Add a document

The files API endpoint can be used to upload a document to Paradigm to be then used in the Chat with docs application.

Prerequisites

In order to do so, here are the prerequisites:

• A Paradigm API key: if you do not have one, go to your Paradigm profile and generate a new API key.
• The desired document to upload: The file to upload cannot have a size above 100MB.

Usage methods

There are several ways to call the endpoint:

1. With the OpenAI python client (recommended)
2. With the python requests package: to avoid having the OpenAI layer
3. Through a curl request: good to do a quick check or a first test

OpenAI python client

Setup

Install the OpenAI python package with the following bash command:

pip install --upgrade openai

You can then setup the OpenAI python client in your script:

from openai import OpenAI as OpenAICompatibleClient
import os

# Get API key from environment
api_key = os.getenv("PARADIGM_API_KEY")
# Our base url
base_url = "https://paradigm.lighton.ai/api/v2"

# Configure the OpenAI client
client = OpenAICompatibleClient(api_key=api_key, base_url=base_url)

Here the Paradigm API key is set up in an environment variable, but you could perfectly forward it through argument parsing with argparse.

Usage

To upload a file into Paradigm, you can use the client.files.create() method.
An example is described below to upload the file called test_upload_file.pdf:

upload_response = client.files.create(
	file=open("/path/to/test_upload_file.pdf", "rb"),
	purpose="documents"
)

The given response would then follow the OpenAI format:

FileObject(
    id=1,
    bytes=9626,
    created_at=1714656771,
    filename='test_upload_file.pdf',
    object='file',
    purpose='documents',
    status='success',
    status_details=None
)

Python requests package

You can also avoid using the OpenAI python class and directly send request to the API endpoint through the requests package.

import requests
import os

# Get API key from environment
api_key = os.getenv("PARADIGM_API_KEY")
# Path of the file to upload
file_path = "/path/to/test_upload_file.pdf"

response = requests.request(
	method="POST",
	url=f"https://paradigm.lighton.ai/api/v2/files",
	headers={
		'Authorization': f"Bearer {api_key}"
	},
	data={"purpose": "documents"},
	files={
		"file": open(file_path, "rb"),
	}
)

print(response.json())

You would then get a JSON answer as a dictionnary:

{
    'id': 1,
    'object': 'file',
    'bytes': 9626,
    'created_at': 1714659874,
    'filename': 'test_upload_file.pdf',
    'purpose': 'documents',
    'status': 'success'
}

cURL request

If you would prefer sending a request to Paradigm with a simple cURL command, here is an example:

curl https://paradigm.lighton.ai/api/v2/files \
  -H "Authorization: Bearer $PARADIGM_API_KEY" \
  -F purpose="documents" \
  -F file="@/path/to/test_upload_file.pdf"