NewsGPT-Using-LangChain-and-FastAPI

所属分类:后台框架
开发工具:Jupyter Notebook
文件大小:0KB
下载次数:0
上传日期:2023-09-10 10:34:01
上 传 者sh-1993
说明:  NewsGPT是一个web应用程序,使用LangChain和FastAPI框架总结新闻文章。它采用BART Large CNN模型作为LLM,并且它...,
(NewsGPT is a web app that summarizes news articles using LangChain and FastAPI frameworks. It employs BART Large CNN model as LLM, and it also provides support to incorporate OpenAI s ChatGPT.)

文件列表:
Images of the Working APP/ (0, 2023-09-10)
Images of the Working APP/Accessing the NewsGPT's FastAPI from GitBash.png (34268, 2023-09-10)
Images of the Working APP/Landing Page of NewsGPT's FastAPI.png (14493, 2023-09-10)
Images of the Working APP/Using NewsGPT API from local IDE.png (61706, 2023-09-10)
Images of the Working APP/Using the custom function of FastAPI.png (60086, 2023-09-10)
Images of the Working APP/img.txt (1, 2023-09-10)
NewsGPT Code.ipynb (22848, 2023-09-10)
Use NewsGPT from IDE.py (828, 2023-09-10)
Wroking.txt (148, 2023-09-10)
bash_code.sh (357, 2023-09-10)
requirements.txt (50, 2023-09-10)

# NewsGPT Using LangChain and FastAPI ![GitHub stars](https://img.shields.io/github/stars/MUmairAB/NewsGPT-Using-LangChain-and-FastAPI?style=flat-square) ![GitHub forks](https://img.shields.io/github/forks/MUmairAB/NewsGPT-Using-LangChain-and-FastAPI?style=flat-square) ![GitHub issues](https://img.shields.io/github/issues/MUmairAB/NewsGPT-Using-LangChain-and-FastAPI?style=flat-square) ![GitHub pull requests](https://img.shields.io/github/issues-pr/MUmairAB/NewsGPT-Using-LangChain-and-FastAPI?style=flat-square) This repository contains an implementation of NewsGPT, a news summarization model, using **LangChain** and **FastAPI**. This model is production-ready and can seamlessly function as a standalone application or be seamlessly integrated into other applications. Through this project, you have the capability to produce concise summaries of news articles, providing you with the primary highlights of each article. ## Table of Contents - [1. Introduction](#introduction) - [2. Installation](#installation) - [3. Usage](#usage) - [4. API Endpoints](#api-endpoints) - [5. Screenshots of the Working App](#screenshots) - [6. License](#license) - [7. Contributions](#contributions) ## 1. Introduction NewsGPT is a powerful language model that can generate coherent and contextually relevant summaries of news articles. This project leverages LangChain, a state-of-the-art language model, and FastAPI, a modern web framework, to create an API for generating news articles on-the-fly. It employs [BART Large CNN](https://huggingface.co/facebook/bart-large-cnn) model as LLM. Additionally, it extends support for seamless integration with **OpenAI's ChatGPT**. ## 2. Installation Before you begin, ensure you have Python 3.9+ installed on your system. You can then set up the project as follows: #### 2.1 Clone the repository: ```bash git clone https://github.com/MUmairAB/NewsGPT-Using-LangChain-and-FastAPI.git cd NewsGPT-Using-LangChain-and-FastAPI ``` #### 2.2 Install the required dependencies: ``` pip install -r requirements.txt ``` #### 2.3 Replace your own HuggingFace **Access Key** in **secret_key.py** file. ## 3. Usage To use NewsGPT, follow these steps: #### 3.1 Step 1: If you are running the code in Google Colab, then proceed to the next step. But if you are running the code on your local computer, then make the following changes in **NewsGPT Code** file. **A)** Remove the following code from the file. ``` #The following code is necessary to run the FastAPI app in Colab # But if you are running it locally, then you can un-comment the following app.add_middleware( CORSMiddleware, allow_origins=['*'], allow_credentials=True, allow_methods=['*'], allow_headers=['*'], ) ``` **B)** Replace the following code: ``` #Run the FastAPI app on local server import nest_asyncio from pyngrok import ngrok import uvicorn ngrok_tunnel = ngrok.connect(8000) print('Public URL:', ngrok_tunnel.public_url) nest_asyncio.apply() uvicorn.run(app, port=8000) ``` with ``` import uvicorn uviconr.run(app="NewsGPT Code:app", host="127.0.0.1", port=8000, reload=True) ``` #### 3.2 Step 2 **A)** Start the FastAPI web server: ``` python 'NewsGPT Code.py' ``` **B)** Open your web browser and navigate to http://localhost:8000/docs to access the Swagger documentation and try out the API endpoints. **C)** Use the API endpoints to generate news article summaries programmatically. ## 4. API Endpoints #### 4.1 /summary: Generate summarised news articles by providing the article's URL as input prompts. For detailed information on how to use each endpoint, refer to the Swagger documentation available at **http://localhost:8000/docs**. ## 5. Screenshots of the Working App Following are the snaps of the running app. #### 5.1 Using the NewsGPT app in a web browser. #### 5.2 Using the NewsGPT app from the GitBash terminal using the [Bash Script](https://github.com/MUmairAB/NewsGPT-Using-LangChain-and-FastAPI/blob/main/bash_code.sh) #### 5.3 Using the NewsGPT app from local IDE using [Python Script](https://github.com/MUmairAB/NewsGPT-Using-LangChain-and-FastAPI/blob/main/Use%20NewsGPT%20from%20IDE.py). ## 6. License This project is licensed under the MIT License. Feel free to use, modify, and distribute this code for your own purposes. ## 7. Contributions Thank you for using NewsGPT-Using-LangChain-and-FastAPI! If you have any questions or encounter any issues, please don't hesitate to [create an issue](https://github.com/MUmairAB/NewsGPT-Using-LangChain-and-FastAPI/issues).

近期下载者

相关文件


收藏者