Support run tokens #2105
Draft
Support run tokens #2105
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
"Run tokens" are used to run downstream Replicate models from within a model.
They are not yet exposed in an API, but can be found inside a Cog predictor with some ugly frame inspection:
```python
def _find_api_token() -> str:
frame = inspect.currentframe()
while frame:
if "self" in frame.f_locals:
self = frame.f_locals["self"]
if hasattr(self, "_current_run_token"):
token = self._current_run_token
return token
frame = frame.f_back
raise ValueError("No run token found in call stack")
```
This makes run_token available via current_scope. Example usage:
```python
from cog import current_scope
class MyPredictor:
def predict(self):
token = current_scope().run_token()
if token:
# use token
```
Eventually this should just be a value.
philandstuff
force-pushed
the
run-tokens
branch
from
3cb68d5 to
b06a692
Compare
|
|
||
| def include(model_path: str) -> Callable[..., Any]: | ||
| def run(**inputs: dict[str, Any]) -> Any: | ||
| client = replicate.Client(api_token=_find_api_token()) |
There was a problem hiding this comment.
This can use current_scope().run_token, which is the affordance that exposes the run token to the model. In future, if the prototype is successful, we should make replicate-python automatically detect this and use it if no token was explicitly provided.
Further, I think the whole include function here probably belongs on replicate-python, not in cog?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
"Run tokens" are used to run downstream Replicate models from within a model.
They are not yet exposed in an API, but can be found inside a Cog predictor with some ugly frame inspection: