A Python wrapper around TGI and TEI servers
Project description
Py-TXI
Py-TXI is a Python wrapper around Text-Generation-Inference and Text-Embedding-Inference that enables creating and running TGI/TEI instances through the awesome docker-py
in a similar style to Transformers API.
Installation
pip install py-txi
Py-TXI is designed to be used in a similar way to Transformers API. We use docker-py
(instead of a dirty subprocess
solution) so that the containers you run are linked to the main process and are stopped automatically when your code finishes or fails.
Advantages
- Easy to use: Py-TXI is designed to be used in a similar way to Transformers API.
- Automatic cleanup: Py-TXI stops the Docker container when your code finishes or fails.
- Batched inference: Py-TXI supports sending a batch of inputs to the server for inference.
- Automatic port allocation: Py-TXI automatically allocates a free port for the Inference server.
- Configurable: Py-TXI allows you to configure the Inference servers using a simple configuration object.
- Verbose: Py-TXI streams the logs of the underlying Docker container to the main process so you can debug easily.
Usage
Here's an example of how to use it:
from py_txi import TGI, TGIConfig
llm = TGI(config=TGIConfig(model_id="bigscience/bloom-560m", gpus="0"))
output = llm.generate(["Hi, I'm a language model", "I'm fine, how are you?"])
print("LLM:", output)
llm.close()
Output: LLM: [' student. I have a problem with the following code. I have a class that has a method that', '"\n\n"I\'m fine," said the girl, "but I don\'t want to be alone.']
from py_txi import TEI, TEIConfig
embed = TEI(config=TEIConfig(model_id="BAAI/bge-base-en-v1.5"))
output = embed.encode(["Hi, I'm an embedding model", "I'm fine, how are you?"])
print("Embed:", output)
embed.close()
Output: [array([[ 0.01058742, -0.01588806, -0.03487622, ..., -0.01613717, 0.01772875, -0.02237891]], dtype=float32), array([[ 0.02815401, -0.02892136, -0.0536355 , ..., 0.01225784, -0.00241452, -0.02836569]], dtype=float32)]
That's it! Now you can write your Python scripts using the power of TGI and TEI without having to worry about the underlying Docker containers.
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
File details
Details for the file py-txi-0.10.0.tar.gz
.
File metadata
- Download URL: py-txi-0.10.0.tar.gz
- Upload date:
- Size: 11.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.14
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | a0c93bb0998e51207e0ea9204e995a83a11b9a5a1f63ebe073253295e7271c1e |
|
MD5 | 946b918000a81d7cd5d8b7e4e9ad888a |
|
BLAKE2b-256 | 3809555285b5f0e7c1c56048aba4cffe52c743d03074c3208bb3098f57007cda |
File details
Details for the file py_txi-0.10.0-py3-none-any.whl
.
File metadata
- Download URL: py_txi-0.10.0-py3-none-any.whl
- Upload date:
- Size: 12.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.1.1 CPython/3.10.14
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d667f2fb36427e520df9bc14a719428c75438d59f0cf94a3b9027a6984c788c9 |
|
MD5 | ec299986e9346368c0e4a4804ac0a9b8 |
|
BLAKE2b-256 | 158090a9bc5956c95db55b09e83156d8e9a4aa8829ca300640369cd00cd98806 |