Skip to content

Commit 3bf1d75

Browse files
authored
Update Weave info (#1275)
https://wandb.atlassian.net/browse/DOCS-1439 Context: Request from Weave PM to update W&B docs Weave info to help with Weave onboarding Changes - Update https://docs.wandb.ai/guides/weave/ to match https://github.com/wandb/weave/blob/master/docs/docs/introduction.md with some slight modifications - Add callouts on Quickstart to direct folks to Weave docs if they are trying to do the Weave thing
1 parent aee7ee4 commit 3bf1d75

2 files changed

Lines changed: 26 additions & 15 deletions

File tree

content/guides/quickstart.md

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,10 @@ weight: 2
1010
---
1111
Install W&B to track, visualize, and manage machine learning experiments of any size.
1212

13+
{{% alert %}}
14+
Are you looking for information on W&B Weave? See the [Weave Python SDK quickstart](https://weave-docs.wandb.ai/quickstart) or [Weave TypeScript SDK quickstart](https://weave-docs.wandb.ai/reference/generated_typescript_docs/intro-notebook).
15+
{{% /alert %}}
16+
1317
## Sign up and create an API key
1418

1519
To authenticate your machine with W&B, generate an API key from your user profile or at [wandb.ai/authorize](https://wandb.ai/authorize). Copy the API key and store it securely.
@@ -41,6 +45,7 @@ pip install wandb
4145
```
4246
```python
4347
import wandb
48+
4449
wandb.login()
4550
```
4651

@@ -122,3 +127,4 @@ Explore more features of the W&B ecosystem:
122127
4. Automate hyperparameter searches and optimize models with [W&B Sweeps]({{< relref "/guides/models/sweeps/" >}}).
123128
5. Analyze runs, visualize model predictions, and share insights on a [central dashboard]({{< relref "/guides/models/tables/" >}}).
124129
6. Visit [W&B AI Academy](https://wandb.ai/site/courses/) to learn about LLMs, MLOps, and W&B Models through hands-on courses.
130+
7. Visit the [official W&B Weave documentation](https://weave-docs.wandb.ai/) to learn how to track track, experiment with, evaluate, deploy, and improve your LLM-based applications using Weave.

content/guides/weave/_index.md

Lines changed: 20 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -6,24 +6,29 @@ title: W&B Weave
66
weight: 4
77
---
88

9-
{{< cta-button colabLink="http://wandb.me/weave_colab" >}}
9+
{{% alert %}}
10+
Are you looking for the official Weave documentation? Head over to [https://weave-docs.wandb.ai/](https://weave-docs.wandb.ai/).
11+
{{% /alert %}}
1012

11-
Weave is a lightweight toolkit for tracking and evaluating LLM applications. Use W&B Weave to visualize and inspect the execution flow of your LLMs, analyze the inputs and outputs of your LLMs, view the intermediate results and securely store and manage your prompts and LLM chain configurations.
13+
W&B Weave is a framework for tracking, experimenting with, evaluating, deploying, and improving LLM-based applications. Designed for flexibility and scalability, Weave supports every stage of your LLM application development workflow:
1214

13-
{{< img src="/images/weave/weave-hero.png" alt="" >}}
15+
- **Tracing & Monitoring**: Track LLM calls and application logic to debug and analyze production systems.
16+
- **Systematic Iteration**: Refine and iterate on prompts, datasets and models.
17+
- **Experimentation**: Experiment with different models and prompts in the LLM Playground.
18+
- **Evaluation**: Use custom or pre-built scorers alongside our comparison tools to systematically assess and enhance application performance.
19+
- **Guardrails**: Protect your application with safeguards for content moderation, prompt safety, and more.
1420

15-
With W&B Weave, you can:
16-
* Log and debug language model inputs, outputs, and traces
17-
* Build rigorous, apples-to-apples evaluations for language model use cases
18-
* Organize all the information generated across the LLM workflow, from experimentation to evaluations to production
21+
## Get started with Weave
1922

20-
{{% alert %}}
21-
Looking for Weave docs? See the [W&B Weave Docs](https://weave-docs.wandb.ai/).
22-
{{% /alert %}}
23+
Are you new to Weave? Set up and start using Weave with the [Python quickstart](https://weave-docs.wandb.ai/quickstart) or [TypeScript quickstart](https://weave-docs.wandb.ai/reference/generated_typescript_docs/intro-notebook).
24+
25+
## Advanced guides
2326

24-
## How to get started
25-
Depending on your use case, explore the following resources to get started with W&B Weave:
27+
Learn more about advanced topics:
2628

27-
* [Quickstart: Track inputs and outputs of LLM calls](https://wandb.github.io/weave/quickstart)
28-
* [Build an Evaluation pipeline tutorial](https://wandb.github.io/weave/tutorial-eval)
29-
* [Model-Based Evaluation of RAG applications tutorial](https://wandb.github.io/weave/tutorial-rag)
29+
- [Integrations](https://weave-docs.wandb.ai/guides/integrations/): Use Weave with popular LLM providers, local models, frameworks, and third-party services.
30+
- [Cookbooks](https://weave-docs.wandb.ai/reference/gen_notebooks/intro_notebook): Build with Weave using Python and TypeScript. Tutorials are available as interactive notebooks.
31+
- [W&B AI Academy](https://www.wandb.courses/pages/w-b-courses): Build advanced RAG systems, improve LLM prompting, fine-tune LLMs, and more.
32+
- [Weave Python SDK](https://weave-docs.wandb.ai/reference/python-sdk/weave/)
33+
- [Weave TypeScript SDK](https://weave-docs.wandb.ai/reference/typescript-sdk/weave/)
34+
- [Weave Service API](https://weave-docs.wandb.ai/reference/service-api/call-start-call-start-post)

0 commit comments

Comments
 (0)