semantic-eq 1.0.5

Python SDK for Semantic Equivalence API - optimize prompts for semantic equivalence

Semantic EQ SDK

This package provides a simple Python client for the Semantic EQ API.

Installation

pip install semantic-eq

Usage

from semantic_eq_sdk import SemanticEQ
import openai

# Initialize SemanticEQ client, compress your system prompt
seq_client = SemanticEQ(api_key="YOUR_SEMANTIC_EQ_API_KEY", system_prompt="<your-input-system-prompt>")

# Compress the original user prompt and system prompt
compressed = seq_client.compress_prompt(user_prompt="Your long and detailed prompt...")

# Call OpenAI's GPT-4 with the compressed prompt
openai.api_key = "YOUR_OPENAI_API_KEY"
response = openai.ChatCompletion.create(
    model="gpt-4o",  # or "gpt-4" if preferred
    messages=[
        {"role": "system", "content": compressed.compressed_system_prompt},
        {"role": "user", "content": compressed.compressed_user_prompt}
    ]
)

# Print the response from GPT-4
print(response["choices"][0]["message"]["content"])

Publishing a New Version (for Maintainers)

Publishing the SDK is handled by a script that automates the entire process.

Prerequisites:

1. PyPI Account: You need an account on PyPI and an API token.
2. Twine Configuration: Your local machine must be configured to authenticate with PyPI. You can do this by setting the TWINE_USERNAME and TWINE_PASSWORD environment variables.

To publish a new version:

1. Navigate to the SDK directory: cd semantic_eq_sdk
2. Run the publishing script. You have two options:
   • To automatically bump the patch version (e.g., 1.0.1 -> 1.0.2), run the script without arguments:

     ./publish_sdk.sh
     

   • To specify an exact version (e.g., for a major release like 2.0.0), provide it as an argument:

     ./publish_sdk.sh 2.0.0
     

3. The script will handle everything else automatically.