mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-05-19 18:35:16 +02:00
feat(collection): doc_ids accepts str|list, design cleanups
- 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.
This commit is contained in:
parent
d7b36aaf3f
commit
a47c36a3f5
13 changed files with 322 additions and 45 deletions
|
|
@ -111,7 +111,8 @@ def test_wrap_with_doc_context_single(populated_backend):
|
|||
docs = populated_backend._scoped_docs("papers", ["d1"])
|
||||
wrapped = wrap_with_doc_context(docs, "what is this?")
|
||||
assert "d1: alpha.pdf — About alpha." in wrapped
|
||||
assert "specified the following document:" in wrapped
|
||||
assert "specified the following document" in wrapped
|
||||
assert "<docs>" in wrapped and "</docs>" in wrapped
|
||||
assert "User question: what is this?" in wrapped
|
||||
|
||||
|
||||
|
|
@ -121,10 +122,22 @@ def test_wrap_with_doc_context_multi(populated_backend):
|
|||
wrapped = wrap_with_doc_context(docs, "compare them")
|
||||
assert "d1: alpha.pdf — About alpha." in wrapped
|
||||
assert "d2: beta.pdf — About beta." in wrapped
|
||||
assert "specified the following documents:" in wrapped
|
||||
assert "specified the following documents" in wrapped
|
||||
assert "<docs>" in wrapped and "</docs>" in wrapped
|
||||
assert "User question: compare them" in wrapped
|
||||
|
||||
|
||||
def test_scoped_docs_raises_on_missing(populated_backend):
|
||||
with pytest.raises(DocumentNotFoundError, match="nonexistent"):
|
||||
populated_backend._scoped_docs("papers", ["d1", "nonexistent"])
|
||||
|
||||
|
||||
def test_normalize_doc_ids():
|
||||
assert LocalBackend._normalize_doc_ids("d1") == ["d1"]
|
||||
assert LocalBackend._normalize_doc_ids(["d1", "d2"]) == ["d1", "d2"]
|
||||
assert LocalBackend._normalize_doc_ids(None) is None
|
||||
|
||||
|
||||
def test_normalize_doc_ids_rejects_empty_list():
|
||||
with pytest.raises(ValueError, match="cannot be empty"):
|
||||
LocalBackend._normalize_doc_ids([])
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue