Files
aaronAI/scripts/test_retrieval.py
aaron 9e86297e2a api.py: tool-call retrieval, drop the keyword intent classifier
Removes classify_retrieval_intent and the type/folder filter parameters on
retrieve_context. The keyword classifier was the same anti-pattern as the
formatting-driven docx chunker: a heuristic that locks the user into specific
phrasings and fails silently on anything novel. A scope enum (personal /
library / conversations / memory) would have been the same heuristic in a
fancier wrapper — the categories themselves are mine, not Aaron's.

New shape: a retrieve_documents tool exposed to Claude. Tool takes a single
query argument; the model decides when to call it, what to search for, and
how many times per turn (multi-query falls out naturally for compound asks).
Pre-LLM retrieval is gone — memory still rides as ground truth in the prompt,
but corpus content is fetched on demand by the model with concrete queries
it crafts itself, not the user's raw phrasing.

retrieve_context is now pure: hybrid retrieval + cross-encoder rerank + dedup,
no filters. The reranker ranks, the model judges relevance. When ranking
fails (e.g. abstract instructional queries pulling philosophy books), the
right fix is a better reranker, not another query-time taxonomy. That work
is acknowledged but deferred.

System prompt updated to teach the model about the tool and to prefer
concrete tokens (named entities, project names, course codes) over abstract
phrasing when constructing search queries.
2026-05-19 23:05:25 +00:00

54 lines
1.7 KiB
Python

"""End-to-end test of retrieve_context with intent routing + reranking.
Avoids loading the full FastAPI app; replicates the chat-handler retrieval
call shape and prints classifier output + final ranked sources for each query.
"""
import os
import sys
from pathlib import Path
from dotenv import load_dotenv
load_dotenv(Path.home() / "aaronai" / ".env", override=True)
sys.path.insert(0, str(Path(__file__).parent))
# Stub anthropic so api.py import doesn't fail without the SDK loaded.
# We only need retrieve_context.
import types
sys.modules.setdefault("anthropic", types.ModuleType("anthropic"))
sys.modules["anthropic"].Anthropic = lambda **kw: None
# Same for whisper if present
if "faster_whisper" not in sys.modules:
sys.modules["faster_whisper"] = types.ModuleType("faster_whisper")
import importlib.util
spec = importlib.util.spec_from_file_location("api", Path(__file__).parent / "api.py")
api = importlib.util.module_from_spec(spec)
# Don't execute the whole module (it starts FastAPI). Instead, exec only definitions.
# Easier: just import the functions we need by exec'ing the file but catching errors.
try:
spec.loader.exec_module(api)
except Exception as e:
print(f"(continuing despite api.py side-effect error: {e})")
retrieve_context = api.retrieve_context
QUERIES = [
"write me a bio",
"my professional bio",
"Aaron Nelson CV consulting and design work",
"FWN3D consulting",
"syllabi I have taught",
"philosophy of teaching",
"Hudson Valley Additive Manufacturing Center",
"Aaron Nelson is an artist and educator working in additive manufacturing",
]
for q in QUERIES:
pieces, sources = retrieve_context(q)
print(f"\n=== {q!r} ===")
for i, src in enumerate(sources, 1):
print(f" {i}. {src}")