LLM-RAG- PMR BRANCH

[sarthh7777]

PS C:\Users\dell\Downloads\llmrag3> pytest -v
===================================================================== test session starts ======================================================================
platform win32 -- Python 3.13.2, pytest-8.3.5, pluggy-1.6.0
rootdir: C:\Users\dell\Downloads\llmrag3
configfile: pytest.ini
testpaths: tests
plugins: anyio-4.9.0, langsmith-0.4.1
collected 31 items

tests\test_basic.py .... [ 12%]
tests\test_chunking.py ... [ 22%]
tests\test_components.py ....... [ 45%]
tests\test_embedder.py . [ 48%]
tests\test_ingestion.py . [ 51%]
tests\test_pipeline.py ... [ 61%]
tests\test_simple.py ..... [ 77%]
tests\test_smoke.py ..... [ 93%]
tests\test_vector_store.py .. [100%]

================ 31 passed in 42.54s ================

TESTS SUCCESSFULL

[onestardao]

noticed you’ve got chunking and ingestion tests wired in — depending on how deep you go (esp. mixed format or cross-PDF), this layer tends to hit early semantic collapse.
we’ve dealt with it head-on in our own engine — feel free to reach out if you want to compare patterns or failure modes.