|
1 | 1 | # LinkedIn AI: |
2 | 2 | Build Your Own AI Assistant powered by LinkedIn Content |
3 | 3 |
|
4 | | -This hackathon repository provides you with the foundation to build an AI assistant that can answer questions based on LinkedIn content. The system uses RAG (Retrieval-Augmented Generation) to provide responses that matchs knowledge of the content author. |
5 | | - |
6 | 4 | ## 🚀 Getting Started: Installation |
7 | 5 |
|
8 | | -### Option 1: Install directly from GitHub |
9 | | - |
10 | 6 | ``` |
11 | | -bashpip install git+https://github.com/shahules786/linkedin_ai.git |
12 | | -``` |
13 | | - |
14 | | -This command downloads and installs the package directly from the GitHub repository. It gives you the latest version without needing to clone the repo locally. |
15 | | - |
16 | | -### Option 2: Clone and install locally |
17 | | -``` |
18 | | -bashgit clone git@github.com:shahules786/linkedin_ai.git |
| 7 | +git clone git@github.com:shahules786/linkedin_ai.git |
19 | 8 | cd linkedin_ai |
20 | 9 | pip install -e . |
21 | 10 | ``` |
22 | | -This approach clones the repository to your local machine, then installs it in "editable" mode (the -e flag). This allows you to make changes to the code and have them take effect immediately without reinstalling.# |
23 | | - |
24 | | -## Quick Example |
25 | | -```py |
26 | | -import os |
27 | | -from linkedin_ai import LinkedinAI |
28 | | - |
29 | | -# Set your OpenAI API key in environment variables for security |
30 | | -os.environ["OPENAI_API_KEY"] = "YOUR_OPENAI_API_KEY" |
31 | | - |
32 | | -# Create an instance using BM25 retrieval with your LinkedIn data |
33 | | -my_ai = LinkedinAI.from_bm25(posts="path/to/your/linkedin_posts.json") |
34 | | - |
35 | | -# Ask questions to your AI assistant |
36 | | -response = my_ai.ask("What is the best way to learn Python?") |
37 | | -print(response) |
38 | | -``` |
39 | | - |
40 | | -This code initializes a LinkedIn AI assistant that leverages the BM25 algorithm to find relevant content in your LinkedIn posts before generating a response. The response will match the style of the original content. |
41 | 11 |
|
42 | 12 | ## Your Hackathon Journey |
| 13 | + |
43 | 14 | ### Step 1: Explore the Basics |
44 | | -Start by checking out the [example notebook](docs/0_example.ipynb) to understand how the core functionality works. This will introduce you to: |
| 15 | +Start by checking out the [example notebook](0_example.ipynb) to understand how the core functionality works. This will introduce you to: |
45 | 16 |
|
46 | 17 | - How to load LinkedIn post data |
47 | 18 | - How to initialize the AI assistant |
48 | 19 | - How to ask questions and get responses |
49 | 20 |
|
50 | 21 | ### Step 2: Run Your First Experiment |
51 | | -Move on to the [experiment notebook](docs/01_experiment.ipynb) where you'll learn: |
| 22 | +Move on to the [experiment notebook](01_experiment.ipynb) where you'll learn: |
52 | 23 |
|
53 | | -- How to create test datasets |
54 | 24 | - How to set up LLM-based evaluation metrics |
55 | 25 | - How to run and track experiments systematically |
56 | | -- How to compare different approaches |
| 26 | +- How to compare different experiments |
| 27 | +- Ship the best-performing version of your AI assistant |
57 | 28 |
|
58 | 29 | ## Key Features |
59 | 30 |
|
|
0 commit comments