# Python

## Python Integration

QuickSilver supports seamless integration with the [OpenAI Python client library](https://pypi.org/project/openai/), allowing developers to interact with agents using a familiar interface.

### Installation

```bash
pip install openai
```

### Usage

```python
from openai import OpenAI

# Initialize the client
client = OpenAI(
    api_key="your-api-key",  # Use your Agent ID as the API Key
    base_url="https://api-quicksilver.iotex.ai/v1",  # QuickSilver API endpoint
)

# Prepare Actor input
run_input = {
    "model": "gpt-3.5-turbo",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Tell me about OpenAPI schemas."}
    ],
    "temperature": 0.7
}

# Run the conversation
response = client.chat.completions.create(**run_input)

# Process the response
print(response.choices[0].message.content)
```

### Tips

* Multi-turn conversations are supported by adding more messages to the messages array.
* Fully compatible with OpenAI’s chat.completions interface — just point it to QuickSilver’s API.
* Keep your API key secure. Never expose it in public code or client-side applications.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.iotex.io/quicksilver/developers/sdk-integrations/python.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.