ClearML/clearml-docs
1
0
Fork 0
mirror of https://github.com/clearml/clearml-docs synced 2025-06-26 18:17:44 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Small edits (#820)

Browse Source
This commit is contained in:
pollfly
2024-04-04 10:45:19 +03:00
committed by GitHub
parent 6e20f6ab0e
commit bb056d7b93
7 changed files with 20 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
docs/integrations/langchain.md
View File

@@ -15,7 +15,6 @@ Integrate ClearML with the following steps:
1. Set up the `ClearMLCallbackHandler`. The following code creates a [ClearML Task](../fundamentals/task.md) called
`llm` in the `langchain_callback_demo` project, which captures your script's information, including Git details,
uncommitted code, and python environment:
```python
from langchain.callbacks import ClearMLCallbackHandler
from langchain_openai import OpenAI
@@ -34,14 +33,13 @@ Integrate ClearML with the following steps:
llm = OpenAI(temperature=0, callbacks=[clearml_callback])
```
You can also pass the following parameters to the `ClearMLCallbackHandler` object:
* `task_type` – The type of ClearML task to create (see [task types](../fundamentals/task.md#task-types))
* `tags` – A list of tags to add to the task
* `visualize` - Set to `True` for ClearML to capture the run's Dependencies and Entities plots to the ClearML task
* `complexity_metrics` - Set to `True` to log complexity metrics
* `stream_logs` - Set to `True` to stream callback actions to ClearML Parameters.
1. Use `ClearMLCallbackHandler.flush_tracker()` after each model request to make sure all outputs, including metrics and
You can also pass the following parameters to the `ClearMLCallbackHandler` object:
* `task_type` – The type of ClearML task to create (see [task types](../fundamentals/task.md#task-types))
* `tags` – A list of tags to add to the task
* `visualize` - Set to `True` for ClearML to capture the run's Dependencies and Entities plots to the ClearML task
* `complexity_metrics` - Set to `True` to log complexity metrics
* `stream_logs` - Set to `True` to stream callback actions to ClearML Parameters.
1. Use `ClearMLCallbackHandler.flush_tracker()` after each model request to make sure all outputs, including metrics and
prompts, are logged to ClearML:
```python

12
docs/integrations/tao.md
View File

@@ -77,17 +77,17 @@ logging metrics, model files, plots, debug samples, and more, so you can gain mo
```
clearml_config{
project: "TAO Toolkit ClearML Demo"
task: "detectnet_v2_resnet18_clearml"
tags: "detectnet_v2"
tags: "training"
tags: "resnet18"
tags: "unpruned"
task: "detectnet_v2_resnet18_clearml"
tags: "detectnet_v2"
tags: "training"
tags: "resnet18"
tags: "unpruned"
}
```
This configuration may vary depending on the schema the network follows. For more information, see the [NVIDIA documentation](https://docs.nvidia.com/tao/tao-toolkit/text/mlops/clearml.html#configuring-the-clearml-element-in-the-training-spec).
And that's it! Whenever you train a model using TAO toolkit, a [ClearML Task](../fundamentals/task.md) will be created,
And that's it! Whenever you train a model using TAO Toolkit, a [ClearML Task](../fundamentals/task.md) will be created,
which will capture your model files, training configuration, scalars, debug samples, plots, console output, and more.
You can view all of this captured information in the [ClearML Web UI](../webapp/webapp_exp_track_visual.md).