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.
77 lines
2.8 KiB
Python
77 lines
2.8 KiB
Python
# tests/sdk/test_client.py
|
|
import pytest
|
|
from pageindex.client import PageIndexClient, LocalClient, CloudClient
|
|
|
|
|
|
def test_local_client_is_pageindex_client(tmp_path):
|
|
client = LocalClient(model="gpt-4o", storage_path=str(tmp_path / "pi"))
|
|
assert isinstance(client, PageIndexClient)
|
|
|
|
|
|
def test_cloud_client_is_pageindex_client():
|
|
client = CloudClient(api_key="pi-test")
|
|
assert isinstance(client, PageIndexClient)
|
|
|
|
|
|
def test_empty_api_key_legacy_method_error_is_specific(tmp_path, caplog):
|
|
"""Empty api_key falls back to local mode; legacy methods raise a clear error."""
|
|
import warnings
|
|
from pageindex.errors import PageIndexAPIError
|
|
|
|
client = PageIndexClient(api_key="", storage_path=str(tmp_path / "pi"))
|
|
# Empty api_key → local mode; legacy methods should explain why
|
|
with warnings.catch_warnings():
|
|
warnings.simplefilter("ignore", PendingDeprecationWarning)
|
|
with pytest.raises(PageIndexAPIError, match="empty string"):
|
|
client.submit_document("some.pdf")
|
|
|
|
|
|
def test_none_api_key_legacy_method_error_is_generic(tmp_path):
|
|
"""api_key=None → local mode; legacy methods raise generic error (not 'empty')."""
|
|
import warnings
|
|
from pageindex.errors import PageIndexAPIError
|
|
|
|
client = PageIndexClient(api_key=None, model="gpt-4o", storage_path=str(tmp_path / "pi"))
|
|
with warnings.catch_warnings():
|
|
warnings.simplefilter("ignore", PendingDeprecationWarning)
|
|
with pytest.raises(PageIndexAPIError) as exc_info:
|
|
client.submit_document("some.pdf")
|
|
assert "empty" not in str(exc_info.value)
|
|
|
|
|
|
def test_collection_default_name(tmp_path):
|
|
client = LocalClient(model="gpt-4o", storage_path=str(tmp_path / "pi"))
|
|
col = client.collection()
|
|
assert col.name == "default"
|
|
|
|
|
|
def test_collection_custom_name(tmp_path):
|
|
client = LocalClient(model="gpt-4o", storage_path=str(tmp_path / "pi"))
|
|
col = client.collection("papers")
|
|
assert col.name == "papers"
|
|
|
|
|
|
def test_list_collections_empty(tmp_path):
|
|
client = LocalClient(model="gpt-4o", storage_path=str(tmp_path / "pi"))
|
|
assert client.list_collections() == []
|
|
|
|
|
|
def test_list_collections_after_create(tmp_path):
|
|
client = LocalClient(model="gpt-4o", storage_path=str(tmp_path / "pi"))
|
|
client.collection("papers")
|
|
assert "papers" in client.list_collections()
|
|
|
|
|
|
def test_delete_collection(tmp_path):
|
|
client = LocalClient(model="gpt-4o", storage_path=str(tmp_path / "pi"))
|
|
client.collection("papers")
|
|
client.delete_collection("papers")
|
|
assert "papers" not in client.list_collections()
|
|
|
|
|
|
def test_register_parser(tmp_path):
|
|
client = LocalClient(model="gpt-4o", storage_path=str(tmp_path / "pi"))
|
|
class FakeParser:
|
|
def supported_extensions(self): return [".txt"]
|
|
def parse(self, file_path, **kwargs): pass
|
|
client.register_parser(FakeParser())
|