Spaces:
Paused
Paused
File size: 2,933 Bytes
0b9dc2e | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 | # -*- coding: utf-8 -*-
"""Example of DashScope model calls with MultiAgentFormatter and image input.
Demonstrates combining DashScopeMultiAgentFormatter with multimodal (vision)
content: Alice shares an image in a multi-agent conversation, and the model
is asked to summarize what everyone is looking at.
"""
import asyncio
import os
from _utils import stream_and_collect
from agentscope.formatter import DashScopeMultiAgentFormatter
from agentscope.message import Msg, TextBlock, DataBlock, URLSource
from agentscope.model import DashScopeChatModel
from agentscope.credential import DashScopeCredential
TEST_IMAGE_URL = (
"https://help-static-aliyun-doc.aliyuncs.com/file-manage"
"-files/zh-CN/20241022/emyrja/dog_and_girl.jpeg"
)
async def example_multiagent_image_url() -> None:
"""Multi-agent conversation where Alice shares an image for the group."""
formatter = DashScopeMultiAgentFormatter()
model = DashScopeChatModel(
credential=DashScopeCredential(
api_key=os.environ["DASHSCOPE_API_KEY"],
),
model="qwen3.5-plus",
stream=True,
context_size=1_000_000,
parameters=DashScopeChatModel.Parameters(thinking_enable=True),
formatter=formatter,
)
image_block = DataBlock(
source=URLSource(url=TEST_IMAGE_URL, media_type="image/jpeg"),
)
msgs = [
Msg(
name="system",
content=[
TextBlock(
text=(
"You are a helpful moderator in a group chat. "
"Summarize what the image shows and what the "
"participants said."
),
),
],
role="system",
),
Msg(
name="alice",
content=[
TextBlock(
text="Hey everyone, look at this cute photo I took!",
),
image_block,
],
role="user",
),
Msg(
name="bob",
content=[
TextBlock(text="Aww, that's adorable! Where was this taken?"),
],
role="assistant",
),
Msg(
name="alice",
content=[TextBlock(text="At the local park yesterday.")],
role="user",
),
Msg(
name="moderator",
content=[
TextBlock(
text="Please summarize the image content and the "
"conversation in one paragraph.",
),
],
role="user",
),
]
print("=== Multi-Agent + Multimodal Call ===")
await stream_and_collect(await model(msgs))
if __name__ == "__main__":
asyncio.run(example_multiagent_image_url())
|