aiconfig — LLM 应用框架中文文档

Getting Started Tutorial

Check out the full Getting Started tutorial.

Install

```bash

for python installation:

pip3 install python-aiconfig

for node.js installation:

npm install aiconfig

setup streaming

inference_options = InferenceOptions(stream=True)

Quickstart

For VS Code Users:

• Install the AIConfig Editor VS Code Extension

If you're not using VS Code, follow these steps:

1. pip3 install python-aiconfig
2. export OPENAI_API_KEY='your-key'
3. aiconfig edit

Use cases

AIConfig makes it easy to work with complex prompt chains, various models, and advanced generative AI workflows. Start with these recipes and access more in /cookbooks:

• RAG with AIConfig
• Function Calling with OpenAI
• CLI Chatbot
• Prompt Routing
• Multi-LLM Consistency
• Safety Guardrails for LLMs - LLama Guard
• Chain-of-Verification

or using poetry: poetry add python-aiconfig

or using yarn: yarn add aiconfig

```

Note: You need to install the python AIConfig package to use AIConfig Editor to create and iterate on prompts even if you plan to use the Node SDK to interact with your aiconfig in your application code.

You must specify your OpenAI API Key. Open your Terminal and add this line, replacing ‘your-api-key-here’ with your API key: export OPENAI_API_KEY='your-api-key-here'.

Use the AIConfig SDK

You can run the prompts from the aiconfig generated from AIConfig Editor in your application code using either python or Node SDK. We’ve shown the python SDK below.

```python

load your AIConfig

from aiconfig import AIConfigRuntime, InferenceOptions import asyncio

config = AIConfigRuntime.load("travel.aiconfig.json")

save the aiconfig to disk and serialize outputs from the model run

config.save('updated_travel.aiconfig.json', include_outputs=True) ```

Edit your AIConfig

You can quickly iterate and edit your aiconfig using AIConfig Editor.

1. Open your Terminal
2. Run this command: aiconfig edit --aiconfig-path=travel.aiconfig.json

A new tab with AIConfig Editor opens in your default browser at http://localhost:8080/ with the prompts, chaining logic, and settings from travel.aiconfig.json. The editor auto-saves every 15 seconds and you can manually save with the Save button. Your updates will be reflected in the AIConfig file.

Contribute to AIConfig

We are rapidly developing AIConfig! We welcome PR contributions and ideas for how to improve the project.

• Join the conversation on Discord - #aiconfig channel
• Open an issue for feature requests
• Read our contributing guide

Supported Models

AIConfig supports the following models out of the box. See examples:

• OpenAI models (GPT-3, GPT-3.5, GPT-4, DALLE3)
• Gemini
• LLaMA
• LLaMA Guard
• Google PaLM models (PaLM chat)
• Hugging Face Text Generation Task models (Ex. Mistral-7B)

If you need to use a model that isn't provided out of the box, you can implement a ModelParser for it. See instructions on how to support a new model in AIConfig.

Open AIConfig Editor in VS Code

AIConfig Editor helps you visually create and edit the prompts and model parameters stored as AIConfigs.

1. Install the AIConfig Editor for VS Code
2. Open the travel.aiconfig.json file in VS Code. This will automatically open the AIConfig Editor in VS Code.