https://github.com/llm-workflow-engine/lwe-plugin-provider-chat-fireworks
LLM Workflow Engine (LWE) Chat Fireworks Provider plugin
https://github.com/llm-workflow-engine/lwe-plugin-provider-chat-fireworks
Last synced: 3 months ago
JSON representation
LLM Workflow Engine (LWE) Chat Fireworks Provider plugin
- Host: GitHub
- URL: https://github.com/llm-workflow-engine/lwe-plugin-provider-chat-fireworks
- Owner: llm-workflow-engine
- Created: 2024-05-03T16:06:29.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-07-07T00:31:33.000Z (almost 2 years ago)
- Last Synced: 2024-12-31T22:41:51.397Z (over 1 year ago)
- Language: Python
- Size: 4.88 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) Chat Fireworks Provider plugin
Chat Fireworks Provider plugin for [LLM Workflow Engine](https://github.com/llm-workflow-engine/llm-workflow-engine)
Access to [Fireworks](https://fireworks.ai/models) chat models.
## Installation
### Export API key
Grab a Fireworks API key from [https://fireworks.ai/api-keys](https://fireworks.ai/api-keys)
Export the key into your local environment:
```bash
export FIREWORKS_API_KEY=
```
### 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-chat-fireworks
```
### 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-chat-fireworks.git
```
Install the development package:
```bash
cd lwe-plugin-provider-chat-fireworks
pip install -e .
```
## Configuration
Add the following to `config.yaml` in your profile:
```yaml
plugins:
enabled:
- provider_chat_fireworks
# Any other plugins you want enabled...
# THIS IS OPTIONAL -- By default the plugin loads all model data via an API
# call on startup. This does make startup time longer.
# You can instead provide a 'models' object here with the relevant data, and
# It will be used instead of an API call.
provider_chat_fireworks:
models:
# 'id' parameter of the model as it appears in the API.
"accounts/fireworks/models/llama-v3-8b-instruct":
# The only parameter, and it's required.
max_tokens: 8192
```
## Usage
From a running LWE shell:
```
/provider fireworks
/model model_name accounts/fireworks/models/llama-v3-8b-instruct
```