TokenizedToast
所属分类:内容生成
开发工具:Jupyter Notebook
文件大小:0KB
下载次数:0
上传日期:2023-08-22 01:20:27
上 传 者:
sh-1993
说明: AI策划的新闻稿。在这里,我们每天拉入最新的新闻文章,为特定用户选择文章,并生成简短的教育信息...,
(AI-Curated Newsletter. Where we pull in current news articles daily, select articles for a particular user, and generate a short-educative newsletter based off of these articles.)
文件列表:
ArchV2/ (0, 2024-01-02)
ArchV2/Batch-Encoding/ (0, 2024-01-02)
ArchV2/Batch-Encoding/delete.py (1724, 2024-01-02)
ArchV2/Batch-Encoding/encoder.py (3572, 2024-01-02)
ArchV2/Batch-Encoding/load_pretrained.py (450, 2024-01-02)
ArchV2/Batch-Encoding/main.py (5218, 2024-01-02)
ArchV2/Batch-Encoding/testing.py (2327, 2024-01-02)
ArchV2/Content-Processor/ (0, 2024-01-02)
ArchV2/Content-Processor/article_extraction.py (3741, 2024-01-02)
ArchV2/Content-Processor/main.py (7386, 2024-01-02)
ArchV2/RSS-Extractor/ (0, 2024-01-02)
ArchV2/RSS-Extractor/article_extraction.py (3079, 2024-01-02)
ArchV2/RSS-Extractor/cleaning-rss.ipynb (8999, 2024-01-02)
ArchV2/RSS-Extractor/delete.py (855, 2024-01-02)
ArchV2/RSS-Extractor/feed_checking.py (1261, 2024-01-02)
ArchV2/RSS-Extractor/main.py (2083, 2024-01-02)
py (4057, 2024-01-02)
ArchV2/UserRequestContent/ (0, 2024-01-02)
ArchV2/UserRequestContent/gatewayRequestHandler/ (0, 2024-01-02)
ArchV2/UserRequestContent/gatewayRequestHandler/lambda_handler.py (1556, 2024-01-02)
ETL/ (0, 2024-01-02)
ETL/Content-Transform/ (0, 2024-01-02)
ETL/Content-Transform/cleaning.py (1447, 2024-01-02)
ETL/Content-Transform/main.py (598, 2024-01-02)
ETL/EMR/ (0, 2024-01-02)
ETL/EMR/cli-command.sh (1151, 2024-01-02)
ETL/EMR/emr.py (4743, 2024-01-02)
ETL/EMR/emr_boostrap.sh (339, 2024-01-02)
ETL/EMR/software-config.json (610, 2024-01-02)
ETL/RSS-Extractor/ (0, 2024-01-02)
ETL/RSS-Extractor/article_extraction.py (3080, 2024-01-02)
ETL/RSS-Extractor/main.py (4057, 2024-01-02)
ETL/RSS-Extractor/rss-feeds.json (129673, 2024-01-02)
LICENSE (1075, 2024-01-02)
Lambdas/ (0, 2024-01-02)
Lambdas/ArticleRecommendation/ (0, 2024-01-02)
Lambdas/ArticleRecommendation/lambda_handler.py (40, 2024-01-02)
Lambdas/Failsafe-EC2-Costs.py (660, 2024-01-02)
Lambdas/MidnightPusher.py (2324, 2024-01-02)
... ...
# TokenizedToast
![ToastLogo-removebg-preview](https://github.com/Charles-Gormley/TokenizedToast/assets/76138796/196513e4-dac5-46a8-9134-34e7b9ee51e3)
AI-Curated Newsletter. Where we pull in current news articles daily, select articles for a particular user, and generate a short-educative newsletter based off of these articles.
# TokenizedToast
AI-Curated Newsletter. Where we pull in current news articles daily, select articles for a particular user, and generate a short-educative newsletter based off of these articles.
## Requirements
* Python: 3.10
* Run: pip install -r requirments.txt
## Project Sections
1. Building & Traing Topic Modelings Models
2. Data Pipeline For Daily RSS Feeds
3. Topic Modelling at end of Data Pipeline
4. Article Recommendation Algorithm
5. LLM Summarization w/ User Parameters
6. Email Sending
7. MLOps
### 1. Building & Traing Topic Modelings Models
#### Datasets
1. https://www.kaggle.com/datasets/rmisra/news-category-dataset
2. https://www.kaggle.com/datasets/jeet2016/us-financial-news-articles
3. https://www.kaggle.com/datasets/jkkphys/english-wikipedia-articles-20170820-sqlite
近期下载者:
相关文件:
收藏者: