This API uses various tools and libraries to fetch content from a URL, process it, and generate responses using OpenAI's language models. It supports both GET and POST requests.
To get starting first clone the Repo and than install packages.
git clone https://github.com/RaheesAhmed/rag-with-any-url.git
npm install
or
npm i
Start the server by running:
npm start
The server will run on http://localhost:3000
. You can use the /chat
endpoint to interact with the API.
Returns a welcome message and the expected parameters.
Accepts a JSON body with the following fields:
query (string, required): The query to ask.
url (string, required): The URL to fetch content from.
model (string, optional): The model to use (default: "gpt-4o").
temperature (number, optional): The temperature setting for the model (default: 0.7).
maxTokens (number, optional): The maximum number of tokens (default: 1000).
chunkSize (number, optional): The size of the chunks to split the text into (default: 1000).
chunkOverlap (number, optional): The overlap between chunks (default: 200).
Include the openai-api-key in the request headers.
{
"query": "What is the main topic of the article?",
"url": "https://example.com/article",
"model": "gpt-4o",
"temperature": 0.7,
"maxTokens": 1000,
"chunkSize": 1000,
"chunkOverlap": 200
}
Include the openai-api-key
in the headers
of the request.
This API is a powerful tool for fetching and processing content from URLs and generating responses using OpenAI's language models. Feel free to extend and customize it to suit your needs.