Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Docs fix #272

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@

ShellAgent is the most powerful, open, and modular Agentic Framework open-sourced by MyShell. It's deeply integrated into MyShell's ecosystem, allowing developers to build powerful AI Apps, publish to MyShell, and earn rewards.

The current ShellAgent mode is on Windows Only, and requires a decent GPU to run. We will support Cloud and Mac version in the future. Due to limited server capability, Cloud version is only supported with limited developers. If you need Cloud version, please contact us with your past building experience, we will gradually open up more seats for developers who need Cloud version.
The current ShellAgent mode is on Windows Only, and requires a decent GPU to run. We will support Cloud and Mac versions in the future. Due to limited server capability, Cloud version is only supported with limited developers. If you need Cloud version, please contact us with your past building experience, we will gradually open up more seats for developers who need Cloud version.

The widget supports currently focus mainly on image generation relevant ones, we will make sure more widgets will be supported in Q4 2024.

Expand All @@ -22,7 +22,7 @@ You can find the download link for the ShellAgent installation package from the

The installation package includes the ShellAgent framework engine, commonly used widgets and models.

After downloading, extract it locally to complete the installation. No need to handle environment issues.
After downloading, extract it locally to complete the installation. No need to handle environmental issues.

### 3. Run ShellAgent

Expand All @@ -32,7 +32,7 @@ Click run.bat in the main directory, wait for the initialization to complete in

For ComfyUI users, ShellAgent supports importing models from local ComfyUI projects.

Set the storage path (absolute path) of the models in settings, and we will merge the models of ShellAgent and the specified directory through symbolic links. After merging, the two directories are similar like shortcuts.
Set the storage path (absolute path) of the models in settings, and we will merge the models of ShellAgent and the specified directory through symbolic links. After merging, the two directories are similar to shortcuts.

### Common Issues During Installation

Expand Down
2 changes: 1 addition & 1 deletion proconfig/core/block.py
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,7 @@ class WorkflowTask(TaskBase):
class ComfyWorkflowTask(WidgetTask):
mode: Literal["widget", "comfy_workflow"] = "widget"
api: str # must be provided
comfy_workflow_id: str | None = None # might be depreacated later
comfy_workflow_id: str | None = None # might be deprecated later
location: str | None = None

Task = Union[ComfyWorkflowTask, BlockTask, WidgetTask, WorkflowTask]
Expand Down
4 changes: 2 additions & 2 deletions proconfig/runners/runner.py
Original file line number Diff line number Diff line change
Expand Up @@ -282,7 +282,7 @@ def save_breakpoint_backup(self, workflow: Workflow, completed_tasks, environ, l

with open(os.path.join(save_dir, f'{workflow.debug_uuid}.pkl'), 'wb') as file:
cloudpickle.dump(data, file)
# since the file may be very large (> 20G?). Flush should be ensured here to gaurantee the save process complete
# since the file may be very large (> 20G?). Flush should be ensured here to guarantee the save process complete
file.flush()
os.fsync(file.fileno())

Expand Down Expand Up @@ -624,4 +624,4 @@ def run_automata(self, automata: Automata, sess_state: SessionState, payload: di
event_mapping = {f'MESSAGE_{message_count}_{k}' if k != "CHAT" else k: v for k, v in event_mapping.items()}
sess_state.event_mapping.update(event_mapping)

return sess_state, render
return sess_state, render
2 changes: 1 addition & 1 deletion servers/common.py
Original file line number Diff line number Diff line change
Expand Up @@ -512,7 +512,7 @@ async def check_repo_status():
# sort and get the latest 2 tags
stable_tags = sorted(stable_tags, key=lambda x: [int(i) for i in x.split('/')[-1][1:].split('.')], reverse=True)[:2]
preview_tags = sorted(preview_tags, key=lambda x: parse_version(x), reverse=True)[:2]
# remove the tags that is a prerelease
# remove the tags that are prerelease
if os.environ.get('UPDATE_PRE_RELEASE', '0') != '1':
print("update pre release is disabled")
stable_tags = [tag for tag in stable_tags if not is_prerelease(tag.split('/')[-1])]
Expand Down
4 changes: 2 additions & 2 deletions servers/helper.py
Original file line number Diff line number Diff line change
Expand Up @@ -41,7 +41,7 @@ async def helper_query(data: Dict):
widget = GPTWidget()
inputs = dict(
model="gpt-4o",
system_prompt="You are a OCR detector, you will always faithfully extract the text in the input image",
system_prompt="You are an OCR detector, you will always faithfully extract the text in the input image",
user_prompt="Please extract the text in the provided image:"
)
for image in images:
Expand Down Expand Up @@ -166,4 +166,4 @@ async def submit_feedback(data: SubmitFeedbackRequest):
return {
"success": True,
"data": submit_data
}
}