATABRICKS_TOKEN \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<ai-gateway-endpoint>",
    "input": "What is Databricks?"
  }' \
  https://<workspace-url>/ai-gateway/mlflow/v1/embeddings

Vervang <workspace-url> door de URL van uw Azure Databricks werkruimte en <ai-gateway-endpoint> door de naam van uw Unity AI Gateway-eindpunt.

Supervisor-API

Supervisor API

De Supervisor-API (/mlflow/v1/responses) is een openresponses-compatibele, provideragnostische API voor het bouwen van agents in beta. Accountbeheerders kunnen toegang inschakelen vanaf de pagina Previews . Zie Azure Databricks previews beheren. Kies het beste model voor uw agentgebruiksscenario tussen providers, zonder dat u uw code hoeft te wijzigen.

Python

from openai import OpenAI
import os

DATABRICKS_TOKEN = os.environ.get('DATABRICKS_TOKEN')

client = OpenAI(
  api_key=DATABRICKS_TOKEN,
  base_url="https://<workspace-url>/ai-gateway/mlflow/v1"
)

response = client.responses.create(
  model="<ai-gateway-endpoint>",
  input=[{"role": "user", "content": "What is Databricks?"}]
)

print(response.output_text)

REST API

curl \
  -u token:$DATABRICKS_TOKEN \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<ai-gateway-endpoint>",
    "input": [
      {"role": "user", "content": "What is Databricks?"}
    ]
  }' \
  https://<workspace-url>/ai-gateway/mlflow/v1/responses

Vervang <workspace-url> door de URL van uw Azure Databricks werkruimte en <ai-gateway-endpoint> door de naam van uw Unity AI Gateway-eindpunt.

Query-eindpunten met systeemeigen API's

Systeemeigen API's bieden providerspecifieke interfaces om query's uit te voeren op modellen op Azure Databricks. Gebruik systeemeigen API's voor toegang tot de nieuwste providerspecifieke functies.

OpenAI-antwoorden-API

OpenAI-antwoorden-API

Python

from openai import OpenAI
import os

DATABRICKS_TOKEN = os.environ.get('DATABRICKS_TOKEN')

client = OpenAI(
  api_key=DATABRICKS_TOKEN,
  base_url="https://<workspace-url>/ai-gateway/openai/v1"
)

response = client.responses.create(
  model="<ai-gateway-endpoint>",
  max_output_tokens=256,
  input=[
    {
      "role": "user",
      "content": [{"type": "input_text", "text": "Hello!"}]
    },
    {
      "role": "assistant",
      "content": [{"type": "output_text", "text": "Hello! How can I assist you today?"}]
    },
    {
      "role": "user",
      "content": [{"type": "input_text", "text": "What is Databricks?"}]
    }
  ]
)

print(response.output)

REST API

curl \
  -u token:$DATABRICKS_TOKEN \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<ai-gateway-endpoint>",
    "max_output_tokens": 256,
    "input": [
      {
        "role": "user",
        "content": [{"type": "input_text", "text": "Hello!"}]
      },
      {
        "role": "assistant",
        "content": [{"type": "output_text", "text": "Hello! How can I assist you today?"}]
      },
      {
        "role": "user",
        "content": [{"type": "input_text", "text": "What is Databricks?"}]
      }
    ]
  }' \
  https://<workspace-url>/ai-gateway/openai/v1/responses

Vervang <workspace-url> door de URL van uw Azure Databricks werkruimte en <ai-gateway-endpoint> door de naam van uw Unity AI Gateway-eindpunt.

Anthropic Messages-API

API voor antropische berichten

Python

import anthropic
import os

DATABRICKS_TOKEN = os.environ.get('DATABRICKS_TOKEN')

client = anthropic.Anthropic(
  api_key="unused",
  base_url="https://<workspace-url>/ai-gateway/anthropic",
  default_headers={
    "Authorization": f"Bearer {DATABRICKS_TOKEN}",
  },
)

message = client.messages.create(
  model="<ai-gateway-endpoint>",
  max_tokens=256,
  messages=[
    {"role": "user", "content": "Hello!"},
    {"role": "assistant", "content": "Hello! How can I assist you today?"},
    {"role": "user", "content": "What is Databricks?"},
  ],
)

print(message.content[0].text)

REST API

curl \
  -u token:$DATABRICKS_TOKEN \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "model": "<ai-gateway-endpoint>",
    "max_tokens": 256,
    "messages": [
      {"role": "user", "content": "Hello!"},
      {"role": "assistant", "content": "Hello! How can I assist you today?"},
      {"role": "user", "content": "What is Databricks?"}
    ]
  }' \
  https://<workspace-url>/ai-gateway/anthropic/v1/messages

Vervang <workspace-url> door de URL van uw Azure Databricks werkruimte en <ai-gateway-endpoint> door de naam van uw Unity AI Gateway-eindpunt.

Google Gemini-API

Google Gemini-API

Python

from google import genai
from google.genai import types
import os

DATABRICKS_TOKEN = os.environ.get('DATABRICKS_TOKEN')

client = genai.Client(
  api_key="databricks",
  http_options=types.HttpOptions(
    base_url="https://<workspace-url>/ai-gateway/gemini",
    headers={
      "Authorization": f"Bearer {DATABRICKS_TOKEN}",
    },
  ),
)

response = client.models.generate_content(
  model="<ai-gateway-endpoint>",
  contents=[
    types.Content(
      role="user",
      parts=[types.Part(text="Hello!")],
    ),
    types.Content(
      role="model",
      parts=[types.Part(text="Hello! How can I assist you today?")],
    ),
    types.Content(
      role="user",
      parts=[types.Part(text="What is Databricks?")],
    ),
  ],
  config=types.GenerateContentConfig(
    max_output_tokens=256,
  ),
)

print(response.text)

REST API

curl \
  -u token:$DATABRICKS_TOKEN \
  -X POST \
  -H "Content-Type: application/json" \
  -d '{
    "contents": [
      {
        "role": "user",
        "parts": [{"text": "Hello!"}]
      },
      {
        "role": "model",
        "parts": [{"text": "Hello! How can I assist you today?"}]
      },
      {
        "role": "user",
        "parts": [{"text": "What is Databricks?"}]
      }
    ],
    "generationConfig": {
      "maxOutputTokens": 256
    }
  }' \
  https://<workspace-url>/ai-gateway/gemini/v1beta/models/<ai-gateway-endpoint>:generateContent

Vervang <workspace-url> door de URL van uw Azure Databricks werkruimte en <ai-gateway-endpoint> door de naam van uw Unity AI Gateway-eindpunt.

Volgende stappen

  • Supervisor-API (bèta) - voer werkstromen voor meerdere uitvoeringen van agents uit met gehoste hulpprogramma's via /mlflow/v1/responses
  • Last updated on