LlamaAPI is a Python SDK for interacting with the Llama API. It abstracts away the handling of aiohttp sessions and headers, allowing for a simplified interaction with the API.
You can install the LlamaAPI SDK using pip:
pip install llamaapi
After installing the SDK, you can use it in your Python projects like so:
import json
from llamaapi import LlamaAPI
# Initialize the llamaapi with your api_token
llama = LlamaAPI("<your_api_token>")
# Define your API request
api_request_json = {
"messages": [
{"role": "user", "content": "Extract the desired information from the following passage.:\n\nHi!"},
],
"functions": [
{'name': 'information_extraction',
'description': 'Extracts the relevant information from the passage.',
'parameters': {
'type': 'object',
'properties': {
'sentiment': {
'title': 'sentiment',
'type': 'string',
'description': 'the sentiment encountered in the passage'
},
'aggressiveness': {
'title': 'aggressiveness',
'type': 'integer',
'description': 'a 0-10 score of how aggressive the passage is'
},
'language': {
'title': 'language',
'type': 'string',
'description': 'the language of the passage'
}
},
'required': ['sentiment', 'aggressiveness', 'language']
}
}
],
"stream": False,
"function_call": {"name": "information_extraction"},
}
# Make your request and handle the response
response = llama.run(api_request_json)
print(json.dumps(response.json(), indent=2))
Other parameters that you can pass in the request json is:
{
...
"max_length" = 500,
"temperature"= 0.1,
"top_p"= 1.0,
"frequency_penalty"=1.0
...
}
Note: Stream is still not working, so it is recommended to submit with stream: False
.
Version 0.1: Initial release
We welcome contributions to this project. Please see the Contributing Guidelines for more details.
llamaapi SDK is licensed under the MIT License. Please see the License File for more details.