Object: ChatResponse
Object
system_prompt
question
answer
model
sources
source_documents
total_tokens
prompt_tokens
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
Hey with wandb is it possible to link from the sweep api?
best_run = sweep.best_run()
I have the best run but it isn't clear to me how to link through the api. the UI works fine but trying to get the api working also. I have been reading the docs but missing something.
To link to the best run from a sweep using the Weights & Biases API, you can follow these steps:
1. **Instantiate the W&B API**: First, you need to instantiate the W&B API to interact with your sweeps and runs.
```python
import wandb
api = wandb.Api()
```
2. **Get the Sweep Object**: Use the `api.sweep` method to get the sweep object. You need to provide the path to the sweep in the format `"<entity>/<project>/<sweep_id>"`.
```python
sweep = api.sweep("entity/project/...
gpt-4-0125-preview
https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDQ0OTIy
https://docs.wandb.ai/guides/launch/sweeps-on-launch
https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDMyMzkx
https://docs.wandb.ai/guides/sweeps/faq
https://github.com/wandb/examples/tree/master/colabs/pytorch-lightning/Fine_tuning_a_Transformer_with_Pytorch_Lightning.ipynb
https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDUzMTM5
https://wandb.ai/wandb/wandb_spacy_sweeps/reports/--Vmlldzo5NDA2MjE=
https://wandb.ai/wandb_fc/...
source: https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDQ0OTIy
source_type: report
has_code: True
```
sweep_id = wandb.sweep(sweep_config)
```
When you run this, you should get a link to the sweep which you can view in the browser and use to track your sweep runs.
Once you have initialized the sweep you need an agent. An agent is a model training script you can use to pair the sweep configurations. Let’s define a simple training script:
```
def train():
# Initialize wandb with a sa...
9,974
9,084
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
Hey I have a question about using wandb with fastapi in a prod environment. is it recommended to initialize wandb within a specific route function, ie
`.route('/')
def my_function():
wandb.init(...)
`
or should i initialize beforehand:
`wandb.init(...)
.route('/')
def my_function():
...`
I'm getting a long list of log items in the console and many of them are empty.
Integrating Weights & Biases (`wandb`) with FastAPI in a production environment requires careful consideration of how and where to initialize `wandb` to ensure efficient logging and minimal performance impact. Here are some best practices and recommendations:
### Best Practices for Integrating `wandb` with FastAPI
1. **Initialize `wandb` Outside Route Functions**: It's generally recommended to initialize `wandb` outside of specific route functions. This approach ensures that `wandb.init()` is ...
gpt-4-0125-preview
https://docs.wandb.ai/guides/integrations/fastai/v1
https://docs.wandb.ai/guides/integrations/dagster
https://github.com/wandb/examples/tree/master/examples/fastai/fastai-v1-examples/fastai1-simpsons/train.py
https://wandb.ai/borisd13/demo_config/reports/--Vmlldzo4MzAyNA==
https://docs.wandb.ai/guides/integrations/fastai/
https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDY0Nzc3
https://github.com/wandb/wandb/tree/main/wandb/integration/fastai/__init__.py
https://github.com/wandb/wandb/tree/...
source: https://docs.wandb.ai/guides/integrations/fastai/v1
source_type: documentation
has_code: True
---
:::note
This documentation is for fastai v1.
If you use the current version of fastai, you should refer to fastai page.
:::
For scripts using fastai v1, we have a callback that can automatically log model topology, losses, metrics, weights, gradients, sample predictions and best trained model.
```
import wandb
from wandb.fastai import WandbCallback
wandb.init()
learn = cnn\_learner(d...
9,247
8,356
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
Hey I have a question about using wandb with fastapi in a prod environment. is it recommended to initialize wandb within a specific route function, ie
`.route('/')
def my_function():
wandb.init(...)
`
or should i initialize beforehand:
`wandb.init(...)
.route('/')
def my_function():
...`
I'm getting a long list of log items in the console and many of them are empty.
When integrating Weights & Biases (`wandb`) with FastAPI, especially in a production environment, it's important to consider the lifecycle of your FastAPI application and how `wandb` runs interact with it. Here are some best practices and considerations:
### Best Practices for Initializing `wandb` with FastAPI
1. **Initialize `wandb` within Specific Route Functions**: It's generally recommended to initialize `wandb` within specific route functions where you need to log data or start a new run....
gpt-4-0125-preview
https://docs.wandb.ai/guides/integrations/dagster
https://github.com/wandb/examples/tree/master/examples/fastai/fastai-v1-examples/fastai1-simpsons/train.py
https://wandb.ai/borisd13/demo_config/reports/--Vmlldzo4MzAyNA==
https://docs.wandb.ai/guides/integrations/fastai/
https://github.com/wandb/examples/tree/master/examples/fastai/basics/tabular.py
https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDY0Nzc3
https://github.com/wandb/wandb/tree/main/wandb/integration/fastai/__init__.py
https://...
source: https://docs.wandb.ai/guides/integrations/dagster
source_type: documentation
has_code: True
1. Log in to W&B. Note: if you are using W&B Server ask your admin for the instance host name.
2. Collect your API key by navigating to the authorize page or in your user/team settings. For a production environment we recommend using a service account to own that key.
3. Set an environment variable for that API key export `WANDB_API_KEY=YOUR_KEY`.
The proceeding examples demonstrate where to sp...
9,032
8,120
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
Could you provide more details or context about your query? It's unclear what specific issue or question you have regarding Weights & Biases.
Could you provide more details or context about your query? It's unclear what specific issue or question you have regarding Weights & Biases.
gpt-4-0125-preview
https://github.com/wandb/examples/tree/master/colabs/intro/3_in_1_Intro_to_Weights_&_Biases_CV,_NLP_and_RL.ipynb
https://wandb.ai/diganta/ECANet-sweep/reports/--Vmlldzo0MDk1MTc=
https://wandb.ai/giskard/product_description/reports/--Vmlldzo1ODIzNDUz
https://wandb.ai/wandb_fc/tips/reports/--VmlldzoxNjcwOTg1
https://wandb.ai/andrea0/writing/reports/--VmlldzozMDE4OTYz
https://github.com/wandb/examples/tree/master/colabs/scikit/Simple_Scikit_Integration.ipynb
https://github.com/wandb/edu/tree/main/e...
source: https://github.com/wandb/examples/tree/master/colabs/intro/3_in_1_Intro_to_Weights_&_Biases_CV,_NLP_and_RL.ipynb
source_type: notebook
has_code: False
Weights & Biases is a developer toolkit for machine learning experiment tracking, dataset and model versioning, and collaboration
In this mega 3-in-1 notebook you'll see how Weights and Biases seamlessly integrates into ML code across modalities -- one example each from Computer Vision, NLP and Reinforcement Learning -- as well as acros...
8,899
8,682
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
Can you provide more details or context to enhance your query regarding Weights & Biases?
It seems like you're interested in learning more about Weights & Biases (W&B), but your query lacks specific details. Could you please provide more information or clarify what aspect of W&B you're interested in? For example, are you looking for information on how to get started, specific features like experiment tracking, dataset versioning, model management, or integrations with machine learning frameworks? Let me know so I can provide you with the most relevant information.
gpt-4-0125-preview
https://wandb.ai/diganta/ECANet-sweep/reports/--Vmlldzo0MDk1MTc=
https://github.com/wandb/examples/tree/master/colabs/intro/3_in_1_Intro_to_Weights_&_Biases_CV,_NLP_and_RL.ipynb
https://wandb.ai/giskard/product_description/reports/--Vmlldzo1ODIzNDUz
https://wandb.ai/wandb_fc/tips/reports/--VmlldzoxNjcwOTg1
https://wandb.ai/wandb_fc/partners/reports/--VmlldzoyMzQyMTE1
https://wandb.ai/andrea0/writing/reports/--VmlldzozMDE4OTYz
https://github.com/wandb/edu/tree/main/edu_resources/README.md
https:/...
source: https://wandb.ai/diganta/ECANet-sweep/reports/--Vmlldzo0MDk1MTc=
source_type: report
has_code: False
Weights & Biases is a collection of tools that make research more transparent and engaging. The power of logging literally anything and everything at the expense of a few lines of code is probably one of the most powerful weapon a researcher can wield.
Some of the more advanced features that could be useful for more researchers include:
* : Probably my favourite out of the lot, Artif...
9,094
8,804
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
How can weights & biases help when building llm-powered apps?
Weights & Biases (W&B) offers a suite of tools and features that can significantly enhance the development of LLM-powered applications. Here's how W&B can assist in this process:
1. **W&B Prompts**: This is a set of LLMOps tools designed specifically for the development of LLM-powered applications. W&B Prompts allow you to visualize and inspect the execution flow of your LLMs, analyze the inputs and outputs, view intermediate results, and securely store and manage your prompts and LLM chain con...
gpt-4-0125-preview
https://wandb.ai/rmitson/30-days-of-llms/reports/--Vmlldzo2MjA0NDc2
https://docs.wandb.ai/guides/prompts
https://wandb.ai/rmitson/30-days-of-llms/reports/--Vmlldzo2Mjg5NjIy
https://wandb.ai/rmitson/30-days-of-llms/reports/--Vmlldzo2MjA0NDI2
https://wandb.ai/rmitson/30-days-of-llms/reports/--Vmlldzo2MjA0MTM2
https://wandb.ai/rmitson/30-days-of-llms/reports/--Vmlldzo2MjAzMTA4
https://wandb.ai/rmitson/30-days-of-llms/reports/--Vmlldzo2MjMwMTM0
https://wandb.ai/rmitson/30-days-of-llms/reports/--Vmll...
source: https://wandb.ai/rmitson/30-days-of-llms/reports/--Vmlldzo2MjA0NDc2
source_type: report
has_code: False
* No deep machine learning knowledge is needed, just some familiarity with Python programming.
* Strategies for continual enhancement of your LLM applications.
* Unique perspectives on the LLM tools used by Weights & Biases.
Embark on this educational adventure to excel in crafting LLM-powered applications. [Sign up now.](http://wandb.me/building-llm-powered-apps)
Don't miss our nex...
8,375
6,977
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
please show me how to log training output_name model of the current training run
To log the output name of a model during a current training run in Weights & Biases, you can use the `log_model` method. This method allows you to declare a model artifact as an output of a run, enabling you to track the model along with its metadata, such as the name, description, and any other relevant information. Here's how you can do it:
1. **Initialize your W&B run**: Start by initializing a run in your training script. This will start tracking your training process.
```python
im...
gpt-4-0125-preview
https://github.com/wandb/wandb/tree/main/wandb/beta/workflows.py
https://github.com/wandb/examples/tree/master/colabs/simpletransformers/SimpleTransformersQA.ipynb
https://wandb.ai/vincenttu/finetuning_zephyr7b/reports/--Vmlldzo1ODc0MTcx
https://wandb.ai/stacey/nlg/reports/--Vmlldzo1NzcwNzY=
https://docs.wandb.ai/guides/track/log/log-models
https://github.com/wandb/examples/tree/master/colabs/pytorch-lightning/Optimize_Pytorch_Lightning_models_with_Weights_&_Biases.ipynb
https://github.com/wandb...
source: https://github.com/wandb/wandb/tree/main/wandb/beta/workflows.py
source_type: code
has_code: True
def log_model(
model_obj: Any,
name: str = "model",
aliases: Optional[Union[str, List[str]]] = None,
description: Optional[str] = None,
metadata: Optional[dict] = None,
project: Optional[str] = None,
scope_project: Optional[bool] = None,
**kwargs: Dict[str, Any],
) -> "_SavedModel":
"""Log a model object to enable model-centric workflows in the UI.
S...
8,750
8,072
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
What are some great resources for me to better understand Weights & Biases usage for Deep Learning?
There are several resources available to help you understand and effectively use Weights & Biases (W&B) for Deep Learning. Here's a curated list of official and community-recommended resources:
### Official Weights & Biases Learning Resources
1. **Introduction to using Weights and Biases** – A video and slide deck providing an introductory overview of W&B. This is a great starting point to understand the platform's capabilities.
- [Video](https://www.youtube.com/watch?v=Se1HvbAM0O4)
- [S...
gpt-4-0125-preview
https://github.com/wandb/edu/tree/main/edu_resources/README.md
https://wandb.ai/wandb_fc/tips/reports/--VmlldzoxNjcwOTg1
https://wandb.ai/ayush-thakur/dl-question-bank/reports/--VmlldzoyMDIzOTM=
https://wandb.ai/justintenuto/bag-of-words/reports/--VmlldzoxOTQ3OTUx
https://github.com/wandb/edu/tree/main/edu_resources/README.md
https://github.com/wandb/examples/tree/master/colabs/intro/3_in_1_Intro_to_Weights_&_Biases_CV,_NLP_and_RL.ipynb
https://wandb.ai/wandb_fc/articles/reports/--Vmlldzo1NDc2Mj...
source: https://github.com/wandb/edu/tree/main/edu_resources/README.md
source_type: markdown
has_code: False
Below are some resources that you can make use of as a student, student instructor (TA, GSI), or educator.
We've included introductory content to help get you and your students started using *Weights & Biases* to enable collaborative, repeatable machine and deep learning in your classroom, research lab, or student-run organization.
The resources below are targeted at educators or inst...
9,101
8,146
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
does weights and balances have an integration with LangChain?
Yes, Weights & Biases (W&B) has an integration with LangChain, a framework for developing applications powered by language models. This integration facilitates the development and tracking of Large Language Model (LLM) applications, allowing users to visualize and inspect the execution flow of LLMs, analyze inputs and outputs, view intermediate results, and manage prompts and LLM agent configurations securely.
**How to integrate LangChain with Weights & Biases:**
1. **Install the necessary pac...
gpt-4-0125-preview
https://wandb.ai/a-sh0ts/wandb_prompts_snowflake_demo/reports/--Vmlldzo0ODI2MzA5
https://docs.wandb.ai/guides/integrations/langchain
https://wandb.ai/a-sh0ts/langchain_callback_demo/reports/--VmlldzozNjk1NTUw
https://github.com/wandb/examples/tree/master/colabs/prompts/W&B_Prompts_with_Custom_Columns.ipynb
https://docs.wandb.ai/ref/js/
https://kleiber.me/blog/2023/05/14/tracking-inspecting-prompts-langchain-agents-weights-and-biases/
https://docs.wandb.ai/guides/prompts/quickstart
https://wandb....
source: https://wandb.ai/a-sh0ts/wandb_prompts_snowflake_demo/reports/--Vmlldzo0ODI2MzA5
source_type: report
has_code: True
'
Description: Learn how our new integration with Snowflake works, complete with interactive code, a demo video, and a whole lot more
Body:
In the rapidly evolving landscape of machine learning and data science, innovative tools and frameworks are constantly surfacing to optimize workflow. Weights & Biases is excited to announce has now integrated with Snowpark Contain...
8,702
7,709
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
is there an example of how to use Launch on Sagemaker using BYOI (Bring your own image)?
To use Weights & Biases (W&B) Launch on Amazon SageMaker with your own image (BYOI), you need to follow a process that involves preparing your Docker image to be compatible with SageMaker, pushing it to Amazon Elastic Container Registry (ECR), and then configuring W&B Launch to use this image for your training jobs. Here's a step-by-step guide based on the provided documentation:
1. **Prepare Your Docker Image**: Ensure your Docker image is SageMaker compatible. This means it must meet SageMake...
gpt-4-0125-preview
https://docs.wandb.ai/guides/launch/sagemaker
https://docs.wandb.ai/guides/launch/setup-launch-sagemaker
https://docs.wandb.ai/guides/launch/launch-faqs
https://docs.wandb.ai/guides/launch/setup-launch-sagemaker
https://docs.wandb.ai/guides/launch/setup-launch-sagemaker
https://github.com/wandb/wandb/tree/main/wandb/sdk/launch/runner/sagemaker_runner.py
https://github.com/wandb/wandb/tree/main/wandb/sdk/launch/runner/sagemaker_runner.py
https://github.com/wandb/edu/tree/main/llm-apps-course/docs...
source: https://docs.wandb.ai/guides/launch/sagemaker
source_type: web_search
has_code: None
Title: Launch on SageMaker | Weights & Biases Documentation
Description: <strong>Use</strong> <strong>W</strong>&<strong>B</strong> <strong>Launch</strong> <strong>to</strong> send your runs to AWS <strong>SageMaker</strong>. <strong>There</strong> are two ways <strong>to</strong> <strong>use</strong> <strong>Launch</strong> <strong>on</strong> <strong>SageMaker</strong>:
Bring your own image (BYOI)...
8,739
7,939
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
Can multiple users write to the same stream table?
Yes, multiple users can write to the same StreamTable in Weights & Biases. The server uses a queue to order any concurrent messages, supporting multiple or parallel processes writing to the same StreamTable. This functionality is particularly useful for collaborative projects or environments where data from different sources need to be aggregated in real-time.
Here's how Weights & Biases handles concurrent writes to a StreamTable:
- **Concurrent Writing**: Multiple processes or users can log da...
gpt-4-0125-preview
https://github.com/wandb/weave/tree/master/examples/experimental/ProductionMonitoring/stream_table_api.ipynb
https://docs.wandb.ai/guides/weave/prod-mon
https://docs.wandb.ai/guides/weave/prod-mon
https://github.com/wandb/weave/tree/master/weave/engine_trace.py
https://github.com/wandb/weave/tree/master/examples/experimental/ProductionMonitoring/ProductionMonitoringConceptualOverview.ipynb
https://docs.wandb.ai/guides/weave/streamtable
https://github.com/wandb/weave/tree/master/examples/experime...
source: https://github.com/wandb/weave/tree/master/examples/experimental/ProductionMonitoring/stream_table_api.ipynb
source_type: notebook
has_code: True
# show the StreamTable
st
```
All log calls on a given StreamTable instance will append the given rows to that instance.
In a notebook, the StreamTable variable on a line by itself will return a Weave Panel view of the StreamTable. The StreamTable will contain all the logged columns and their values, as well as a `timestamp` column indica...
8,952
8,315
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
Can I get an enlarged/focused view for charts?
Yes, you can get an enlarged or focused view for charts in Weights & Biases to better visualize specific areas of interest. This can be particularly useful when you want to closely examine the data or focus on a particular region of a plot. Here are some ways to achieve this:
1. **Zoom and Pan**: Weights & Biases charts support smooth pan and zoom interactions. You can click and drag on the plots to pan around or use scrolling to zoom in and out. This feature allows you to focus on the most rel...
gpt-4-0125-preview
https://wandb.ai/stacey/sfmlearner/reports/--Vmlldzo2Nzg2Nw==
https://wandb.ai/wandb_fc/tips/reports/--VmlldzoxNjcwOTg1
https://docs.wandb.ai/guides/app/pages/project-page
https://wandb.ai/wandb/posts/reports/--VmlldzoyNjk3Nzg=
https://github.com/wandb/examples/tree/master/colabs/intro/Report_API_Quickstart.ipynb
https://docs.wandb.ai/guides/app/features/custom-charts/
https://docs.wandb.ai/guides/app/pages/workspaces
https://wandb.ai/andrea0/writing/reports/--VmlldzozMDE4OTk2
https://wandb.ai/w...
source: https://wandb.ai/stacey/sfmlearner/reports/--Vmlldzo2Nzg2Nw==
source_type: report
has_code: False
* Charts are zoomed into the most relevant regions. For example, the bottom left "smooth_loss" zooms in on the first 400 steps and shows that setting smooth_weight around 0.5 results in less stable initial training with a spike around step 100.
* The view synthesis objective chart shows all the pixel_losses smoothed, sorted, and added to each other instead of plotting them on top of each ot...
9,273
8,522
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
how can I get the path to where an artifact is being written?
To get the path to where an artifact is being written in Weights & Biases, you can use the `path` method provided in the Weights & Biases API. This method is part of the artifact handling functionality and allows you to retrieve the storage location of an artifact.
Here's a basic example of how you might use this in a Python script:
```python
import wandb
# Initialize a W&B run
run = wandb.init()
# Assuming you have an artifact named 'my_artifact'
artifact = run.use_artifact('entity/project...
gpt-4-0125-preview
https://github.com/wandb/weave/tree/master/weave/artifact_local.py
https://github.com/wandb/wandb/tree/main/wandb/sdk/verify/verify.py
https://github.com/wandb/wandb/tree/main/wandb/sdk/data_types/saved_model.py
https://docs.wandb.ai/guides/artifacts/track-external-files
https://github.com/wandb/wandb/tree/main/tests/pytest_tests/system_tests/test_artifacts/test_artifact_cli.py
https://github.com/wandb/wandb/tree/main/wandb/sdk/artifacts/storage_handlers/gcs_handler.py
https://github.com/wandb/w...
source: https://github.com/wandb/weave/tree/master/weave/artifact_local.py
source_type: code
has_code: True
def _get_write_path(self, path: str) -> pathlib.Path:
write_dirname = pathlib.Path(self._write_dirname)
full_path = write_dirname / path
if (
not pathlib.Path(full_path)
.resolve()
.is_relative_to(write_dirname.resolve())
):
raise errors.WeaveAccessDeniedError()
return full_path
def direct_url(sel...
7,890
7,269
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
I am logging some metrics using wandb.log method and I have runs grouped by Group. Within that group each run has the metrics logged. While analyzing the runs in the table format on the UI previously before some days it would show average metric of the runs within the group next to the group name, but it's showing basically nothing now. Has anything changed in wandb ?
It seems like you're encountering an issue with the display of average metrics for grouped runs in the W&B UI. While the provided context doesn't specifically address recent changes to the W&B UI or the display of average metrics for grouped runs, I can offer some general advice on troubleshooting and what steps you might consider taking next.
1. **Check for UI Updates or Changes**: W&B frequently updates its platform to introduce new features or improve existing ones. It's possible that a rece...
gpt-4-0125-preview
https://github.com/wandb/wandb/tree/main/wandb/sdk/wandb_run.py
https://docs.wandb.ai/guides/track/log/logging-faqs
https://github.com/wandb/wandb/tree/main/wandb/sdk/wandb_run.py
https://docs.wandb.ai/guides/track/log/logging-faqs
https://docs.wandb.ai/ref/python/run
https://docs.wandb.ai/guides/integrations/add-wandb-to-any-library
https://docs.wandb.ai/guides/track/limits
https://docs.wandb.ai/guides/integrations/add-wandb-to-any-library
https://docs.wandb.ai/guides/track/log/customize-loggin...
source: https://github.com/wandb/wandb/tree/main/wandb/sdk/wandb_run.py
source_type: code
has_code: True
wandb keeps track of a global step, which by default increments with each
call to `wandb.log`, so logging related metrics together is encouraged.
If it's inconvenient to log related metrics together
calling `wandb.log({"train-loss": 0.5}, commit=False)` and then
`wandb.log({"accuracy": 0.9})` is equivalent to calling
`wandb.log({"train-loss": 0.5, "acc...
8,998
8,160
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
what are best practices for logging artifacts that optimally wont consume all of my storage.
To log artifacts in Weights & Biases without consuming excessive storage, you can follow these best practices:
1. **Use Reference Artifacts**: Instead of uploading large datasets or model files directly to W&B, you can use reference artifacts to track files saved outside the W&B system. This method involves logging a reference (usually a URI) to the data stored in an external cloud storage bucket or another accessible location. This way, you only store metadata about the files in W&B, significa...
gpt-4-0125-preview
https://docs.wandb.ai/guides/app/features/storage
https://wandb.ai/stacey/cshanty/reports/--Vmlldzo4NDI3NzM=
https://docs.wandb.ai/guides/app/features/storage
https://github.com/wandb/weave/tree/master/weave/wandb_interface/wandb_lite_run.py
https://wandb.ai/broutonlab/first_steps/reports/--Vmlldzo2NjE3MDI=
https://docs.wandb.ai/guides/artifacts/data-privacy-and-compliance
https://wandb.ai/andrea0/azure-2023/reports/--Vmlldzo0NDA2NDgw
https://docs.wandb.ai/guides/artifacts/artifacts-faqs
https:/...
source: https://docs.wandb.ai/guides/app/features/storage
source_type: documentation
has_code: False
If you are approaching or exceeding your storage limit, there are multiple paths forward to manage your data. The path that's best for you will depend on your account type and your current project setup.
W&B offers different methods of optimizing your storage consumption:
* Use reference artifacts to track files saved outside the W&B system, instead of uploading them to W&B storage.
* Use an ...
8,485
7,652
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
In the Runs view / Workspace, what button do we push to hide the sidebar with the list of all the run names?
To hide the sidebar with the list of all the run names in the Runs view or Workspace of Weights & Biases, you can use the **Expand button**. This button allows you to toggle the visibility of the sidebar, effectively hiding or showing it as needed. The Expand button serves as a way to manage UI elements within the Workspace, providing more space for viewing graphs or other data by collapsing the sidebar when it's not needed.
Here's a brief guide on managing the sidebar visibility:
- Look for t...
gpt-4-0125-preview
https://docs.wandb.ai/guides/runs/
https://docs.wandb.ai/guides/app/features/runs-table
https://docs.wandb.ai/guides/app/features/runs-table
https://docs.wandb.ai/guides/app/pages/project-page
https://docs.wandb.ai/guides/runs/grouping
https://docs.wandb.ai/guides/app/pages/project-page
https://wandb.ai/stacey/xtable/reports/--Vmlldzo4MTc0MTA=
https://github.com/wandb/edu/tree/main/llm-apps-course/docs_sample/tags.md
https://github.com/wandb/examples/tree/master/examples/streamlit/wandb_streamli...
source: https://docs.wandb.ai/guides/runs/
source_type: documentation
has_code: False
View Runs associated to a project with the W&B App UI. Navigate to the W&B App and search for the name of your project.
In the following example we search for a project called "my-first-run":
Select the project. This will redirect you to that project's Workspace. A Project's Workspace gives you a personal sandbox to compare runs. Use projects to organize models that can be compared, working on the same pro...
8,425
7,902
System: You are Wandbot - a support expert in Weights & Biases, wandb and weave.
Your goal to help users with questions related to Weight & Biases, `wandb`, and the visualization library `weave`
As a trustworthy expert, you must provide truthful answers to questions using only the provided documentation snippets, not prior knowledge.
Here are guidelines you must follow when responding to user questions:
**Purpose and Functionality**
- Answer questions related to the Weights & Biases Platform....
I keep getting `Error in callback <bound method _WandbInit._pause_backend of <wandb.sdk.wandb_init._WandbInit object at 0x7fcee805af50>>`
```TypeError Traceback (most recent call last)
TypeError: _WandbInit._pause_backend() takes 1 positional argument but 2 were given
```
when calling `wandb.init()`. It was working ok earlier. I get this with versions 0.15.12 and 0.15.10.
How can I resolve this?
The error you're encountering, `TypeError: _WandbInit._pause_backend() takes 1 positional argument but 2 were given`, suggests that there's a mismatch between the method definition and how it's being called, which is likely due to an internal issue within the `wandb` library itself. This could be related to changes or regressions in the specific versions of `wandb` you mentioned (0.15.12 and 0.15.10).
Here are some steps you can take to resolve this issue:
1. **Update to the Latest Version**: ...
gpt-4-0125-preview
https://docs.wandb.ai/guides/technical-faq/general
https://docs.wandb.ai/guides/integrations/keras
https://github.com/wandb/wandb/tree/main/wandb/integration/keras/callbacks/tables_builder.py
https://docs.wandb.ai/ref/python/integrations/keras/
https://pypi.org/project/wandb/
https://github.com/wandb/wandb/tree/main/tests/pytest_tests/unit_tests_old/assets/fixtures/train.py
https://github.com/wandb/wandb/tree/main/wandb/sdk/artifacts/artifact.py
https://github.com/wandb/wandb/tree/main/wandb/__i...
source: https://docs.wandb.ai/guides/technical-faq/general
source_type: web_search
has_code: None
Title: General - Weights & Biases Documentation - Wandb
Description: When <strong>wandb</strong>.<strong>init</strong>() is called from your training script an API call is made to create a run object on our servers. A new process is started to stream and collect metrics, thereby <strong>keeping</strong> all threads and logic out of your primary process. Your script runs normally and writes to local...
8,501
7,491
Total Rows: 398