mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-05-19 18:35:16 +02:00
a47c36a3f5
- Collection.query and Backend.query/query_stream accept doc_ids as str, list[str] or None. Single str is normalized to [str] inside each backend; bare [] is rejected with ValueError at both layers. - wrap_with_doc_context wraps the scoped doc list in <docs>...</docs> and SCOPED_SYSTEM_PROMPT instructs the agent to treat that block as data, not instructions (defense against prompt injection via auto-generated doc_description). - _require_cloud_api now distinguishes api_key="" from api_key=None; the former gives a targeted error pointing at the empty-string vs fall-back-to-local situation when legacy SDK methods are called. - Legacy PageIndexClient.list_documents docstring spells out the return-shape difference vs collection.list_documents() to flag a silent migration footgun (paginated dict with id/name keys vs plain list[dict] with doc_id/doc_name keys). - Remove dead CloudBackend.get_agent_tools stub (not on the Backend protocol; only ever returned an empty AgentTools()) and the SYSTEM_PROMPT alias (OPEN_/SCOPED_SYSTEM_PROMPT are the explicit names now). - README quick start and streaming example now pass doc_ids; new multi-document section shows both str and list forms. - examples/demo_query_modes.py exercises all five query-mode cases (single-doc, multi-doc with/without env var, scoped single, scoped multi) for manual verification.
36 lines
1.6 KiB
Python
36 lines
1.6 KiB
Python
from __future__ import annotations
|
|
from dataclasses import dataclass, field
|
|
from typing import Protocol, Any, AsyncIterator, runtime_checkable
|
|
|
|
from ..events import QueryEvent
|
|
|
|
|
|
@dataclass
|
|
class AgentTools:
|
|
"""Structured container for agent tool configuration (local mode only)."""
|
|
function_tools: list[Any] = field(default_factory=list)
|
|
mcp_servers: list[Any] = field(default_factory=list)
|
|
|
|
|
|
@runtime_checkable
|
|
class Backend(Protocol):
|
|
# Collection management
|
|
def create_collection(self, name: str) -> None: ...
|
|
def get_or_create_collection(self, name: str) -> None: ...
|
|
def list_collections(self) -> list[str]: ...
|
|
def delete_collection(self, name: str) -> None: ...
|
|
|
|
# Document management
|
|
def add_document(self, collection: str, file_path: str) -> str: ...
|
|
def get_document(self, collection: str, doc_id: str, include_text: bool = False) -> dict: ...
|
|
def get_document_structure(self, collection: str, doc_id: str) -> list: ...
|
|
def get_page_content(self, collection: str, doc_id: str, pages: str) -> list: ...
|
|
def list_documents(self, collection: str) -> list[dict]: ...
|
|
def delete_document(self, collection: str, doc_id: str) -> None: ...
|
|
|
|
# Query — doc_ids accepts a single id or a list; implementations should
|
|
# normalize internally (a bare str is treated as a single-element list).
|
|
def query(self, collection: str, question: str,
|
|
doc_ids: str | list[str] | None = None) -> str: ...
|
|
async def query_stream(self, collection: str, question: str,
|
|
doc_ids: str | list[str] | None = None) -> AsyncIterator[QueryEvent]: ...
|