ProfessorNovaandClaude Opus 5
784b76baf7
Self-hosted knowledge management for SMEs: a split-screen Markdown editor whose sections an LLM refines while you write, and RAG question answering over the documents that result. FastAPI + Postgres/pgvector on the back, SvelteKit on the front, everything OpenAI-compatible and self-hostable. Squashed into a single commit; the development history stays local. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CA43ZJda8Rbp2hKXNy8f6b
25 lines
822 B
Python
25 lines
822 B
Python
"""Deterministic fake embeddings for indexing/retrieval tests.
|
|
|
|
Identical text maps to an identical unit vector (cosine distance 0);
|
|
unrelated texts land near-orthogonal. Semantics are exercised by the evals
|
|
against the real endpoint — these tests cover the SQL plumbing.
|
|
"""
|
|
|
|
import hashlib
|
|
import math
|
|
import random
|
|
|
|
from app.models import EMBEDDING_DIM
|
|
|
|
|
|
def deterministic_embedding(text: str) -> list[float]:
|
|
seed = hashlib.sha256(text.encode()).digest()
|
|
rng = random.Random(seed)
|
|
vector = [rng.uniform(-1.0, 1.0) for _ in range(EMBEDDING_DIM)]
|
|
norm = math.sqrt(sum(value * value for value in vector))
|
|
return [value / norm for value in vector]
|
|
|
|
|
|
async def fake_embed(texts: list[str], *, role: str = "embedding") -> list[list[float]]:
|
|
return [deterministic_embedding(text) for text in texts]
|