Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

fix: fix line numbers because of ruff format #35

Merged
merged 1 commit into from
Dec 17, 2024
Merged

fix: fix line numbers because of ruff format #35

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 21 additions & 21 deletions docs/editor_agents/examples/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,13 +139,13 @@ First, we import dependencies and set up the Project:
Make sure to insert your Project's hash here.

<!--codeinclude-->
[agent.py](../../code_examples/gcp/frame_classification.py) lines:1-14
[agent.py](../../code_examples/gcp/frame_classification.py) lines:1-15
<!--/codeinclude-->

Next, we create a data model and a system prompt based on the Project Ontology that will tell Claude how to structure its response:

<!--codeinclude-->
[agent.py](../../code_examples/gcp/frame_classification.py) lines:17-28
[agent.py](../../code_examples/gcp/frame_classification.py) lines:18-29
<!--/codeinclude-->


Expand Down Expand Up @@ -316,14 +316,14 @@ Next, we create a data model and a system prompt based on the Project Ontology t
We also need an Anthropic API client to communicate with Claude:

<!--codeinclude-->
[agent.py](../../code_examples/gcp/frame_classification.py) lines:31-32
[agent.py](../../code_examples/gcp/frame_classification.py) lines:32-33
<!--/codeinclude-->


Finally, we define our editor agent:

<!--codeinclude-->
[agent.py](../../code_examples/gcp/frame_classification.py) lines:35-66
[agent.py](../../code_examples/gcp/frame_classification.py) lines:36-65
<!--/codeinclude-->

The agent:
Expand Down Expand Up @@ -597,15 +597,15 @@ For this, you will need to have your `<project_hash>` ready.

<!--codeinclude-->

[agent.py](../../code_examples/gcp/object_classification.py) lines:1-13
[agent.py](../../code_examples/gcp/object_classification.py) lines:1-14

<!--/codeinclude-->

Now that we have the project, we can extract the generic ontology object as well as that actual ontology objects that we care about.

<!--codeinclude-->

[agent.py](../../code_examples/gcp/object_classification.py) lines:14-18
[agent.py](../../code_examples/gcp/object_classification.py) lines:15-19

<!--/codeinclude-->

Expand All @@ -621,7 +621,7 @@ is only allowed to choose between the object types that are not of the generic o

<!--codeinclude-->

[agent.py](../../code_examples/gcp/object_classification.py) lines:20-29
[agent.py](../../code_examples/gcp/object_classification.py) lines:22-30

<!--/codeinclude-->

Expand Down Expand Up @@ -905,15 +905,15 @@ With the system prompt ready, we can instantiate an api client for Claude.

<!--codeinclude-->

[agent.py](../../code_examples/gcp/object_classification.py) lines:31-33
[agent.py](../../code_examples/gcp/object_classification.py) lines:33-34

<!--/codeinclude-->

Now, let's define the editor agent.

<!--codeinclude-->

[agent.py](../../code_examples/gcp/object_classification.py) lines:36-45
[agent.py](../../code_examples/gcp/object_classification.py) lines:38-46

<!--/codeinclude-->

Expand All @@ -927,7 +927,7 @@ Notice how the `crop` variable has a convenient `b64_encoding` method to produce

<!--codeinclude-->

[agent.py](../../code_examples/gcp/object_classification.py) lines:46-59
[agent.py](../../code_examples/gcp/object_classification.py) lines:47-60

<!--/codeinclude-->

Expand All @@ -938,15 +938,15 @@ If successful, the old generic object can be removed and the newly classified ob

<!--codeinclude-->

[agent.py](../../code_examples/gcp/object_classification.py) lines:61-81
[agent.py](../../code_examples/gcp/object_classification.py) lines:63-80

<!--/codeinclude-->

Finally, we'll save the labels with Encord.

<!--codeinclude-->

[agent.py](../../code_examples/gcp/object_classification.py) lines:83-85
[agent.py](../../code_examples/gcp/object_classification.py) lines:83-84

<!--/codeinclude-->

Expand Down Expand Up @@ -1047,27 +1047,27 @@ Let us go through the code section by section.
First, we import dependencies and setup the FastAPI app with CORS middleware:

<!--codeinclude-->
[main.py](../../code_examples/fastapi/frame_classification.py) lines:1-22
[main.py](../../code_examples/fastapi/frame_classification.py) lines:1-25
<!--/codeinclude-->

The CORS middleware is crucial as it allows the Encord platform to make requests to your API.

Next, we set up the Project and create a data model based on the Ontology:

<!--codeinclude-->
[main.py](../../code_examples/fastapi/frame_classification.py) lines:24-28
[main.py](../../code_examples/fastapi/frame_classification.py) lines:28-30
<!--/codeinclude-->

We create the system prompt that tells Claude how to structure its response:

<!--codeinclude-->
[main.py](../../code_examples/fastapi/frame_classification.py) lines:30-41
[main.py](../../code_examples/fastapi/frame_classification.py) lines:33-45
<!--/codeinclude-->

Finally, we define the endpoint to handle the classification:

<!--codeinclude-->
[main.py](../../code_examples/fastapi/frame_classification.py) lines:44-71
[main.py](../../code_examples/fastapi/frame_classification.py) lines:48-78
<!--/codeinclude-->

The endpoint:
Expand All @@ -1079,7 +1079,7 @@ The endpoint:
5. Parses Claude's response into classification instances
6. Adds the classifications to the label row and saves it

### Testing the Agent**
### Testing the Agent

**STEP 1: Run the FastAPI Server**
With the agent laid down, we can run it and test it.
Expand Down Expand Up @@ -1155,25 +1155,25 @@ Let's walk through the key components.
First, we setup the FastAPI app and CORS middleware:

<!--codeinclude-->
[main.py](../../code_examples/fastapi/object_classification.py) lines:1-22
[main.py](../../code_examples/fastapi/object_classification.py) lines:1-23
<!--/codeinclude-->

Then we setup the client, Project, and extract the generic Ontology object:

<!--codeinclude-->
[main.py](../../code_examples/fastapi/object_classification.py) lines:24-30
[main.py](../../code_examples/fastapi/object_classification.py) lines:26-32
<!--/codeinclude-->

We create the data model and system prompt for Claude:

<!--codeinclude-->
[main.py](../../code_examples/fastapi/object_classification.py) lines:32-43
[main.py](../../code_examples/fastapi/object_classification.py) lines:34-47
<!--/codeinclude-->

Finally, we define our object classification endpoint:

<!--codeinclude-->
[main.py](../../code_examples/fastapi/object_classification.py) lines:46-84
[main.py](../../code_examples/fastapi/object_classification.py) lines:50-97
<!--/codeinclude-->

The endpoint:
Expand Down
4 changes: 2 additions & 2 deletions docs/task_agents/examples/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -148,7 +148,7 @@ Suppose you have a _fake_ model like this one, which predicts labels, bounding b

<!--codeinclude-->

[Fake model predictions](../../code_examples/tasks/prelabel_videos.py) lines:28-51
[Fake model predictions](../../code_examples/tasks/prelabel_videos.py) lines:29-52

<!--/codeinclude-->

Expand Down Expand Up @@ -176,7 +176,7 @@ Create a pre-labeling agent using the following code as a template:

<!--codeinclude-->

[prelabel_video.py](../../code_examples/tasks/prelabel_videos.py) lines:10-78
[prelabel_video.py](../../code_examples/tasks/prelabel_videos.py) lines:10-77

<!--/codeinclude-->

Expand Down
Loading