Quickstart
Nebula is currently in private beta.
To request access, see the sign up form.
This guide describes how to access and use the Nebula LLM (large language model).
Request access
You must request access from the sign up form to use the model. Once your request is approved, you will receive instructions about using the Playground and API.
Use the playground
You can use the Model API playground to start testing the model quickly without the need to write any code. The playground is a great way to get started by testing your transcripts and prompts.
Use the Model API
- Add your
ApiKey
to the header. You should have received the key when you were granted access to the model. - The Model API requires the
prompt
parameter along withinstruction
andconversation
in the request body. For best practices, see prompt design.
For details about the Model API parameters, see the API reference documentation.
cURL
The following example shows the basic structure of a cURL request and prompt. Because the language model parameters arenβt specified, default values are used.
curl -X POST --location 'https://api-nebula.symbl.ai/v1/model/generate' \
--header 'Content-Type: application/json' \
--header 'ApiKey: YOUR_API_KEY' \
--data '{
"prompt": {
"instruction": "your instruction goes here",
"conversation": {
"text": "the transcript of your conversation goes here "
}
},
}'
Python
The following Python example provides a prompt and shows how to use additional parameters in the request.
import requests
import json
url = "https://api-nebula.symbl.ai/v1/model/generate"
# Prepare the request payload
payload = json.dumps(
{
"prompt": {
# Your instruction or question goes here
"instruction": "Generate summary of this conversation.",
"conversation": {
# Your conversation transcript goes here
"text": "Representative: Hello, How are you?\nCustomer: Hi, good. I am trying to get access to my account but ....",
}
}
"max_new_tokens": 256
}
)
# Set the headers with the API key
headers = {
"ApiKey": f"{api_key}",
"accept": "application/json",
"Content-Type": "application/json",
}
# Make the POST request
response = requests.request("POST", url, headers=headers, data=payload)
# Process the response
if response.status_code == 200:
data = response.json()
print("Output:\n", data)
else:
print("Request failed with status code:", response.status_code)
print("Error message:", response.text)
You should receive a response similar to this:
{
'model': 'nebula-large',
'output': { 'scores': None,
'text': '\n'
'1. Schedule a demo for Mr. Smith to see the software in
'
'action.\n'
'2. Coordinate with the team to arrange a suitable time '
'for the demo.\n'
'3. Provide information about the software solution's '
'features and benefits.\n'
'4. Highlight the software's customization capabilities '
'and seamless integration into existing workflows.\n'
'5. Address any concerns or questions that may arise '
'during the demo.\n'
'6. Partner with Mr. Smith to maximize business '
'efficiency and achieve goals.'},
'stats': { 'input_tokens': 2303,
'output_tokens': 32,
'total_tokens': 2335}
}
Updated 24 days ago