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

Remove deprecated use of env variables for configuration

Browse source
This commit is contained in:
Yiorgis Gozadinos 2025-11-07 10:54:32 +02:00
parent b51283c647
commit 0b696d9629
No known key found for this signature in database
6 changed files with 34 additions and 157 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
CHANGELOG.md
View file

@ -9,6 +9,10 @@
- Updated CLI documentation to clarify global vs per-command options
- **BREAKING**: Standardized configuration filename to `haiku.rag.yaml` in user directories (was incorrectly using `config.yaml`). Users with existing `config.yaml` in their user directory will need to rename it to `haiku.rag.yaml`
### Removed
- **BREAKING**: Removed deprecated `.env`-based configuration system. The `haiku-rag init-config --from-env` command and `load_config_from_env()` function have been removed. All configuration must now be done via YAML files. Environment variables for API keys (e.g., `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`) and service URLs (e.g., `OLLAMA_BASE_URL`) are still supported and can be set via `.env` files.
## [0.14.1] - 2025-11-06
### Added

29
docs/configuration.md
View file

@ -15,15 +15,6 @@ haiku-rag init-config
This creates a `haiku.rag.yaml` file in your current directory with all available settings.
!!! warning "Deprecation Notice"
Environment variable configuration via `.env` files is deprecated and will be removed in future versions. Please migrate to YAML configuration.
To migrate from environment variables (`.env` file):
```bash
haiku-rag init-config --from-env
```
## Configuration File Locations
`haiku.rag` searches for configuration files in this order:
@ -219,14 +210,7 @@ embeddings:
vector_dim: 1024
```
The Ollama base URL can be configured via environment variable or config file:
```bash
# Via environment variable (recommended)
export OLLAMA_BASE_URL=http://localhost:11434
```
Or in your config file:
The Ollama base URL can be configured in your config file or via environment variable:
```yaml
providers:
@ -234,7 +218,16 @@ providers:
base_url: http://localhost:11434
```
If neither is set, it defaults to `http://localhost:11434`.
Or via environment variable:
```bash
export OLLAMA_BASE_URL=http://localhost:11434
```
If not configured, it defaults to `http://localhost:11434`.
!!! note
You can use a `.env` file in your project directory to set environment variables like `OLLAMA_BASE_URL` and API keys (e.g., `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`). These will be automatically loaded when running `haiku-rag` commands.
### VoyageAI

34
haiku_rag_slim/haiku/rag/cli.py
View file

@ -6,14 +6,7 @@ from pathlib import Path
from typing import Any
import typer
# Load environment variables from .env file before importing Config
try:
from dotenv import load_dotenv
load_dotenv()
except ImportError:
pass
from dotenv import load_dotenv
from haiku.rag.app import HaikuRAGApp
from haiku.rag.config import (
@ -26,6 +19,9 @@ from haiku.rag.config import (
from haiku.rag.logging import configure_cli_logging
from haiku.rag.utils import is_up_to_date
# Load environment variables from .env file for API keys and service URLs
load_dotenv()
cli = typer.Typer(
context_settings={"help_option_names": ["-h", "--help"]}, no_args_is_help=True
)
@ -326,16 +322,11 @@ def init_config(
Path("haiku.rag.yaml"),
help="Output path for the config file",
),
from_env: bool = typer.Option(
False,
"--from-env",
help="Migrate settings from .env file",
),
):
"""Generate a YAML configuration file with defaults or from .env."""
"""Generate a YAML configuration file with defaults."""
import yaml
from haiku.rag.config.loader import generate_default_config, load_config_from_env
from haiku.rag.config.loader import generate_default_config
if output.exists():
typer.echo(
@ -343,18 +334,7 @@ def init_config(
)
raise typer.Exit(1)
if from_env:
# Load from environment variables (including .env if present)
from dotenv import load_dotenv
load_dotenv()
config_data = load_config_from_env()
if not config_data:
typer.echo("Warning: No environment variables found to migrate.")
typer.echo("Generating default configuration instead.")
config_data = generate_default_config()
else:
config_data = generate_default_config()
config_data = generate_default_config()
# Write YAML with comments
with open(output, "w") as f:

2
haiku_rag_slim/haiku/rag/config/__init__.py
View file

@ -3,7 +3,6 @@ import os
from haiku.rag.config.loader import (
find_config_file,
generate_default_config,
load_config_from_env,
load_yaml_config,
)
from haiku.rag.config.models import (
@ -40,7 +39,6 @@ __all__ = [
"find_config_file",
"load_yaml_config",
"generate_default_config",
"load_config_from_env",
"get_config",
"set_config",
]

56
haiku_rag_slim/haiku/rag/config/loader.py
View file

@ -86,59 +86,3 @@ def generate_default_config() -> dict:
},
"a2a": {"max_contexts": 1000},
}
def load_config_from_env() -> dict:
"""Load current config from environment variables (for migration)."""
result = {}
env_mappings = {
"ENV": "environment",
"DEFAULT_DATA_DIR": ("storage", "data_dir"),
"MONITOR_DIRECTORIES": ("monitor", "directories"),
"DISABLE_DB_AUTOCREATE": ("storage", "disable_autocreate"),
"VACUUM_RETENTION_SECONDS": ("storage", "vacuum_retention_seconds"),
"LANCEDB_URI": ("lancedb", "uri"),
"LANCEDB_API_KEY": ("lancedb", "api_key"),
"LANCEDB_REGION": ("lancedb", "region"),
"EMBEDDINGS_PROVIDER": ("embeddings", "provider"),
"EMBEDDINGS_MODEL": ("embeddings", "model"),
"EMBEDDINGS_VECTOR_DIM": ("embeddings", "vector_dim"),
"RERANK_PROVIDER": ("reranking", "provider"),
"RERANK_MODEL": ("reranking", "model"),
"QA_PROVIDER": ("qa", "provider"),
"QA_MODEL": ("qa", "model"),
"RESEARCH_PROVIDER": ("research", "provider"),
"RESEARCH_MODEL": ("research", "model"),
"CHUNK_SIZE": ("processing", "chunk_size"),
"CONTEXT_CHUNK_RADIUS": ("processing", "context_chunk_radius"),
"MARKDOWN_PREPROCESSOR": ("processing", "markdown_preprocessor"),
"OLLAMA_BASE_URL": ("providers", "ollama", "base_url"),
"VLLM_EMBEDDINGS_BASE_URL": ("providers", "vllm", "embeddings_base_url"),
"VLLM_RERANK_BASE_URL": ("providers", "vllm", "rerank_base_url"),
"VLLM_QA_BASE_URL": ("providers", "vllm", "qa_base_url"),
"VLLM_RESEARCH_BASE_URL": ("providers", "vllm", "research_base_url"),
"A2A_MAX_CONTEXTS": ("a2a", "max_contexts"),
}
for env_var, path in env_mappings.items():
value = os.getenv(env_var)
if value is not None:
# Special handling for MONITOR_DIRECTORIES - parse comma-separated list
if env_var == "MONITOR_DIRECTORIES":
if value.strip():
value = [p.strip() for p in value.split(",") if p.strip()]
else:
value = []
if isinstance(path, tuple):
current = result
for key in path[:-1]:
if key not in current:
current[key] = {}
current = current[key]
current[path[-1]] = value
else:
result[path] = value
return result

66
tests/test_config_loader.py
View file

@ -1,11 +1,8 @@
import os
import pytest
from haiku.rag.config.loader import (
find_config_file,
generate_default_config,
load_config_from_env,
load_yaml_config,
)
@ -50,7 +47,7 @@ def test_find_config_file_user_config(tmp_path, monkeypatch):
"haiku.rag.utils.get_default_data_dir", mock_get_default_data_dir
)
config_file = tmp_path / "config.yaml"
config_file = tmp_path / "haiku.rag.yaml"
config_file.write_text("environment: production")
found = find_config_file()
@ -114,68 +111,29 @@ def test_generate_default_config():
assert config["embeddings"]["vector_dim"] == 4096
def test_load_config_from_env(monkeypatch):
"""Test loading config from environment variables."""
monkeypatch.setenv("ENV", "development")
monkeypatch.setenv("EMBEDDINGS_PROVIDER", "openai")
monkeypatch.setenv("EMBEDDINGS_MODEL", "text-embedding-3-small")
monkeypatch.setenv("EMBEDDINGS_VECTOR_DIM", "1536")
monkeypatch.setenv("QA_PROVIDER", "anthropic")
monkeypatch.setenv("QA_MODEL", "claude-3-haiku")
config = load_config_from_env()
assert config["environment"] == "development"
assert config["embeddings"]["provider"] == "openai"
assert config["embeddings"]["model"] == "text-embedding-3-small"
assert config["embeddings"]["vector_dim"] == "1536"
assert config["qa"]["provider"] == "anthropic"
assert config["qa"]["model"] == "claude-3-haiku"
def test_load_config_from_env_empty():
"""Test loading from env when no relevant vars set."""
# Clear any env vars that might be set
env_vars = [
"ENV",
"EMBEDDINGS_PROVIDER",
"QA_PROVIDER",
"OPENAI_API_KEY",
]
original_values = {}
for var in env_vars:
original_values[var] = os.environ.get(var)
if var in os.environ:
del os.environ[var]
try:
config = load_config_from_env()
# Should return empty or minimal dict
assert isinstance(config, dict)
finally:
# Restore original values
for var, value in original_values.items():
if value is not None:
os.environ[var] = value
def test_config_precedence_cwd_over_user(tmp_path, monkeypatch):
"""Test that cwd config takes precedence over user config."""
monkeypatch.chdir(tmp_path)
# Create separate directories for cwd and user config
cwd_dir = tmp_path / "cwd"
cwd_dir.mkdir()
user_dir = tmp_path / "user"
user_dir.mkdir()
# Mock get_default_data_dir to return tmp_path
monkeypatch.chdir(cwd_dir)
# Mock get_default_data_dir to return user_dir
def mock_get_default_data_dir():
return tmp_path
return user_dir
monkeypatch.setattr(
"haiku.rag.utils.get_default_data_dir", mock_get_default_data_dir
)
# Create both configs
cwd_config = tmp_path / "haiku.rag.yaml"
cwd_config = cwd_dir / "haiku.rag.yaml"
cwd_config.write_text("environment: from-cwd")
user_config = tmp_path / "config.yaml"
user_config = user_dir / "haiku.rag.yaml"
user_config.write_text("environment: from-user")
found = find_config_file()