Takeoff Client is a Python client for the Takeoff Server
Project description
Takeoff Python Client Library
Table of Contents
About
The Takeoff Python Client Library serves as an essential tool for interacting with the Takeoff Server. It simplifies the process of sending requests to the server, offering a streamlined, Pythonic interface. This library is designed for developers who need to integrate their Python applications with the Takeoff Server, providing them with a robust and efficient way to communicate with the server's API.
Getting Started
Installing
To get started with the Takeoff Python Client Library, you can install it directly using pip:
pip install takeoff_client
Alternatively, if you are working on developing the library, you can install it in editable mode. This allows you to make changes to the library and test them in real-time. Navigate to the python-client
folder and run the following command:
pip install -e .
Usage
Establishing a Connection
To start using the client, you need to establish a connection with the Takeoff Server. You can do this by creating an instance of the TakeoffClient. Replace "http://localhost" and 3000 with the appropriate URL and port of your Takeoff Server.
client = TakeoffClient(base_url="http://localhost", port=3000)
Interaction with Server
For more details, please check the API documentation below.
Retrieving Reader Information
To get information about the reader from the server, use the get_reader() method. This method sends a request to the server and returns reader-related information.
client.get_reader()
Embedding
For querying the embedding model, use the embed() method.
client.embed("Text to embed")
Generation
To generate text based on a given input, use the generate() method.
client.generate("Text to generate")
Takeoff Python Client API Documentation
To convert the provided method descriptions into API documentation, I'll structure each description to include key components like a brief overview, parameters, return type, and any additional notes or exceptions. Here's how the API documentation can be structured:
Takeoff Python Client API Documentation
1. get_readers()
Overview: Retrieves a list of information about all readers from the Takeoff Server.
Returns:
dict
: A dictionary containing information about all readers.
Example Usage:
reader_info = client.get_readers()
2. embed(text, consumer_group="embed")
Overview: Embeds a batch of text using the specified consumer group.
Parameters:
text
(str | List[str]): The text or list of texts to be embedded.consumer_group
(str, optional): The consumer group to use for embedding. Defaults to "embed".
Returns:
dict
: A dictionary containing the embedding response.
Exceptions:
- Raises an exception if the embedding request fails.
Example Usage:
embedding_response = client.embed("Sample text")
3. generate(text, sampling_temperature=None, sampling_topp=None, sampling_topk=None, repetition_penalty=None, no_repeat_ngram_size=None, max_new_tokens=None, min_new_tokens=None, regex_string=None, json_schema=None, prompt_max_tokens=None, consumer_group="primary")
Overview: Generates text based on the given input and parameters.
Parameters:
text
(str | List[str]): The input text or list of texts for generation.- Additional optional parameters for controlling text generation:
sampling_temperature
(float)sampling_topp
(float)sampling_topk
(int)repetition_penalty
(float)no_repeat_ngram_size
(int)max_new_tokens
(int)min_new_tokens
(int)regex_string
(str)json_schema
(Any)prompt_max_tokens
(int)consumer_group
(str): Defaults to "primary".
Returns:
dict
: A dictionary containing the generated text response.
Exceptions:
- Raises an exception if the text generation request fails.
Example Usage:
generated_text = client.generate("Sample input text")
4. generate_stream(text, sampling_temperature=None, sampling_topp=None, sampling_topk=None, repetition_penalty=None, no_repeat_ngram_size=None, max_new_tokens=None, min_new_tokens=None, regex_string=None, json_schema=None, prompt_max_tokens=None, consumer_group="primary")
Overview:
Similar to generate
, but returns an iterator for streaming the generated text.
Parameters:
- Same as
generate
method.
Returns:
Iterator[Event]
: An iterator that yields a server sent event
Exceptions:
- Raises an exception if the text generation request fails.
Example Usage:
generator = client.generate_stream(["Sample input"])
for event in generator:
print(event.data)
Project details
Release history Release notifications | RSS feed
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
Hashes for takeoff_client-0.2.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 023366befd7299510352e821e4070e2e37f3ad89f0afda2ac679836dc8c8b3ec |
|
MD5 | 9dc2be2409935f382e42a30839b4ed46 |
|
BLAKE2b-256 | 2111c40699a4161ab43c0337c41553c65de02b3d9447e8221eb483b70a2cd61a |