pip install -U pageindex

import os
from pageindex import PageIndexClient
 
os.environ["OPENAI_API_KEY"] = "your-openai-key"
 
client = PageIndexClient(
    index="gpt-5.6-luna",     # model that builds the tree index
    chat="gpt-5.6-sol",       # model that searches the tree
)
 
doc_id = client.submit_document("./2023-annual-report.pdf")["doc_id"]
 
answer = client.chat(
    "What was the 2023 operating margin, and where is it stated?",
    doc_id=doc_id,
)
print(answer)

import os
from pageindex import PageIndexClient
 
os.environ["PAGEINDEX_API_KEY"] = "your-pageindex-key"
os.environ["OPENAI_API_KEY"] = "your-openai-key"
 
client = PageIndexClient(
    index="cloud",            # index and store in PageIndex Cloud
    chat="gpt-5.6-sol",       # your own model answers
)
 
# Cloud indexing is asynchronous — wait=True blocks until the document is ready
doc_id = client.submit_document("./2023-annual-report.pdf", wait=True)["doc_id"]
print(client.chat("What was the 2023 operating margin?", doc_id=doc_id))

client.chat("What changed in the risk factors?", doc_id=doc_id)
 
# Several documents at once
client.chat("Compare the results across these reports", doc_id=[doc_id_a, doc_id_b])
 
# Stream the answer as text chunks
for chunk in client.chat("Summarize this document", doc_id=doc_id, stream=True):
    print(chunk, end="", flush=True)

messages = [
    {
        "role": "system",
        "content": (
            'Cite only statements supported by tool outputs using '
            '<cite doc="{docName}" page="{pageNumber}"/>'
        ),
    },
    {"role": "user", "content": "Summarize the document."},
]
 
answer = client.chat(messages, doc_id=doc_id)

Revenue increased during the reporting period. <cite doc="report.pdf" page="12"/>

client.list_documents()   # everything you have indexed