You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: public_dropin_environments/python311_genai_agents/README.md
+3-38Lines changed: 3 additions & 38 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -6,37 +6,16 @@ workflows using CrewAI, LangGraph, Llama-Index and other agentic workflows.
6
6
Additionally, this environment is fully compatible with `Codespaces` and `Notebooks` in the DataRobot platform.
7
7
8
8
## 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).
20
10
21
11
## Instructions
22
12
23
13
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.
26
15
27
16
_The Dockerfile.local should be used when customizing the Dockerfile or building locally._
28
17
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]
40
19
From within the `af-component-agents` repo run the following while replacing `path/to/` with the approprite path of your local environment:
0 commit comments