Co-Agent: Multi-Agent Conversational Framework
Co-Agent is a sophisticated Multi-Agent Conversational Framework designed to automate the creation of LinkedIn-ready posts from blog content. Leveraging advanced AI technologies such as Google Gemini for natural language processing and multi-agent systems for task delegation, Co-Agent ensures an engaging, professional, and shareable output tailored for social media.
🌟 Key Features
-
Intelligent Blog Scraping
Extracts meaningful content from blogs using a customizable scraper. -
AI-Driven Summarization
Summarizes blogs into concise LinkedIn posts, maintaining professional tone and format. -
Multi-Agent Collaboration
Deploys a dynamic agent-based system for iterative content refinement, ensuring quality and coherence. -
Cross-Platform Support
Features both a Streamlit-based UI and console-based interface for accessibility and user convenience. -
Plug-and-Play Architecture
Easily integrates with pre-trained LLMs like Google Gemini or other APIs for future scalability. -
Preformatted Outputs
Produces LinkedIn-ready summaries complete with hashtags, headlines, and call-to-action links.
🚀 Quick Start
Installation
Install Co-Agent from PyPI using the following command:
pip install coagent-framework
Usage
Console Workflow
Here’s a step-by-step example for using Co-Agent via the console:
from co_agent import AssistantAgent, UserProxyAgent, llm_config
from co_agent import scraper
# Setting up the Google Gemini LLM API key
llm_config["api_key"] = "Your_Google_API_Key"
# Initializing the scraper
blog_scraper = scraper.BlogScraper(name="blog_scraper")
blog_scraper.scrape()
# Initialize agents (Assistant and User Proxy)
print("Multi-Agent Chat started:")
assistant = AssistantAgent(name="assistant", llm_config=llm_config)
user_proxy = UserProxyAgent(name="user_proxy", assistant=assistant)
# Process blog content for LinkedIn
summary = user_proxy.initiate_postmaking_process("blog_1")
Streamlit UI
To use Co-Agent with an interactive interface, visit the Streamlit app here: 👉 https://co-agent.streamlit.app/
Simply enter the blog URL in the provided field, and the app will guide you through the process of generating a LinkedIn-ready post.
🛠️ How It Works
Core Components
-
Scraper Module
The scraper fetches content from a user-provided blog URL, stripping unnecessary formatting while retaining essential information. -
Multi-Agent System
- AssistantAgent: Responsible for generating initial summaries from blog content.
- UserProxyAgent: Reviews and refines the summary based on user feedback and iterative collaboration.
-
LLM Integration
Google Gemini, or a similar LLM, is used for understanding context, generating concise summaries, and formatting content. -
Database Storage
Approved summaries are stored in a database for later retrieval, ensuring content reusability. -
Formatter
Formats the final summary into a LinkedIn-ready post, including a headline, body, hashtags, and call-to-action links.
📂 Directory Structure
The following is the structure of the project:
coagent_framework/co_agent/
├── agents.py # Multi-agent system implementation
├── scraper.py # Blog scraping functionality
├── database.py # Database utilities
├── config.py # Configuration settings
app.py # main file
pyproject.toml # Poetry configuration for dependencies
README.md # Project documentation
📊 Example Output
Input
Blog URL: Viola-Jones Algorithm Blog
Output
Headline:
Viola-Jones Object Detection: A Revolutionary Leap in Computer Vision
Body:
Remember the early 2000s when real-time object detection felt like science fiction? That all changed thanks to the groundbreaking work of Viola and Jones! Their 2001 algorithm, a marvel of machine learning, used a boosted cascade of simple features (Haar-like features and AdaBoost) to achieve incredibly efficient object detection. This clever approach prioritized relevant features and quickly discarded irrelevant ones, making real-time face detection a reality – a true game-changer!
This algorithm's impact is still felt today. Easily accessible via OpenCV, it continues to serve as a foundational element in many computer vision applications. Want to delve deeper into the magic behind this revolutionary technique?
⚖️ License
This project is licensed under the MIT License. See the LICENSE file on our github for more details.
Metadata
Release files for coagent-framework 0.2.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| coagent_framework-0.2.2.tar.gz | 8.0 kB | Without provenance | Details for coagent_framework-0.2.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| coagent_framework-0.2.2-py3-none-any.whl | Python 3 | none | any | Details for coagent_framework-0.2.2-py3-none-any.whl |
Total release size: 17.7 kB
Release files / coagent_framework-0.2.2.tar.gz
| Download URL | coagent_framework-0.2.2.tar.gz |
|---|---|
| Size | 8.0 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
2b6166fd589e4adde720c5f55ac8302ab0ee3971035ff75476119063eb72333a
|
|
BLAKE2b-256 checksum How to use checksums |
0e1344072e1d114a3f8da57faed98c35fc4dbfde6eed3da8f87766ba81baf461
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.3 CPython/3.12.4 Windows/10
|
Release files / coagent_framework-0.2.2-py3-none-any.whl
| Download URL | coagent_framework-0.2.2-py3-none-any.whl |
|---|---|
| Size | 9.6 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a9bf785c2005644abbaeccfa31813167a0e491477dcfea0af03eb8c0522e2814
|
|
BLAKE2b-256 checksum How to use checksums |
5534c69ee94967bd15776d3f61d31f7a83e1ac93ccdac26e1514ed806482068d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.8.3 CPython/3.12.4 Windows/10
|
Security for coagent-framework 0.2.2
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.