https://github.com/explodinggradients/linkedin_ai
https://github.com/explodinggradients/linkedin_ai
Last synced: 10 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/explodinggradients/linkedin_ai
- Owner: explodinggradients
- License: apache-2.0
- Created: 2025-04-17T21:15:19.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2025-05-03T06:38:02.000Z (about 1 year ago)
- Last Synced: 2025-08-18T13:38:39.985Z (10 months ago)
- Language: Jupyter Notebook
- Size: 18.7 MB
- Stars: 1
- Watchers: 1
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# LinkedIn AI:
Build Your Own AI Assistant powered by LinkedIn Content
## 🚀 Getting Started: Installation
```
git@github.com:explodinggradients/linkedin_ai.git
cd linkedin_ai
pip install --pre-release=allow -e . # mlflow is pre-release
```
## Your Hackathon Journey
### Step 1: Explore the Basics
Start by checking out the [example notebook](0_example.ipynb) to understand how the core functionality works. This will introduce you to:
- How to load LinkedIn post data
- How to initialize the AI assistant
- How to ask questions and get responses
### Step 2: Run Your First Experiment
Move on to the [experiment notebook](1_experiment.ipynb) where you'll learn:
- How to set up LLM-based evaluation metrics
- How to run and track experiments systematically
- How to compare different experiments
- Ship the best-performing version of your AI assistant
## Key Features
✅ BM25 Search: Uses the BM25 algorithm for fast keyword-based retrieval
✅ Vector Search: Supports semantic search using embeddings
✅ MLFlow Integration: Built-in experiment tracking and logging