Load .env in evals

evaluations/evaluations/benchmark.py

@@ -5,6 +5,7 @@ from typing import Any, cast
 
 import logfire
 import typer
+from dotenv import load_dotenv
 from pydantic_ai.models.openai import OpenAIChatModel
 from pydantic_ai.providers.ollama import OllamaProvider
 from pydantic_evals import Dataset as EvalDataset
@@ -22,6 +23,8 @@ from haiku.rag.config import AppConfig, find_config_file, load_yaml_config
 from haiku.rag.logging import configure_cli_logging
 from haiku.rag.qa import get_qa_agent
 
+load_dotenv()
+
 QA_JUDGE_MODEL = "qwen3"
 
 logfire.configure(send_to_logfire="if-token-present", service_name="evals")

evaluations/pyproject.toml

@@ -12,6 +12,7 @@ dependencies = [
     "pydantic-ai-slim[evals,logfire]>=1.11.0",
     "datasets>=4.3.0",
     "typer>=0.19.2,<0.20.0",
+    "python-dotenv>=1.0.1",
 ]
 
 [build-system]

uv.lock

@@ -1179,6 +1179,7 @@ dependencies = [
     { name = "datasets" },
     { name = "haiku-rag-slim" },
     { name = "pydantic-ai-slim", extra = ["evals", "logfire"] },
+    { name = "python-dotenv" },
     { name = "typer" },
 ]
 
@@ -1187,6 +1188,7 @@ requires-dist = [
     { name = "datasets", specifier = ">=4.3.0" },
     { name = "haiku-rag-slim", editable = "haiku_rag_slim" },
     { name = "pydantic-ai-slim", extras = ["evals", "logfire"], specifier = ">=1.11.0" },
+    { name = "python-dotenv", specifier = ">=1.0.1" },
     { name = "typer", specifier = ">=0.19.2,<0.20.0" },
 ]