Skip to main content

Semantix GenAI Inference

A python client library to help you interact with the Semantix GenAI Inference API.

Installation

If you're using pip, just install it from the latest release:

$ pip install semantix-genai-inference

Else if you want to run local, clone this repository and install it with poetry:

$ poetry build
$ poetry install

Usage

To use it:

First, make sure you have a valid API key. You can get one at Semantix Gen AI Hub

Set an environment variable with your api secret:

$ export SEMANTIX_API_SECRET=<YOUR_API_SECRET>
$ semantix-ai --help

Configuring with semantix.yaml

Before using the ModelClient, you need to configure the library with a semantix.yaml file. This file should be placed in the same directory where your application is executed. The semantix.yaml file should contain the necessary API keys and other configuration options for the models you want to use.

Here's an example of a semantix.yaml file:

providers:
  semantixHub:
    serverId: "YOUR INFERENCE SERVER ID HERE"
    version: "v0"
    apiSecret: "YOUR SEMANTIX GEN AI HUB API TOKEN"
  cohere:
    apiKey: "YOUR COHERE API KEY"
    generate:
      model: "command"
      version: "v1"

Replace the placeholders with your actual API keys and other configuration options.

Using ModelClient

The ModelClient class allows you to interact with different models. To create a model client, you need to specify the type of model you want to use. The available options are "alpaca", "llama2", and "cohere".

Here's an example of how to create a model client and generate text using the Alpaca model:

from semantix_genai_inference import ModelClient

# Create an Alpaca model client
client = ModelClient.create("alpaca")

# Generate text using the Alpaca model
prompt = "Once upon a time"
generated_text = client.generate(prompt)
print(generated_text)

You can replace "alpaca" with "llama2" or "cohere" to use the Llama2 or Cohere models, respectively.

DEV - Publish to pypi

$ poetry config pypi-token.pypi <YOUR_PYPI_TOKEN>
$ poetry build
$ poetry publish

DEV - Bump version

$ poetry version patch | minor | major | premajor | preminor | prepatch | prerelease

See more at Poetry version command docs

DEV - Commit message semantics

See at Conventional Commits

Metadata

Release files for semantix-genai-inference 0.0.11

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for semantix-genai-inference 0.0.11
File Size Uploaded Provenance Actions
semantix_genai_inference-0.0.11.tar.gz 10.7 kB Without provenance Details for semantix_genai_inference-0.0.11.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for semantix-genai-inference 0.0.11
File Interpreter ABI Platform Actions
semantix_genai_inference-0.0.11-py3-none-any.whl Python 3 none any Details for semantix_genai_inference-0.0.11-py3-none-any.whl

Total release size: 24.9 kB

Release files / semantix_genai_inference-0.0.11.tar.gz

Download URL semantix_genai_inference-0.0.11.tar.gz
Size 10.7 kB
Tags Source
SHA-256 checksum
How to use checksums
b6234eea50f3983e89ea37301e3abf7502123a186b40359dd9f515584aa854cd
BLAKE2b-256 checksum
How to use checksums
841b625f0aca8e5b44229dc01fa20c028652e5dd45af98e27eb53709cb00e0b0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.2.2 CPython/3.10.0 Darwin/21.6.0

Release files / semantix_genai_inference-0.0.11-py3-none-any.whl

Download URL semantix_genai_inference-0.0.11-py3-none-any.whl
Size 14.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
aa04b94541bd8ac9253952a4c2b0e3e67b68f8438a7c83d5432f992f89a5afab
BLAKE2b-256 checksum
How to use checksums
fe123c957f47c8e7e7ffa5bf8da7dc8ee952b0ef38abf1700f8dfcd6502c7cab
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via poetry/1.2.2 CPython/3.10.0 Darwin/21.6.0

Security for semantix-genai-inference 0.0.11

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page