Humata API
Last updated
Last updated
The Humata API is the programmatic entry-point for your Humata documents, conversations, and answers.
Here are the 3-steps to use the Humata API after you sign up:
Create a Humata API Key on the Developer Settings Page (Admin only)
Copy your Document IDs from the Humata Dashboard
Make API Requests
Humata allows you to import new documents via the API. By passing a publicly available URL (or signed URL) to this endpoint, the document will be downloaded and processed on the Humata server.
Fetch the information of an already created PDF. Typically this is useful to poll until pdf.read_status == 'SUCCESS'
(and not pdf.read_status == 'FAILED'
) before asking questions against the PDF.
Create a conversation with a set of documents. A conversation must be created before asking questions to documents.
Humata allows you to chat with your document via the Ask endpoint. Create a conversation and then ask your documents
The Ask Endpoint returns a stream of server-sent events. Here is a full example of response to the question "Who is George Washington?":
Each answer from Humata will provide references to the parts of the document that our AI used to answer the question. The format of references is subject to change.
Humata allows you to download your data via the Download Data endpoint. Simply initiate a request and retrieve your data effortlessly.
By default the API rate limit is 120 requests / minute. This rate limit can be increased by request. Please reach out to support@humata.ai to get this limit raised.
File download successful
true
URL to download the file
Ask a question in a conversation. Response is streamed via server-sent events.
Successfully answered the question.
Imports a PDF from a given URL into the specified folder.
The URL of the PDF to import.
The UUID of the folder to import the PDF into.
Successfully imported the PDF.
The unique identifier of the imported document.
Retrieve details of a PDF by its ID.
The unique identifier of the PDF.
Details of the PDF.
"9294544b-2b6a-4c93-976c-d1910b8c1423"
"example.pdf"
"fcf6c954-ba68-4e39-a7b5-960dc8274ec0"
"2024-12-05T20:18:53.289618+00:00"
"2024-12-05T20:18:55.584786+00:00"
"6c702c82-bb8a-4274-8cb6-074e0bf78084"
"SUCCESS"
"07f5bfc7-72c9-40b7-8151-dcfc2f9613dc"
"PDF"
Creates a new conversation based on the document IDs.
Successfully created a new conversation.
The unique identifier of the created conversation.