Method: projects.locations.endpoints.chat.completions

Exposes an OpenAI-compatible endpoint for chat completions.

Endpoint

post https://aiplatform.googleapis.com/v1/{endpoint}/chat/completions

Path parameters

endpoint string

Required. The name of the endpoint requested to serve the prediction. Format: projects/{project}/locations/{location}/endpoints/{endpoint}

Request body

The request body contains an instance of HttpBody.

Example request

Text

Python

import vertexai
import openai

from google.auth import default, transport

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"

vertexai.init(project=project_id, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# # OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{project_id}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-002",
    messages=[{"role": "user", "content": "Why is the sky blue?"}],
)

print(response)
chat_completions_non_streaming_text.py

Image

Python

import vertexai
import openai

from google.auth import default, transport

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"

vertexai.init(project=project_id, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{project_id}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-002",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe the following image:"},
                {
                    "type": "image_url",
                    "image_url": "gs://cloud-samples-data/generative-ai/image/scones.jpg",
                },
            ],
        }
    ],
)

print(response)
chat_completions_non_streaming_image.py

Text (streaming)

Python

import vertexai
import openai

from google.auth import default, transport

# TODO(developer): Update and un-comment below lines
# project_id = "PROJECT_ID"
# location = "us-central1"

vertexai.init(project=project_id, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{project_id}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-002",
    messages=[{"role": "user", "content": "Why is the sky blue?"}],
    stream=True,
)
for chunk in response:
    print(chunk)
chat_completions_streaming_text.py

Image (streaming)

Python

import vertexai
import openai

from google.auth import default, transport

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

vertexai.init(project=PROJECT_ID, location=location)

# Programmatically get an access token
credentials, _ = default(scopes=["https://www.googleapis.com/auth/cloud-platform"])
auth_request = transport.requests.Request()
credentials.refresh(auth_request)

# OpenAI Client
client = openai.OpenAI(
    base_url=f"https://{location}-aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{location}/endpoints/openapi",
    api_key=credentials.token,
)

response = client.chat.completions.create(
    model="google/gemini-1.5-flash-002",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe the following image:"},
                {
                    "type": "image_url",
                    "image_url": "gs://cloud-samples-data/generative-ai/image/scones.jpg",
                },
            ],
        }
    ],
    stream=True,
)
for chunk in response:
    print(chunk.choices[0].delta.content)
# Example response:
# Here's a description of the image:
# High-angle, close-up view of a rustic scene featuring several blueberry
# scones arranged on a piece of parchment paper...
chat_openai_image_stream_example.py

Response body

If successful, the response is a generic HTTP response whose format is defined by the method.