41 lines
951 B
Markdown
41 lines
951 B
Markdown
# Developer Guidance: OpenAI-Compatible Embeddings
|
|
|
|
## Overview
|
|
This project uses the OpenAI Python SDK with a compatible base URL to call embeddings.
|
|
|
|
## Example Usage
|
|
```python
|
|
from openai import OpenAI
|
|
|
|
client = OpenAI(
|
|
base_url="https://api.gapgpt.app/v1",
|
|
api_key="YOUR_SECRET_KEY_HERE"
|
|
)
|
|
|
|
response = client.embeddings.create(
|
|
model="text-embedding-3-small",
|
|
input="متن برای تبدیل به بردار"
|
|
)
|
|
|
|
print(response.data[0].embedding[:5])
|
|
```
|
|
|
|
## Secret Key Placeholder
|
|
Replace `YOUR_SECRET_KEY_HERE` with your actual secret key.
|
|
|
|
### Recommended: Use an environment variable
|
|
```python
|
|
import os
|
|
from openai import OpenAI
|
|
|
|
client = OpenAI(
|
|
base_url="https://api.gapgpt.app/v1",
|
|
api_key=os.getenv("OPENAI_API_KEY")
|
|
)
|
|
```
|
|
|
|
## Notes
|
|
- Do **not** commit your secret key to source control.
|
|
- Store secrets in `.env` files or your deployment secret manager.
|
|
- Use the embedding output as needed in your application.
|