Workflowai integration docs by yannbu · Pull Request #1 · WorkflowAI/instructor

yannbu · 2025-05-06T15:13:26Z

@pierrevalade @guillaq closes WOR-4550: Prepare MR for Instructor's docs

WDYT ?

Updates compared to our docs are minimal, and are mostly located in the beginning of the docs.

My only question is "is our docs too marketing-oriented ?" if you compare to other docs that are very "dry" and do not try to "sell" the products.

pierrevalade

☑️ reviewed.

pierrevalade · 2025-05-06T16:16:00Z

docs/integrations/workflowai.md

+- **Cloud-based or self-hosted** thanks to our [open-source](https://github.com/WorkflowAI/WorkflowAI/blob/main/LICENSE) licensing model
+- **We value your privacy** and we are SOC-2 Type 1 certified. We do not train models on your data, nor do the LLM providers we use.
+
+Learn more about all WorkflowAI's features in our [docs](https://docs.workflowai.com/).


not sure we want to send developers to the documentation.
the goal of the funnel is to get developers to go to workflowai.com/developers/python/instructor

all other links are basically killing our tracking.

pierrevalade · 2025-05-06T16:16:48Z

docs/integrations/workflowai.md

+
+WorkflowAI is a LLM router, observability and collaboration platform that provides developpers with an extensive toolkit for structured generation.
+
+## Why use WorkflowAI with Instructor?


I think this section is too long, too much links to other place, too much.
the main link that we want developers to go to is: workflowai.com/developers/python/instructor

pierrevalade · 2025-05-06T16:17:20Z

docs/integrations/workflowai.md

+description: "Complete guide to using Instructor with WorkflowAI. Learn how to generate structured, type-safe outputs and leverage WorkflowAI's model-switching, observability & reliability features"
+---
+
+WorkflowAI is a LLM router, observability and collaboration platform that provides developpers with an extensive toolkit for structured generation.


I'll work on that part....

pierrevalade · 2025-05-06T16:18:34Z

docs/integrations/workflowai.md

+    )
+
+    return client.chat.completions.create(
+        model="user-info-extraction-agent/claude-3-7-sonnet-latest", # Agent now runs Claude 3.7 Sonnet


would be a lot better to show more code examples with different model instead.

same feedback apply to the PR on our own documentation.

pierrevalade · 2025-05-06T16:19:36Z

docs/integrations/workflowai.md

+
+WorkflowAI allows you to view all the runs that were made for your agent:
+
+![Run list](</docs/assets/images/runs/list-runs.png>)


can we upload assets?

We can add them to the PR. It looks like they have a bunch of images in docs/img

I really doubt that they will let us commit images to their repo.. (I would definitely not). Can we just upload to our storage and pass a URL?

It looks like integrations doc don't use images

Can we just upload to our storage and pass a URL?

yup, probably the way to go.

pierrevalade · 2025-05-06T16:20:45Z

docs/integrations/workflowai.md

+        messages=[{"role": "user", "content": user_message}],
+    )
+
+if __name__ == "__main__":


no need for that part.
focus on the relevant part that you're highlighting the section.
(adjust as well in a PR for our own documentation)

pierrevalade · 2025-05-06T16:21:26Z

docs/integrations/workflowai.md

+
+## Templating with Input Variables
+
+Introducing input variables separates static instructions from dynamic content, making your agents easier to observe, since WorkflowAI logs these input variables separately. Using input variables also allows to use [benchmarks](https://docs.workflowai.com/features/benchmarks) and [deployments](https://docs.workflowai.com/features/deployments).


re-write this sentence assuming that people don't know what "benchmarks" and "deployments" are, and won't click to know more.

pierrevalade · 2025-05-06T16:22:46Z

docs/integrations/workflowai.md

+    print(f"Classification: {result.kind}") # 'work'
+```
+
+## Using Deployments for Server-Managed Instructions 


can you send this section to a engineer friend of yours @yannbu to check if they do understand this part? thanks.

pierrevalade · 2025-05-06T16:24:11Z

docs/integrations/workflowai.md

+
+## Streaming
+
+We are currently implementing streaming on our OpenAI compatible chat completion endpoint. We'll update this documentation shortly.


@yannbu could you please confirm you have the tests in autopilot setup for streaming + instructor already? thanks.

pierrevalade · 2025-05-06T16:25:47Z

docs/integrations/workflowai.md

+## Streaming
+
+We are currently implementing streaming on our OpenAI compatible chat completion endpoint. We'll update this documentation shortly.
+


include a RECAP section with the main points we want to hit, and a link/CTA on how to get started. I'll review this section, then we will use in all documentations everywhere.

anyacherniss · 2025-05-06T18:07:32Z

docs/integrations/workflowai.md

+    user_info = extract_user_info("John Doe is 32 years old.")
+    print("Basic example result:", user_info)  # UserInfo(name='John Doe', age=32)
+```
+### Supporte Instructor Modes


Typo: "Supporte" (supported?)

guillaq · 2025-05-06T20:55:47Z

docs/integrations/workflowai.md

+
+Then either export your credentials:
+```bash
+export WORKFLOWAI_API_KEY=<your-workflowai-api-key>


That seems unnecessary as well since we are talking to devs ?
Also I don't think the API URL should be configured via an env var since it's a constant ?

We could just say a single sentence like

Set up the base URL of the OpenAI SDK to https://run.workflowai.com/v1 and use a WorflowAI API key in place of the OpenAI api key

?

Maybe we could have something simpler similar to the openai doc ? https://github.com/567-labs/instructor/blob/main/docs/integrations/openai.md

i agree with @guillaq

guillaq · 2025-05-06T20:57:08Z

docs/integrations/workflowai.md

+
+WorkflowAI allows you to view all the runs that were made for your agent:
+
+![Run list](</docs/assets/images/runs/list-runs.png>)


We can add them to the PR. It looks like they have a bunch of images in docs/img

guillaq · 2025-05-06T20:58:47Z

docs/integrations/workflowai.md

+
+WorkflowAI allows you to view all the runs that were made for your agent:
+
+![Run list](</docs/assets/images/runs/list-runs.png>)


I really doubt that they will let us commit images to their repo.. (I would definitely not). Can we just upload to our storage and pass a URL?

It looks like integrations doc don't use images

yannbu added 3 commits May 6, 2025 14:51

WorkflowAI integration docs

4f09ee1

add workflowai docs to mkdocs.yml

7a07203

self contained snippets

8ba377e

yannbu requested review from guillaq and pierrevalade May 6, 2025 15:13

yannbu self-assigned this May 6, 2025

pierrevalade reviewed May 6, 2025

View reviewed changes

anyacherniss reviewed May 6, 2025

View reviewed changes

guillaq reviewed May 6, 2025

View reviewed changes


		WorkflowAI is a LLM router, observability and collaboration platform that provides developpers with an extensive toolkit for structured generation.

		## Why use WorkflowAI with Instructor?


		WorkflowAI allows you to view all the runs that were made for your agent:

		![Run list](</docs/assets/images/runs/list-runs.png>)


		## Templating with Input Variables

		Introducing input variables separates static instructions from dynamic content, making your agents easier to observe, since WorkflowAI logs these input variables separately. Using input variables also allows to use [benchmarks](https://docs.workflowai.com/features/benchmarks) and [deployments](https://docs.workflowai.com/features/deployments).


		## Streaming

		We are currently implementing streaming on our OpenAI compatible chat completion endpoint. We'll update this documentation shortly.

Conversation

yannbu commented May 6, 2025

Uh oh!

pierrevalade left a comment

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants