mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-06-12 19:55:17 +02:00
fix(filesystem): restore summary vector search in cli
This commit is contained in:
parent
7e70b580f0
commit
fc0be1aeee
6 changed files with 147 additions and 3 deletions
|
|
@ -58,3 +58,60 @@ def test_semantic_search_scope_filters_explicit_source_type_facets():
|
|||
{"folder_path": "/documents"}
|
||||
) == {}
|
||||
|
||||
|
||||
def test_existing_summary_projection_index_configures_retrieval_backend(tmp_path, monkeypatch):
|
||||
from pageindex.filesystem import PageIndexFileSystem
|
||||
from pageindex.filesystem.semantic_index import SemanticIndexRecord, SQLiteVecSemanticIndex
|
||||
|
||||
workspace = tmp_path / "workspace"
|
||||
index_dir = workspace / "artifacts" / "projection_indexes"
|
||||
summary_index = SQLiteVecSemanticIndex(index_dir / "summary_only_vector.sqlite")
|
||||
summary_index.reset(
|
||||
dimension=3,
|
||||
metadata={
|
||||
"channel": "summary",
|
||||
"embedding_provider": "openai",
|
||||
"embedding_model": "test-embedding",
|
||||
"embedding_dimensions": 3,
|
||||
},
|
||||
)
|
||||
summary_index.upsert_many(
|
||||
[
|
||||
SemanticIndexRecord(
|
||||
file_ref="file_a",
|
||||
external_id="doc_a",
|
||||
source_type="documents",
|
||||
source_path="documents/a.pdf",
|
||||
title="A",
|
||||
text="summary",
|
||||
vector=[1.0, 0.0, 0.0],
|
||||
)
|
||||
]
|
||||
)
|
||||
filesystem = PageIndexFileSystem(workspace)
|
||||
calls = []
|
||||
|
||||
def fake_configure(index_dir_arg, **kwargs):
|
||||
calls.append((index_dir_arg, kwargs))
|
||||
filesystem.semantic_retrieval_backend = SummaryBackend("doc_a")
|
||||
return filesystem.semantic_retrieval_backend
|
||||
|
||||
monkeypatch.setattr(
|
||||
filesystem,
|
||||
"configure_hybrid_projection_retrieval",
|
||||
fake_configure,
|
||||
)
|
||||
|
||||
assert filesystem.configure_existing_projection_retrieval() is True
|
||||
assert calls == [
|
||||
(
|
||||
filesystem.summary_projection_index_dir,
|
||||
{
|
||||
"embedding_provider": "openai",
|
||||
"embedding_model": "test-embedding",
|
||||
"embedding_dimensions": 3,
|
||||
"embedding_timeout": 60,
|
||||
},
|
||||
)
|
||||
]
|
||||
assert filesystem.semantic_retrieval_channels() == ("summary",)
|
||||
|
|
|
|||
|
|
@ -204,6 +204,11 @@ class PIFSAgentStreamTest(unittest.TestCase):
|
|||
self.assertIn("do not infer metadata presence or absence", AGENT_TOOL_POLICY)
|
||||
self.assertIn("questions about metadata fields", BASH_TOOL_DESCRIPTION)
|
||||
|
||||
def test_prompt_routes_summary_search_to_search_summary(self):
|
||||
self.assertIn("search-summary when the user asks for", BASH_TOOL_DESCRIPTION)
|
||||
self.assertIn("use search-summary <query> <folder>", AGENT_TOOL_POLICY)
|
||||
self.assertIn("do not translate that request into find --where", AGENT_TOOL_POLICY)
|
||||
|
||||
def test_system_prompt_sets_workspace_identity_and_scope(self):
|
||||
self.assertIn("PageIndex FileSystem Demo Agent", AGENT_SYSTEM_PROMPT)
|
||||
self.assertIn("VectifyAI Team", AGENT_SYSTEM_PROMPT)
|
||||
|
|
|
|||
|
|
@ -5,6 +5,24 @@ from pathlib import Path
|
|||
class FakeFileSystem:
|
||||
def __init__(self, workspace):
|
||||
self.workspace = Path(workspace)
|
||||
self.projection_retrieval_configured = False
|
||||
|
||||
def configure_existing_projection_retrieval(self):
|
||||
self.projection_retrieval_configured = True
|
||||
return True
|
||||
|
||||
|
||||
def test_cli_workspace_configures_existing_projection_retrieval(monkeypatch, tmp_path):
|
||||
from pageindex.filesystem import cli
|
||||
|
||||
workspace = tmp_path / "workspace"
|
||||
|
||||
monkeypatch.setattr(cli, "PageIndexFileSystem", FakeFileSystem)
|
||||
|
||||
filesystem = cli._filesystem_from_workspace(str(workspace))
|
||||
|
||||
assert filesystem.workspace == workspace
|
||||
assert filesystem.projection_retrieval_configured is True
|
||||
|
||||
|
||||
def test_cli_passthrough_invokes_pifs_command_executor(monkeypatch, capsys, tmp_path):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue