https://github.com/llm-workflow-engine/lwe-plugin-provider-vertexai
LLM Workflow Engine (LWE) Vertex AI Provider plugin
https://github.com/llm-workflow-engine/lwe-plugin-provider-vertexai
Last synced: 2 months ago
JSON representation
LLM Workflow Engine (LWE) Vertex AI Provider plugin
- Host: GitHub
- URL: https://github.com/llm-workflow-engine/lwe-plugin-provider-vertexai
- Owner: llm-workflow-engine
- Created: 2023-07-26T17:34:54.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2024-01-08T18:58:25.000Z (over 1 year ago)
- Last Synced: 2024-01-08T20:13:38.228Z (over 1 year ago)
- Language: Python
- Size: 2.93 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# LLM Workflow Engine (LWE) Vertex AI Provider plugin
Vertex AI Provider plugin for [LLM Workflow Engine](https://github.com/llm-workflow-engine/llm-workflow-engine)
Access to [Google Vertex AI](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/models) text/code models.
## Installation
You must configure access to the Vertex AI API in Google Cloud by either:
* Having credentials configured for your environment (gcloud, workload identity, etc...)
* Storing the path to a service account JSON file as the `GOOGLE_APPLICATION_CREDENTIALS` environment variable
### From packages
Install the latest version of this software directly from github with pip:
```bash
pip install git+https://github.com/llm-workflow-engine/lwe-plugin-provider-vertexai
```
### From source (recommended for development)
Install the latest version of this software directly from git:
```bash
git clone https://github.com/llm-workflow-engine/lwe-plugin-provider-vertexai.git
```
Install the development package:
```bash
cd lwe-plugin-provider-vertexai
pip install -e .
```
## Configuration
Add the following to `config.yaml` in your profile:
```yaml
plugins:
enabled:
- provider_vertexai
# Any other plugins you want enabled...
```
## Usage
From a running LWE shell:
```
/provider vertexai
/model model_name text-bison
```