mirror of
https://github.com/microsoft/autogen.git
synced 2025-07-04 07:26:28 +00:00
32d2a18bf1
<!-- Thank you for your contribution! Please review https://microsoft.github.io/autogen/docs/Contribute before opening a pull request. --> <!-- Please add a reviewer to the assignee section when you create a PR. If you don't have the access to it, we will shortly find a reviewer and assign them to your PR. --> ## Why are these changes needed? https://github.com/user-attachments/assets/e160f16d-f42d-49e2-a6c6-687e4e6786f4 Enable file upload/paste as a task in AGS. Enables tasks like - Can you research and fact check the ideas in this screenshot? - Summarize this file Only text and images supported for now Underneath, it constructs TextMessage and Multimodal messages as the task. <!-- Please give a short summary of the change and the problem this solves. --> ## Related issue number <!-- For example: "Closes #1234" --> Closes #5773 ## Checks - [ ] I've included any doc changes needed for <https://microsoft.github.io/autogen/>. See <https://github.com/microsoft/autogen/blob/main/CONTRIBUTING.md> to build and test documentation locally. - [ ] I've added tests (if relevant) corresponding to the changes introduced in this PR. - [ ] I've made sure all auto checks have passed. --------- Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
72 lines
2.9 KiB
Python
72 lines
2.9 KiB
Python
import base64
|
|
from typing import Sequence
|
|
|
|
from autogen_agentchat.messages import ChatMessage, MultiModalMessage, TextMessage
|
|
from autogen_core import Image
|
|
from autogen_core.models import UserMessage
|
|
from loguru import logger
|
|
|
|
|
|
def construct_task(query: str, files: list[dict] | None = None) -> Sequence[ChatMessage]:
|
|
"""
|
|
Construct a task from a query string and list of files.
|
|
Returns a list of ChatMessage objects suitable for processing by the agent system.
|
|
|
|
Args:
|
|
query: The text query from the user
|
|
files: List of file objects with properties name, content, and type
|
|
|
|
Returns:
|
|
List of BaseChatMessage objects (TextMessage, MultiModalMessage)
|
|
"""
|
|
if files is None:
|
|
files = []
|
|
|
|
messages = []
|
|
|
|
# Add the user's text query as a TextMessage
|
|
if query:
|
|
messages.append(TextMessage(source="user", content=query))
|
|
|
|
# Process each file based on its type
|
|
for file in files:
|
|
try:
|
|
if file.get("type", "").startswith("image/"):
|
|
# Handle image file using from_base64 method
|
|
# The content is already base64 encoded according to the convertFilesToBase64 function
|
|
image = Image.from_base64(file["content"])
|
|
messages.append(
|
|
MultiModalMessage(
|
|
source="user", content=[image], metadata={"filename": file.get("name", "unknown.img")}
|
|
)
|
|
)
|
|
elif file.get("type", "").startswith("text/"):
|
|
# Handle text file as TextMessage
|
|
text_content = base64.b64decode(file["content"]).decode("utf-8")
|
|
messages.append(
|
|
TextMessage(
|
|
source="user", content=text_content, metadata={"filename": file.get("name", "unknown.txt")}
|
|
)
|
|
)
|
|
else:
|
|
# Log unsupported file types but still try to process based on best guess
|
|
logger.warning(f"Potentially unsupported file type: {file.get('type')} for file {file.get('name')}")
|
|
if file.get("type", "").startswith("application/"):
|
|
# Try to treat as text if it's an application type (like JSON)
|
|
text_content = base64.b64decode(file["content"]).decode("utf-8")
|
|
messages.append(
|
|
TextMessage(
|
|
source="user",
|
|
content=text_content,
|
|
metadata={
|
|
"filename": file.get("name", "unknown.file"),
|
|
"filetype": file.get("type", "unknown"),
|
|
},
|
|
)
|
|
)
|
|
except Exception as e:
|
|
logger.error(f"Error processing file {file.get('name')}: {str(e)}")
|
|
# Continue processing other files even if one fails
|
|
|
|
return messages
|