Ein Hilfsmodul für die Perplexity API
Project description
README
Overview
The PerplexityAPI class is a Python wrapper for interacting with the Perplexity AI API. It allows users to send chat completion requests to the API and retrieve responses. This class handles the creation of payloads, sending requests, and parsing responses.
Installation
To use the PerplexityAPI class, you need to have the requests library installed. You can install it using pip:
pip install requests
Usage
Initialization
To initialize the PerplexityAPI class, you need to provide your API key:
from perplexity_api import PerplexityAPI
api_key = "your_api_key_here"
api = PerplexityAPI(api_key)
Sending a Request
To send a request to the Perplexity AI API, use the send_request method. You need to specify the model and messages, and you can also provide additional keyword arguments:
model = "your_model_name"
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Tell me a joke."}
]
response = api.send_request(model, messages)
Retrieving the Response
To retrieve the response content from the API, use the get_response method. You can pass the JSON data returned by the send_request method, or it will use the last response stored in the instance:
content = api.get_response(response)
print(content)
Methods
__init__(self, api_key)
Initializes the PerplexityAPI instance with the provided API key.
api_key: Your API key for the Perplexity AI API.
create_payload(self, model, messages, **kwargs)
Creates the payload for the API request.
model: The model name to use for the request.messages: A list of message dictionaries.**kwargs: Additional keyword arguments to include in the payload.
send_request(self, model, messages, **kwargs)
Sends a request to the Perplexity AI API and returns the JSON response.
model: The model name to use for the request.messages: A list of message dictionaries.**kwargs: Additional keyword arguments to include in the payload.
get_response(self, json_data=None)
Retrieves the response content from the JSON data. If no JSON data is provided, it uses the last response stored in the instance.
json_data: The JSON data returned by thesend_requestmethod (optional).
Example
from perplexity_api import PerplexityAPI
api_key = "your_api_key_here"
api = PerplexityAPI(api_key)
model = "your_model_name"
messages = [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Tell me a joke."}
]
response = api.send_request(model, messages)
content = api.get_response(response)
print(content)
This example demonstrates how to initialize the PerplexityAPI class, send a request to the Perplexity AI API, and retrieve the response content.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file pplx-0.1.3.tar.gz.
File metadata
- Download URL: pplx-0.1.3.tar.gz
- Upload date:
- Size: 2.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
9d86d64245688384498682b7bb42ea353fa6a1763b8a7cb81817eb613efd7a73
|
|
| MD5 |
5007fa0ab96bdbe8d351c79fb152cc52
|
|
| BLAKE2b-256 |
4b4809f3f09fcb4792766e0ceb45f2ebf3aee1a08c2a0fb965f81bc1adffbc29
|
File details
Details for the file pplx-0.1.3-py3-none-any.whl.
File metadata
- Download URL: pplx-0.1.3-py3-none-any.whl
- Upload date:
- Size: 3.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.0 CPython/3.10.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
58bd557a4e39930c90da1cd1e68465367550dc41a5f2007c113f93ce52a3350b
|
|
| MD5 |
ca94b96e708422d71b193517907746e0
|
|
| BLAKE2b-256 |
eedc99805d5200004909e043f301d59b3a17142981fb042d3193015abb5fca3e
|