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

Remove provider API keys from config, rely on environment variables for those

Browse source
This commit is contained in:
Yiorgis Gozadinos 2025-10-23 13:50:28 +03:00
parent 618b3ffd5f
commit 469d993542
No known key found for this signature in database
9 changed files with 56 additions and 56 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

64
docs/configuration.md
View file

@ -98,16 +98,28 @@ providers:
qa_base_url: ""
research_base_url: ""
api_keys:
voyage: ""
openai: ""
anthropic: ""
cohere: ""
a2a:
max_contexts: 1000
```
## API Keys
API keys are configured through **environment variables**, not in the YAML file.
```bash
# OpenAI
export OPENAI_API_KEY=your-key-here
# Anthropic
export ANTHROPIC_API_KEY=your-key-here
# Voyage AI
export VOYAGE_API_KEY=your-key-here
# Cohere
export CO_API_KEY=your-key-here
```
## File Monitoring
Set directories to monitor for automatic indexing:
@ -145,10 +157,12 @@ embeddings:
provider: voyageai
model: voyage-3.5
vector_dim: 1024
```
providers:
api_keys:
voyage: your-api-key
Set your API key via environment variable:
```bash
export VOYAGE_API_KEY=your-api-key
```
### OpenAI
@ -160,10 +174,12 @@ embeddings:
provider: openai
model: text-embedding-3-small # or text-embedding-3-large
vector_dim: 1536
```
providers:
api_keys:
openai: your-api-key
Set your API key via environment variable:
```bash
export OPENAI_API_KEY=your-api-key
```
### vLLM
@ -207,10 +223,12 @@ OpenAI QA is included in the default installation:
qa:
provider: openai
model: gpt-4o-mini # or gpt-4, gpt-3.5-turbo, etc.
```
providers:
api_keys:
openai: your-api-key
Set your API key via environment variable:
```bash
export OPENAI_API_KEY=your-api-key
```
### Anthropic
@ -221,10 +239,12 @@ Anthropic QA is included in the default installation:
qa:
provider: anthropic
model: claude-3-5-haiku-20241022 # or claude-3-5-sonnet-20241022, etc.
```
providers:
api_keys:
anthropic: your-api-key
Set your API key via environment variable:
```bash
export ANTHROPIC_API_KEY=your-api-key
```
### vLLM
@ -296,10 +316,12 @@ Cohere reranking is included in the default installation:
reranking:
provider: cohere
model: rerank-v3.5
```
providers:
api_keys:
cohere: your-api-key
Set your API key via environment variable:
```bash
export CO_API_KEY=your-api-key
```
### vLLM

13
src/haiku/rag/config/__init__.py
View file

@ -9,7 +9,6 @@ from haiku.rag.config.loader import (
)
from haiku.rag.config.models import (
A2AConfig,
APIKeysConfig,
AppConfig,
EmbeddingsConfig,
LanceDBConfig,
@ -35,7 +34,6 @@ __all__ = [
"ProcessingConfig",
"OllamaConfig",
"VLLMConfig",
"APIKeysConfig",
"ProvidersConfig",
"A2AConfig",
"find_config_file",
@ -54,14 +52,3 @@ else:
# Check for deprecated .env file
check_for_deprecated_env()
# Export API keys to os.environ for provider libraries
if Config.providers.api_keys.openai:
os.environ["OPENAI_API_KEY"] = Config.providers.api_keys.openai
if Config.providers.api_keys.voyage:
os.environ["VOYAGE_API_KEY"] = Config.providers.api_keys.voyage
if Config.providers.api_keys.anthropic:
os.environ["ANTHROPIC_API_KEY"] = Config.providers.api_keys.anthropic
if Config.providers.api_keys.cohere:
# Cohere SDK expects CO_API_KEY (not COHERE_API_KEY)
os.environ["CO_API_KEY"] = Config.providers.api_keys.cohere

5
src/haiku/rag/config/loader.py
View file

@ -90,7 +90,6 @@ def generate_default_config() -> dict:
"qa_base_url": "",
"research_base_url": "",
},
"api_keys": {"voyage": "", "openai": "", "anthropic": "", "cohere": ""},
},
"a2a": {"max_contexts": 1000},
}
@ -126,10 +125,6 @@ def load_config_from_env() -> dict:
"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"),
"VOYAGE_API_KEY": ("providers", "api_keys", "voyage"),
"OPENAI_API_KEY": ("providers", "api_keys", "openai"),
"ANTHROPIC_API_KEY": ("providers", "api_keys", "anthropic"),
"COHERE_API_KEY": ("providers", "api_keys", "cohere"),
"A2A_MAX_CONTEXTS": ("a2a", "max_contexts"),
}

8
src/haiku/rag/config/models.py
View file

@ -56,17 +56,9 @@ class VLLMConfig(BaseModel):
research_base_url: str = ""
class APIKeysConfig(BaseModel):
voyage: str = ""
openai: str = ""
anthropic: str = ""
cohere: str = ""
class ProvidersConfig(BaseModel):
ollama: OllamaConfig = Field(default_factory=OllamaConfig)
vllm: VLLMConfig = Field(default_factory=VLLMConfig)
api_keys: APIKeysConfig = Field(default_factory=APIKeysConfig)
class A2AConfig(BaseModel):

4
src/haiku/rag/reranking/cohere.py
View file

@ -1,4 +1,3 @@
from haiku.rag.config import Config
from haiku.rag.reranking.base import RerankerBase
from haiku.rag.store.models.chunk import Chunk
@ -12,7 +11,8 @@ except ImportError as e:
class CohereReranker(RerankerBase):
def __init__(self):
self._client = cohere.ClientV2(api_key=Config.providers.api_keys.cohere)
# Cohere SDK reads CO_API_KEY from environment by default
self._client = cohere.ClientV2()
async def rerank(
self, query: str, chunks: list[Chunk], top_n: int = 10

2
tests/test_config_loader.py
View file

@ -112,7 +112,6 @@ def test_load_config_from_env(monkeypatch):
monkeypatch.setenv("EMBEDDINGS_VECTOR_DIM", "1536")
monkeypatch.setenv("QA_PROVIDER", "anthropic")
monkeypatch.setenv("QA_MODEL", "claude-3-haiku")
monkeypatch.setenv("OPENAI_API_KEY", "test-key")
config = load_config_from_env()
@ -122,7 +121,6 @@ def test_load_config_from_env(monkeypatch):
assert config["embeddings"]["vector_dim"] == "1536"
assert config["qa"]["provider"] == "anthropic"
assert config["qa"]["model"] == "claude-3-haiku"
assert config["providers"]["api_keys"]["openai"] == "test-key"
def test_load_config_from_env_empty():

6
tests/test_embedder.py
View file

@ -1,3 +1,5 @@
import os
import numpy as np
import pytest
@ -6,8 +8,8 @@ from haiku.rag.embeddings.ollama import Embedder as OllamaEmbedder
from haiku.rag.embeddings.openai import Embedder as OpenAIEmbedder
from haiku.rag.embeddings.vllm import Embedder as VLLMEmbedder
OPENAI_AVAILABLE = bool(Config.providers.api_keys.openai)
VOYAGEAI_AVAILABLE = bool(Config.providers.api_keys.voyage)
OPENAI_AVAILABLE = bool(os.getenv("OPENAI_API_KEY"))
VOYAGEAI_AVAILABLE = bool(os.getenv("VOYAGE_API_KEY"))
VLLM_EMBEDDINGS_AVAILABLE = bool(Config.providers.vllm.embeddings_base_url)

6
tests/test_qa.py
View file

@ -1,3 +1,5 @@
import os
import pytest
from datasets import Dataset
@ -6,8 +8,8 @@ from haiku.rag.client import HaikuRAG
from haiku.rag.config import Config
from haiku.rag.qa.agent import QuestionAnswerAgent
OPENAI_AVAILABLE = bool(Config.providers.api_keys.openai)
ANTHROPIC_AVAILABLE = bool(Config.providers.api_keys.anthropic)
OPENAI_AVAILABLE = bool(os.getenv("OPENAI_API_KEY"))
ANTHROPIC_AVAILABLE = bool(os.getenv("ANTHROPIC_API_KEY"))
VLLM_QA_AVAILABLE = bool(Config.providers.vllm.qa_base_url)

4
tests/test_reranker.py
View file

@ -1,3 +1,5 @@
import os
import pytest
from haiku.rag.config import Config
@ -5,7 +7,7 @@ from haiku.rag.reranking.base import RerankerBase
from haiku.rag.reranking.vllm import VLLMReranker
from haiku.rag.store.models.chunk import Chunk
COHERE_AVAILABLE = bool(Config.providers.api_keys.cohere)
COHERE_AVAILABLE = bool(os.getenv("CO_API_KEY"))
VLLM_RERANK_AVAILABLE = bool(Config.providers.vllm.rerank_base_url)
chunks = [