Skip to content

Commit 59c0af8

Browse files
committed
Update readme
1 parent ec2baea commit 59c0af8

File tree

1 file changed

+3
-38
lines changed
  • public_dropin_environments/python311_genai_agents

1 file changed

+3
-38
lines changed

public_dropin_environments/python311_genai_agents/README.md

Lines changed: 3 additions & 38 deletions
Original file line numberDiff line numberDiff line change
@@ -6,37 +6,16 @@ workflows using CrewAI, LangGraph, Llama-Index and other agentic workflows.
66
Additionally, this environment is fully compatible with `Codespaces` and `Notebooks` in the DataRobot platform.
77

88
## Supported Libraries
9-
10-
This environment is built for python 3 and has support for the following libraries.
11-
For specific version information and the complete list of included packages, see [requirements](requirements.txt).
12-
13-
- crewai
14-
- langgraph
15-
- langchain
16-
- llama-index
17-
- openai
18-
- numpy
19-
- pandas
9+
For specific version information and the complete list of included packages, see [pyproject.toml](pyproject.toml).
2010

2111
## Instructions
2212

2313
1. From the terminal, run `tar -czvf py_dropin.tar.gz -C /path/to/public_dropin_environments/python311_genai_agents/ .`
24-
2. Using either the API or from the UI create a new Custom Environment with the tarball created
25-
in step 1.
14+
2. Using either the API or from the UI create a new Custom Environment with the tarball created in step 1.
2615

2716
_The Dockerfile.local should be used when customizing the Dockerfile or building locally._
2817

29-
### Creating models for this environment
30-
31-
To use this environment, your custom model archive will typically contain a `custom.py` file containing the necessary hooks, as well as other files needed for your workflow. You can implement the hook functions such as `load_model` and `score_unstructured`, as documented [here](../../custom_model_runner/README.md)
32-
33-
Within your `custom.py` code, by importing the necessary dependencies found in this environment, you can implement your Python code under the related custom hook functions, to build your GenAI workflows.
34-
35-
If you need additional dependencies, you can add those packages in your `requirements.txt` file that you include within your custom model archive and DataRobot will make them available to your custom Python code after you build the environment.
36-
37-
# Development
38-
39-
## Synchronizing `pyproject.toml` and other files with `af-component-agents` [Preferred method]
18+
## [Development] Synchronizing `pyproject.toml` and other files with `af-component-agents` [Preferred method]
4019
From within the `af-component-agents` repo run the following while replacing `path/to/` with the approprite path of your local environment:
4120
```bash
4221
task docker_update_reqs AGENT_PATH=/path/to/datarobot-user-models/public_dropin_environments/python311_genai_agents
@@ -46,17 +25,3 @@ This will:
4625
- Synchronize the `pyproject.toml` to the latest unified requirements
4726
- Upgrade the `uv.lock` file
4827
- Update the `requirements.txt` file so it properly displays in the Execution Environment UI.
49-
50-
## Manually updating requirments.txt for proper display inside DataRobot:
51-
Run the following from within the `python311_genai_agents` directory:
52-
```bash
53-
uv lock
54-
uv sync
55-
uv pip freeze > requirements.txt
56-
```
57-
58-
## Manually updating the `uv.lock` file:
59-
Run the following from within the `python311_genai_agents` directory:
60-
```bash
61-
uv lock --no-upgrade
62-
```

0 commit comments

Comments
 (0)