mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-05-19 18:35:16 +02:00
d7b36aaf3f
- get_agent_tools branches on doc_ids:
- scoped (doc_ids=[...]): drops list_documents and hard-enforces a
whitelist on the remaining tools; system prompt switches to
SCOPED_SYSTEM_PROMPT (no list_documents instruction); doc list +
summaries are prepended to the user message via wrap_with_doc_context.
- open (doc_ids=None): unchanged 4-tool agent loop.
- list_documents now exposes doc_description (sqlite + cloud).
- Collection.query emits UserWarning when doc_ids is None and the
collection holds >1 documents; PAGEINDEX_EXPERIMENTAL_MULTIDOC=1
silences it. Single-doc collections skip the warning; empty
collections raise ValueError.
- Agents SDK tracing upload disabled by default (avoids SSL timeouts);
PAGEINDEX_AGENTS_TRACING=1 re-enables it.
- README: new SDK Usage section covering local/cloud quick start,
streaming, multi-doc as experimental, and runnable examples.
96 lines
3.4 KiB
Python
96 lines
3.4 KiB
Python
# pageindex/collection.py
|
|
from __future__ import annotations
|
|
import os
|
|
import warnings
|
|
from typing import AsyncIterator
|
|
from .events import QueryEvent
|
|
from .backend.protocol import Backend
|
|
|
|
|
|
def _multidoc_acked() -> bool:
|
|
return os.getenv("PAGEINDEX_EXPERIMENTAL_MULTIDOC", "").lower() in ("1", "true", "yes")
|
|
|
|
|
|
_MULTIDOC_WARNING = (
|
|
"Querying the entire collection (no doc_ids) is experimental — selection "
|
|
"accuracy depends on auto-generated doc descriptions. Pass doc_ids=[...] "
|
|
"for reliable results, or set PAGEINDEX_EXPERIMENTAL_MULTIDOC=1 to silence "
|
|
"this warning."
|
|
)
|
|
|
|
|
|
class QueryStream:
|
|
"""Wraps backend.query_stream() as an async iterable object."""
|
|
|
|
def __init__(self, backend: Backend, collection: str, question: str,
|
|
doc_ids: list[str] | None = None):
|
|
self._backend = backend
|
|
self._collection = collection
|
|
self._question = question
|
|
self._doc_ids = doc_ids
|
|
|
|
async def stream_events(self) -> AsyncIterator[QueryEvent]:
|
|
async for event in self._backend.query_stream(
|
|
self._collection, self._question, self._doc_ids
|
|
):
|
|
yield event
|
|
|
|
def __aiter__(self):
|
|
return self.stream_events()
|
|
|
|
|
|
class Collection:
|
|
def __init__(self, name: str, backend: Backend):
|
|
self._name = name
|
|
self._backend = backend
|
|
|
|
@property
|
|
def name(self) -> str:
|
|
return self._name
|
|
|
|
def add(self, file_path: str) -> str:
|
|
return self._backend.add_document(self._name, file_path)
|
|
|
|
def list_documents(self) -> list[dict]:
|
|
return self._backend.list_documents(self._name)
|
|
|
|
def get_document(self, doc_id: str, include_text: bool = False) -> dict:
|
|
return self._backend.get_document(self._name, doc_id, include_text=include_text)
|
|
|
|
def get_document_structure(self, doc_id: str) -> list:
|
|
return self._backend.get_document_structure(self._name, doc_id)
|
|
|
|
def get_page_content(self, doc_id: str, pages: str) -> list:
|
|
return self._backend.get_page_content(self._name, doc_id, pages)
|
|
|
|
def delete_document(self, doc_id: str) -> None:
|
|
self._backend.delete_document(self._name, doc_id)
|
|
|
|
def query(self, question: str, doc_ids: list[str] | None = None,
|
|
stream: bool = False) -> str | QueryStream:
|
|
"""Query documents in this collection.
|
|
|
|
- stream=False: returns answer string (sync)
|
|
- stream=True: returns async iterable of QueryEvent
|
|
|
|
Usage:
|
|
answer = col.query("question", doc_ids=[doc_id])
|
|
async for event in col.query("question", doc_ids=[doc_id], stream=True):
|
|
...
|
|
|
|
Passing doc_ids=None queries the entire collection — this is
|
|
experimental; emits a UserWarning unless PAGEINDEX_EXPERIMENTAL_MULTIDOC
|
|
is set.
|
|
"""
|
|
if doc_ids is None and not _multidoc_acked():
|
|
docs = self._backend.list_documents(self._name)
|
|
if not docs:
|
|
raise ValueError(
|
|
f"Cannot query collection '{self._name}': it is empty. "
|
|
"Add documents with col.add(...) first."
|
|
)
|
|
if len(docs) > 1:
|
|
warnings.warn(_MULTIDOC_WARNING, UserWarning, stacklevel=2)
|
|
if stream:
|
|
return QueryStream(self._backend, self._name, question, doc_ids)
|
|
return self._backend.query(self._name, question, doc_ids)
|