Skip to main content

Ads for AI applications. Enabling the Freemium model for the AI era.

Project description

Ads4GPTs Langchain Toolkit

This is the LangChain toolkit for Ads4GPTs.

A Python package that integrates Ads4GPTs functionalities into LangChain applications, allowing for seamless retrieval of relevant advertisements based on contextual input.


Table of Contents


Introduction

Ads4GPTs LangChain Integration is a Python package designed to seamlessly incorporate Ads4GPTs functionalities into your LangChain and LangGraph applications. It provides tools and utilities to retrieve contextually relevant advertisements, leveraging the power of LangChain's agentic framework.

Whether you're building a chatbot, a recommendation system, or any application that can benefit from targeted ads, this package offers a robust and production-ready solution.

Show Your Support

If you find our ADS4GPTs project helpful, please give it a star ⭐️

GitHub Stars


Features

  • Easy Integration: Quickly integrate ad retrieval capabilities into your LangChain agents.
  • Contextual Ad Retrieval: Fetch relevant ads based on the provided context to enhance user engagement.
  • Asynchronous Support: Both synchronous and asynchronous operations are supported for flexibility.
  • Robust Error Handling: Comprehensive error handling and logging for reliable production deployments.

Installation

Using pip

You can install the package directly from PyPI:

pip install ads4gpts-langchain

From Source

Alternatively, you can install the package from source:

git clone https://github.com/ADS4GPTs/ads4gpts.git
cd ads4gpts/libs/python-sdk/ads4gpts-langchain
pip install .

Usage

Prerequisites

  • Python 3.11+
  • (Optional) OpenAI Account and API Key
    • In order to use the ads4gpts_agent you
    • Sign up at OpenAI and obtain an API key.
  • Ads4GPTs API Key

Environment Variables

The package requires certain environment variables for API authentication:

  • OPENAI_API_KEY: Your OpenAI API key.
  • ADS4GPTS_API_KEY: Your Ads4GPTs API key.

Set them in your environment:

export OPENAI_API_KEY='your-openai-api-key'
export ADS4GPTS_API_KEY='your-ads4gpts-api-key'

Alternatively, you can pass the API keys directly when initializing classes or set up a .env file.

Initialization

Import the necessary classes and functions in your Python script:

from ads4gpts_langchain import Ads4gptsInlineSponsoredResponsesTool, Ads4gptsSuggestedPromptsTool, Ads4gptsToolkit

Examples

Example 1: Using Ads4GPTsTool Directly

from ads4gpts_langchain import Ads4gptsInlineSponsoredResponsesTool

# Instantiate the tool (API key retrieved from environment variable)
ads_tool = Ads4gptsInlineSponsoredResponsesTool(ads4gpts_api_key="your-ads4gpts-api-key")

# Retrieve ads synchronously
ads = ads_tool._run(
    id="test_id",
    user={"gender": "female", "age_range": "25-34", "persona": "test_persona"},
    ad_recommendation="test_recommendation",
    undesired_ads="test_undesired_ads",
    context="Looking for the latest smartphone deals",
    num_ads=2,
    style="neutral"
)
print(ads)

# Retrieve ads asynchronously
import asyncio

async def fetch_ads():
    ads = await ads_tool._arun(
        id="test_id",
        user={"gender": "female", "age_range": "25-34", "persona": "test_persona"},
        ad_recommendation="test_recommendation",
        undesired_ads="test_undesired_ads",
        context="Best travel packages to Europe",
        num_ads=3,
        style="neutral"
    )
    print(ads)

asyncio.run(fetch_ads())

### Using the Toolkit

from ads4gpts_langchain import Ads4gptsToolkit

# Initialize the toolkit
toolkit = Ads4gptsToolkit(ads4gpts_api_key="your-ads4gpts-api-key")

# Get the list of tools
tools = toolkit.get_tools()

# Use the tool from the toolkit
ads = tools[0]._run(
    id="test_id",
    user={"gender": "female", "age_range": "25-34", "persona": "test_persona"},
    ad_recommendation="test_recommendation",
    undesired_ads="test_undesired_ads",
    context="Healthy recipes and cooking tips",
    num_ads=1,
    style="neutral"
)
print(ads)

Examples for using them in your LangChain and LangGraph application exist in the examples folder of the parent repo.

Contributing

Contributions are welcome! Please follow these steps:

  1. Fork the Repository: Click the "Fork" button at the top right of the repository page.
  2. Clone Your Fork:
git clone git@github.com:ADS4GPTs/ads4gpts.git
  1. Create a Branch:
git checkout -b feature/your-feature-name
  1. Make Changes: Implement your feature or bug fix.
  2. Run Tests: Ensure all tests pass.
pip install pytest pytest-asyncio
python -m unittest discover tests

Formal tests are still under development. 6. Commit Changes:

git commit -am 'Add your commit message here'
  1. Push to Your Fork:
git push origin feature/your-feature-name
  1. Open a Pull Request: Navigate to the original repository and click "New pull request".

License

This project is licensed under the License of the Ads4GPTs repository.

Contact

For issues and feature requests, please use the GitHub issues page.

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

ads4gpts_langchain-0.1.14.tar.gz (49.1 kB view details)

Uploaded Source

Built Distribution

ads4gpts_langchain-0.1.14-py3-none-any.whl (177.0 kB view details)

Uploaded Python 3

File details

Details for the file ads4gpts_langchain-0.1.14.tar.gz.

File metadata

  • Download URL: ads4gpts_langchain-0.1.14.tar.gz
  • Upload date:
  • Size: 49.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for ads4gpts_langchain-0.1.14.tar.gz
Algorithm Hash digest
SHA256 f6c4cb5bcd5e444a6c4b8342b5b644b2ed34256ab5a6ee912fd7f96ad00d2774
MD5 c042ca2886472ab65ab6bac538155adc
BLAKE2b-256 15099ab61478afc148513ba918eaeace7c98e66cc948d6b34abb22f40ab0b742

See more details on using hashes here.

File details

Details for the file ads4gpts_langchain-0.1.14-py3-none-any.whl.

File metadata

File hashes

Hashes for ads4gpts_langchain-0.1.14-py3-none-any.whl
Algorithm Hash digest
SHA256 7e0e65ef4fe51ca01f1f97fb98a0723d49540c2eaf8dd660560b2e381e34e5fd
MD5 c1363c3f452f0225df02df6dc9435011
BLAKE2b-256 81e9fe00e3e7de6ec907dff12b1f8dc55c496d9a1a079cdfbf0d7962ef605ef6

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page