Use a Model with LlamaIndex
A Model is an OpenAI-compatible chat model, so LlamaIndex’s OpenAILike LLM calls it. Set FACET_BASE_URL and FACET_API_KEY as in Call a Model.
pip install llama-index-llms-openai-like
import os
from llama_index.llms.openai_like import OpenAILike
llm = OpenAILike(
model="support-triage",
api_base=os.environ["FACET_BASE_URL"],
api_key=os.environ["FACET_API_KEY"],
is_chat_model=True,
)
print(llm.complete("My card was charged twice").text)
Set is_chat_model=True: a Model answers only on the chat completions route. Send only the input. Facet adds the Model’s Instructions to every call, so leave out your own system prompt.
Next steps
- Call a Model: every parameter and header a call takes
- Return structured output: get answers as fields or JSON