----------------------
To invoke an API using LlamaIndex, you first need to obtain an API key from the respective service. For example, if you're using the Llama API, you can obtain the key from
Once you have the API key, you can use it to initialize the API object in your Python code. Here's an example of how to do this with the Llama API:
from llama_index.llms.llama_api import LlamaAPI
api_key = "LL-your-key" # replace with your actual API key
llm = LlamaAPI(api_key=api_key)
After initializing the API object, you can use its methods to interact with the API. For example, you can use the
complete method to get a completion for a given prompt:
resp = llm.complete("Paul Graham is ")
print(resp)Or you can use the
chat method to have a conversation with the API:
from llama_index.llms import ChatMessage
messages = [
ChatMessage(
role="system", content="You are a pirate with a colorful personality"
),
ChatMessage(role="user", content="What is your name"),
]
resp = llm.chat(messages)
print(resp)Remember to replace
"LL-your-key" with your actual API key.
For more details, you can refer to the
Llama API documentation ().
----------------------
Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:
----------------------
