Quickstart

Upload a document and run a query. All within minutes.

Get Token

Sign up at chat.activeloop.ai. Navigate to ⚙️ → API tokens, and create a token. Set the token as ACTIVELOOP_TOKEN environment variable.

Upload Documents

We will fetch and index DeepSeek R1 paper.

import os, io, requests

# Fetch a PDF from the URL
pdf_url = "https://arxiv.org/pdf/2501.12948"
pdf_content = io.BytesIO(requests.get(pdf_url).content)

headers = {'Authorization': f'Bearer {os.getenv("ACTIVELOOP_TOKEN")}'}
files = {'file': ('deepseek_r1.pdf', pdf_content) }

response = requests.post(
      'https://api.activeloop.ai/files', 
      headers=headers, 
      files=files
)
# Onced uploaded, it would take few minutes to index

You can learn about the state by listing files.

Query Data

Once the data is indexed, you can run a query against it as if you are calling your LLM .

from openai import OpenAI

client = OpenAI(
    base_url="https://api.activeloop.ai/",
    api_key=os.getenv('ACTIVELOOP_TOKEN')
)

response = client.chat.completions.create(
    model="activeloop-l0",
    messages=[
        {
            "role": "user",
            "content": "What is the AIME score of DeepSeek R1?"
        }
    ]
)

print(response.choices[0].message.content) # answer  
print(response.choices[0].metadata['metadata']['relevant_docs']) # citations