Streaming respons dari model AI Generatif

Streaming melibatkan penerimaan respons terhadap perintah saat dihasilkan. Artinya, segera setelah model menghasilkan token output, token output akan dikirim.

Anda dapat membuat permintaan streaming ke Large Language Model (LLM) (model bahasa besar) Vertex AI menggunakan hal berikut:

API streaming dan non-streaming menggunakan parameter yang sama, serta tidak ada perbedaan harga dan kuota.

Vertex AI Studio

Anda dapat menggunakan Vertex AI Studio untuk mendesain dan menjalankan perintah serta menerima respons yang di-streaming. Dari halaman desain perintah, klik tombol Streaming Response untuk mengaktifkan streaming.

Tombol respons streaming

Bahasa yang didukung

Kode bahasa Bahasa
en Inggris
es Spanyol
pt Portugis
fr Prancis
it Italia
de Jerman
ja Jepang
ko Korea
hi Hindi
zh China
id Indonesia

Contoh

Anda dapat memanggil Streaming API menggunakan salah satu dari hal berikut:

REST API dengan peristiwa yang dikirim server (SSE)

Parameternya berbeda di seluruh jenis model yang digunakan dalam contoh berikut:

Teks

Model yang didukung saat ini adalah text-bison dan text-unicorn. Lihat versi yang tersedia.

Minta

  PROJECT_ID=YOUR_PROJECT_ID
  PROMPT="PROMPT"
  MODEL_ID=text-bison

  curl \
  -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:serverStreamingPredict?alt=sse -d \
  '{
    "inputs": [
      {
        "struct_val": {
          "prompt": {
            "string_val": [ "'"${PROMPT}"'" ]
          }
        }
      }
    ],
    "parameters": {
      "struct_val": {
        "temperature": { "float_val": 0.8 },
        "maxOutputTokens": { "int_val": 1024 },
        "topK": { "int_val": 40 },
        "topP": { "float_val": 0.95 }
      }
    }
  }'

Respons

Respons adalah pesan peristiwa yang dikirim server.

  data: {"outputs": [{"structVal": {"content": {"stringVal": [RESPONSE]},"safetyAttributes": {"structVal": {"blocked": {"boolVal": [BOOLEAN]},"categories": {"listVal": [{"stringVal": [Safety category name]}]},"scores": {"listVal": [{"doubleVal": [Safety category score]}]}}},"citationMetadata": {"structVal": {"citations": {}}}}}]}

Chat

Model yang didukung saat ini adalah chat-bison. Lihat versi yang tersedia.

Minta

PROJECT_ID=YOUR_PROJECT_ID
PROMPT="PROMPT"
AUTHOR="USER"
MODEL_ID=chat-bison

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:serverStreamingPredict?alt=sse -d \
$'{
  "inputs": [
    {
      "struct_val": {
        "messages": {
          "list_val": [
            {
              "struct_val": {
                "content": {
                  "string_val": [ "'"${PROMPT}"'" ]
                },
                "author": {
                  "string_val": [ "'"${AUTHOR}"'"]
                }
              }
            }
          ]
        }
      }
    }
  ],
  "parameters": {
    "struct_val": {
      "temperature": { "float_val": 0.5 },
      "maxOutputTokens": { "int_val": 1024 },
      "topK": { "int_val": 40 },
      "topP": { "float_val": 0.95 }
    }
  }
}'

Respons

Respons adalah pesan peristiwa yang dikirim server.

data: {"outputs": [{"structVal": {"candidates": {"listVal": [{"structVal": {"author": {"stringVal": [AUTHOR]},"content": {"stringVal": [RESPONSE]}}}]},"citationMetadata": {"listVal": [{"structVal": {"citations": {}}}]},"safetyAttributes": {"structVal": {"blocked": {"boolVal": [BOOLEAN]},"categories": {"listVal": [{"stringVal": [Safety category name]}]},"scores": {"listVal": [{"doubleVal": [Safety category score]}]}}}}}]}

Kode

Model yang didukung saat ini adalah code-bison. Lihat versi yang tersedia.

Minta

PROJECT_ID=YOUR_PROJECT_ID
PROMPT="PROMPT"
MODEL_ID=code-bison

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:serverStreamingPredict?alt=sse -d \
$'{
  "inputs": [
    {
      "struct_val": {
        "prefix": {
          "string_val": [ "'"${PROMPT}"'" ]
        }
      }
    }
  ],
  "parameters": {
    "struct_val": {
      "temperature": { "float_val": 0.8 },
      "maxOutputTokens": { "int_val": 1024 },
      "topK": { "int_val": 40 },
      "topP": { "float_val": 0.95 }
    }
  }
}'

Respons

Respons adalah pesan peristiwa yang dikirim server.

data: {"outputs": [{"structVal": {"citationMetadata": {"structVal": {"citations": {}}},"safetyAttributes": {"structVal": {"blocked": {"boolVal": [BOOLEAN]},"categories": {"listVal": [{"stringVal": [Safety category name]}]},"scores": {"listVal": [{"doubleVal": [Safety category score]}]}}},"content": {"stringVal": [RESPONSE]}}}]}

Chat kode

Model yang didukung saat ini adalah codechat-bison. Lihat versi yang tersedia.

Minta

PROJECT_ID=YOUR_PROJECT_ID
PROMPT="PROMPT"
AUTHOR="USER"
MODEL_ID=codechat-bison

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:serverStreamingPredict?alt=sse -d \
$'{
  "inputs": [
    {
      "struct_val": {
        "messages": {
          "list_val": [
            {
              "struct_val": {
                "content": {
                  "string_val": [ "'"${PROMPT}"'" ]
                },
                "author": {
                  "string_val": [ "'"${AUTHOR}"'"]
                }
              }
            }
          ]
        }
      }
    }
  ],
  "parameters": {
    "struct_val": {
      "temperature": { "float_val": 0.5 },
      "maxOutputTokens": { "int_val": 1024 },
      "topK": { "int_val": 40 },
      "topP": { "float_val": 0.95 }
    }
  }
}'

Respons

Respons adalah pesan peristiwa yang dikirim server.

data: {"outputs": [{"structVal": {"safetyAttributes": {"structVal": {"blocked": {"boolVal": [BOOLEAN]},"categories": {"listVal": [{"stringVal": [Safety category name]}]},"scores": {"listVal": [{"doubleVal": [Safety category score]}]}}},"citationMetadata": {"listVal": [{"structVal": {"citations": {}}}]},"candidates": {"listVal": [{"structVal": {"content": {"stringVal": [RESPONSE]},"author": {"stringVal": [AUTHOR]}}}]}}}]}

REST API

Parameternya berbeda di seluruh jenis model yang digunakan dalam contoh berikut:

Teks

Model yang didukung saat ini adalah text-bison dan text-unicorn. Lihat versi yang tersedia.

Minta

  PROJECT_ID=YOUR_PROJECT_ID
  PROMPT="PROMPT"
  MODEL_ID=text-bison

  curl \
  -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:serverStreamingPredict -d \
  '{
    "inputs": [
      {
        "struct_val": {
          "prompt": {
            "string_val": [ "'"${PROMPT}"'" ]
          }
        }
      }
    ],
    "parameters": {
      "struct_val": {
        "temperature": { "float_val": 0.8 },
        "maxOutputTokens": { "int_val": 1024 },
        "topK": { "int_val": 40 },
        "topP": { "float_val": 0.95 }
      }
    }
  }'

Respons

{
  "outputs": [
    {
      "structVal": {
        "citationMetadata": {
          "structVal": {
            "citations": {}
          }
        },
        "safetyAttributes": {
          "structVal": {
            "categories": {},
            "scores": {},
            "blocked": {
              "boolVal": [
                false
              ]
            }
          }
        },
        "content": {
          "stringVal": [
            RESPONSE
          ]
        }
      }
    }
  ]
}

Chat

Model yang didukung saat ini adalah chat-bison. Lihat versi yang tersedia.

Minta

PROJECT_ID=YOUR_PROJECT_ID
PROMPT="PROMPT"
AUTHOR="USER"
MODEL_ID=chat-bison

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:serverStreamingPredict -d \
$'{
  "inputs": [
    {
      "struct_val": {
        "messages": {
          "list_val": [
            {
              "struct_val": {
                "content": {
                  "string_val": [ "'"${PROMPT}"'" ]
                },
                "author": {
                  "string_val": [ "'"${AUTHOR}"'"]
                }
              }
            }
          ]
        }
      }
    }
  ],
  "parameters": {
    "struct_val": {
      "temperature": { "float_val": 0.5 },
      "maxOutputTokens": { "int_val": 1024 },
      "topK": { "int_val": 40 },
      "topP": { "float_val": 0.95 }
    }
  }
}'

Respons

{
  "outputs": [
    {
      "structVal": {
        "candidates": {
          "listVal": [
            {
              "structVal": {
                "content": {
                  "stringVal": [
                    RESPONSE
                  ]
                },
                "author": {
                  "stringVal": [
                    AUTHOR
                  ]
                }
              }
            }
          ]
        },
        "citationMetadata": {
          "listVal": [
            {
              "structVal": {
                "citations": {}
              }
            }
          ]
        },
        "safetyAttributes": {
          "listVal": [
            {
              "structVal": {
                "categories": {},
                "blocked": {
                  "boolVal": [
                    false
                  ]
                },
                "scores": {}
              }
            }
          ]
        }
      }
    }
  ]
}

Kode

Model yang didukung saat ini adalah code-bison. Lihat versi yang tersedia.

Minta

PROJECT_ID=YOUR_PROJECT_ID
PROMPT="PROMPT"
MODEL_ID=code-bison

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:serverStreamingPredict -d \
$'{
  "inputs": [
    {
      "struct_val": {
        "prefix": {
          "string_val": [ "'"${PROMPT}"'" ]
        }
      }
    }
  ],
  "parameters": {
    "struct_val": {
      "temperature": { "float_val": 0.8 },
      "maxOutputTokens": { "int_val": 1024 },
      "topK": { "int_val": 40 },
      "topP": { "float_val": 0.95 }
    }
  }
}'

Respons

{
  "outputs": [
    {
      "structVal": {
        "safetyAttributes": {
          "structVal": {
            "categories": {},
            "scores": {},
            "blocked": {
              "boolVal": [
                false
              ]
            }
          }
        },
        "citationMetadata": {
          "structVal": {
            "citations": {}
          }
        },
        "content": {
          "stringVal": [
            RESPONSE
          ]
        }
      }
    }
  ]
}

Chat kode

Model yang didukung saat ini adalah codechat-bison. Lihat versi yang tersedia.

Minta

PROJECT_ID=YOUR_PROJECT_ID
PROMPT="PROMPT"
AUTHOR="USER"
MODEL_ID=codechat-bison

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://us-central1-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/us-central1/publishers/google/models/${MODEL_ID}:serverStreamingPredict -d \
$'{
  "inputs": [
    {
      "struct_val": {
        "messages": {
          "list_val": [
            {
              "struct_val": {
                "content": {
                  "string_val": [ "'"${PROMPT}"'" ]
                },
                "author": {
                  "string_val": [ "'"${AUTHOR}"'"]
                }
              }
            }
          ]
        }
      }
    }
  ],
  "parameters": {
    "struct_val": {
      "temperature": { "float_val": 0.5 },
      "maxOutputTokens": { "int_val": 1024 },
      "topK": { "int_val": 40 },
      "topP": { "float_val": 0.95 }
    }
  }
}'

Respons

{
  "outputs": [
    {
      "structVal": {
        "candidates": {
          "listVal": [
            {
              "structVal": {
                "content": {
                  "stringVal": [
                    RESPONSE
                  ]
                },
                "author": {
                  "stringVal": [
                    AUTHOR
                  ]
                }
              }
            }
          ]
        },
        "citationMetadata": {
          "listVal": [
            {
              "structVal": {
                "citations": {}
              }
            }
          ]
        },
        "safetyAttributes": {
          "listVal": [
            {
              "structVal": {
                "categories": {},
                "blocked": {
                  "boolVal": [
                    false
                  ]
                },
                "scores": {}
              }
            }
          ]
        }
      }
    }
  ]
}

Vertex AI SDK untuk Python

Untuk mengetahui informasi tentang cara menginstal Vertex AI SDK untuk Python, lihat Menginstal Vertex AI SDK untuk Python.

Teks 

  import vertexai
  from vertexai.language_models import TextGenerationModel

  def streaming_prediction(
      project_id: str,
      location: str,
  ) -> str:
      """Streaming Text Example with a Large Language Model"""

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

  text_generation_model = TextGenerationModel.from_pretrained("text-bison")
  parameters = {
      "temperature": temperature,  # Temperature controls the degree of randomness in token selection.
      "max_output_tokens": 256,  # Token limit determines the maximum amount of text output.
      "top_p": 0.8,  # Tokens are selected from most probable to least until the sum of their probabilities equals the top_p value.
      "top_k": 40,  # A top_k of 1 means the selected token is the most probable among all tokens.
  }

  responses = text_generation_model.predict_streaming(prompt="Give me ten interview questions for the role of program manager.", **parameters)
  for response in responses:
      `print(response)`

Chat 

import vertexai
from vertexai.language_models import ChatModel, InputOutputTextPair

def streaming_prediction(
    project_id: str,
    location: str,
) -> str:
    """Streaming Chat Example with a Large Language Model"""

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

    chat_model = ChatModel.from_pretrained("chat-bison")

    parameters = {
        "temperature": 0.8,  # Temperature controls the degree of randomness in token selection.
        "max_output_tokens": 256,  # Token limit determines the maximum amount of text output.
        "top_p": 0.95,  # Tokens are selected from most probable to least until the sum of their probabilities equals the top_p value.
        "top_k": 40,  # A top_k of 1 means the selected token is the most probable among all tokens.
    }

    chat = chat_model.start_chat(
        context="My name is Miles. You are an astronomer, knowledgeable about the solar system.",
        examples=[
            InputOutputTextPair(
                input_text="How many moons does Mars have?",
                output_text="The planet Mars has two moons, Phobos and Deimos.",
            ),
        ],
    )

    responses = chat.send_message_streaming(
        message="How many planets are there in the solar system?", **parameters)
    for response in responses:
        `print(response)`

Kode 

import vertexai
from vertexai.language_models import CodeGenerationModel

def streaming_prediction(
    project_id: str,
    location: str,
) -> str:
    """Streaming Chat Example with a Large Language Model"""

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

    code_model = CodeGenerationModel.from_pretrained("code-bison")
    parameters = {
        "temperature": 0.8,  # Temperature controls the degree of randomness in token selection.
        "max_output_tokens": 256,  # Token limit determines the maximum amount of text output.
    }

    responses = code_model.predict_streaming(
        prefix="Write a function that checks if a year is a leap year.", **parameters)
    for response in responses:
        `print(response)`

Chat kode 

import vertexai
from vertexai.language_models import CodeChatModel

def streaming_prediction(
    project_id: str,
    location: str,
) -> str:
    """Streaming Chat Example with a Large Language Model"""

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

    codechat_model = CodeChatModel.from_pretrained("codechat-bison")
    parameters = {
        "temperature": 0.8,  # Temperature controls the degree of randomness in token selection.
        "max_output_tokens": 1024,  # Token limit determines the maximum amount of text output.
    }
    codechat = codechat_model.start_chat()

    responses = codechat.send_message_streaming(
        message="Please help write a function to calculate the min of two numbers", **parameters)
    for response in responses:
        `print(response)`

Library klien yang tersedia

Anda dapat menggunakan salah satu library klien berikut untuk melakukan streaming respons:

  • Python
  • Node.js
  • Java
  • Go
  • C#

Untuk melihat contoh permintaan dan respons kode menggunakan REST API, lihat Contoh menggunakan REST API.

Untuk melihat contoh permintaan dan respons kode menggunakan Vertex AI SDK untuk Python, lihat Contoh penggunaan Vertex AI SDK untuk Python.

Responsible AI

Filter responsible Artificial Intelligence (RAI) memindai output streaming saat model menghasilkannya. Jika pelanggaran terdeteksi, filter akan memblokir token output yang melanggar, dan menampilkan output dengan tanda diblokir di bagian safetyAttributes, yang menghentikan streaming.

Langkah berikutnya