Social GPT
This package helps you to build embeddings based on someone social profile. It will scrape the data from the social media and build the embeddings based on the data. The embeddings can be used for further analysis. Once scraped, you can query it with the use of openai.
Installation
Install using following command:
pip install social-gpt
Setup
Update the example.env and change it's name to .env. Add relevant information in the .env file.
Creating embeddings
As of now, only youtube is supported. Also, as of now, we will scrape 50 videos, which we will extend to all of the videos shortly. We will be bringing more social media platforms soon. To create embeddings, run the following command: To get the channel id, go to this website and enter the channel url. It will give you the channel id.
from social_gpt.ingestion.ingestion import SocialIngestion
ingestion = SocialIngestion(channel_id, 'youtube')
index_id = ingestion.create_embeddings()
Store this index_id for querying the embeddings.
Querying embeddings
from social_gpt.query.query_helper import QueryHelper
q = QueryHelper(index_id)
response = q.query('What is the best way to learn python?')
print(response)
That's it!
1 maintainer
Metadata
1 maintainer
Release files for social-gpt 0.0.19
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| social_gpt-0.0.19.tar.gz | 7.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| social_gpt-0.0.19-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 18.6 kB
Release files / social_gpt-0.0.19.tar.gz
How to use checksums
e443d230cf6be29a978dc63711e0f695a1222e3a8f572d4a2ff2255d724de320How to use checksums
e7c3a5a2edb79016f1a98f110cbcbc9b3ae1c7a56d7917aac165273d18cb653cWhat is trusted publishing?
twine/4.0.2 CPython/3.11.3