RAG-POC/tests/conftest.py

59 lines
1.9 KiB
Python

from __future__ import annotations
import hashlib
from collections.abc import Sequence
from typing import Any
class FakeLLM:
chat_model = "fake-chat-model"
embedding_model = "fake-embedding-model"
def complete_json(self, system: str, user: str) -> dict[str, Any]:
if "community" in system.casefold():
return {
"title": "Atlas product community",
"summary": "Acme created Atlas, a graph retrieval product.",
}
return {
"entities": [
{
"canonical_name": "Acme",
"entity_type": "Organization",
"description": "Acme is a technology organization.",
"aliases": ["Acme Corp"],
},
{
"canonical_name": "Atlas",
"entity_type": "Product",
"description": "Atlas is a graph retrieval product.",
"aliases": [],
},
],
"relationships": [
{
"source": "Acme",
"target": "Atlas",
"relationship_type": "CREATED",
"description": "Acme created Atlas.",
}
],
}
def complete_text(self, system: str, user: str) -> str:
return "Acme created Atlas. [S1]"
def embed(self, texts: Sequence[str]) -> list[list[float]]:
vectors: list[list[float]] = []
for text in texts:
normalized = text.casefold()
digest = hashlib.sha256(normalized.encode("utf-8")).digest()
vectors.append(
[
float("atlas" in normalized),
float("acme" in normalized),
digest[0] / 255,
]
)
return vectors