ppx-llamaindex

LlamaIndex integration for the Preference Profile Exchange (PPX).

Install

pip install ppx-llamaindex

Requires Python 3.11+. Published version: 0.1.0a1 (PyPI).

Alpha, tracking a draft specification. Expect breaking changes. The version is 0.1.0a1 on PyPI and 0.1.0-alpha.1 on npm — the same release in each ecosystem's required format.

Load claims as Documents

from ppx_client import PpxClient
from ppx_llamaindex import PpxReader
from llama_index.core import VectorStoreIndex

client = PpxClient("https://api.provider.app")
reader = PpxReader(client, grant_token=my_grant_token,
                   effective_kwargs={"requested_namespaces": ["fragrance"]})
docs = reader.load_data()

index = VectorStoreIndex.from_documents(docs)
query = index.as_query_engine().query("What scent profile suits this user?")

Use as a tool in an agent

from llama_index.core.agent import ReActAgent
from llama_index.llms.openai import OpenAI
from ppx_llamaindex import ppx_preference_tool

tool = ppx_preference_tool(client, grant_token=my_grant_token)
agent = ReActAgent.from_tools([tool], llm=OpenAI(model="gpt-4o-mini"))
agent.chat("Recommend a trip based on my core preferences.")

License

Apache-2.0.