danvics/haiku.rag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

No need to have evaluations in the docker image

Browse source
This commit is contained in:
Yiorgis Gozadinos 2025-11-05 12:35:37 +02:00
parent ba8e503cb1
commit 009e529869
No known key found for this signature in database
2 changed files with 8 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

8
docker/Dockerfile
View file

@ -12,14 +12,14 @@ ENV UV_COMPILE_BYTECODE=1 \
# Copy workspace member directories first (needed for workspace resolution)
COPY pyproject.toml uv.lock ./
COPY haiku_rag_slim/pyproject.toml haiku_rag_slim/README.md haiku_rag_slim/LICENSE haiku_rag_slim/
COPY evaluations/pyproject.toml evaluations/
RUN --mount=type=cache,target=/root/.cache/uv \
uv sync --frozen --no-install-project
uv sync --frozen --no-install-project --no-dev
# Install the project itself
COPY . .
COPY haiku_rag_slim haiku_rag_slim/
COPY README.md LICENSE ./
RUN --mount=type=cache,target=/root/.cache/uv \
uv sync --frozen --no-editable
uv sync --frozen --no-editable --no-dev
# Final layer
FROM python:3.13-slim

8
evaluations/evaluations/benchmark.py
View file

@ -5,6 +5,10 @@ from typing import Any, cast
import logfire
import typer
from haiku.rag.client import HaikuRAG
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
from pydantic_ai.models.openai import OpenAIChatModel
from pydantic_ai.providers.ollama import OllamaProvider
from pydantic_evals import Dataset as EvalDataset
@ -17,10 +21,6 @@ from evaluations.config import DatasetSpec
from evaluations.datasets import DATASETS
from evaluations.llm_judge import ANSWER_EQUIVALENCE_RUBRIC
from evaluations.prompts import WIX_SUPPORT_PROMPT
from haiku.rag.client import HaikuRAG
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
QA_JUDGE_MODEL = "qwen3"