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

Rename EMBDEDDING->EMBEDDINGS in env vars

Browse source
This commit is contained in:
Yiorgis Gozadinos 2025-06-19 17:44:42 +02:00
parent d89b2f1306
commit 943cf3c5e0
No known key found for this signature in database
7 changed files with 26 additions and 26 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

18
README.md
View file

@ -27,24 +27,24 @@ If you want to use an alternative embeddings provider (Ollama being the default)
By default:
```bash
EMBEDDING_PROVIDER="ollama"
EMBEDDING_MODEL="mxbai-embed-large" # or any other model
EMBEDDING_VECTOR_DIM=1024
EMBEDDINGS_PROVIDER="ollama"
EMBEDDINGS_MODEL="mxbai-embed-large" # or any other model
EMBEDDINGS_VECTOR_DIM=1024
```
For VoyageAI:
```bash
EMBEDDING_PROVIDER="voyageai"
EMBEDDING_MODEL="voyage-3.5" # or any other model
EMBEDDING_VECTOR_DIM=1024
EMBEDDINGS_PROVIDER="voyageai"
EMBEDDINGS_MODEL="voyage-3.5" # or any other model
EMBEDDINGS_VECTOR_DIM=1024
VOYAGE_API_KEY="your-api-key"
```
For OpenAI:
```bash
EMBEDDING_PROVIDER="openai"
EMBEDDING_MODEL="text-embedding-3-small" # or text-embedding-3-large
EMBEDDING_VECTOR_DIM=1536
EMBEDDINGS_PROVIDER="openai"
EMBEDDINGS_MODEL="text-embedding-3-small" # or text-embedding-3-large
EMBEDDINGS_VECTOR_DIM=1536
OPENAI_API_KEY="your-api-key"
```

6
src/haiku/rag/config.py
View file

@ -14,9 +14,9 @@ class AppConfig(BaseModel):
DEFAULT_DATA_DIR: Path = get_default_data_dir()
EMBEDDING_PROVIDER: str = "ollama"
EMBEDDING_MODEL: str = "mxbai-embed-large"
EMBEDDING_VECTOR_DIM: int = 1024
EMBEDDINGS_PROVIDER: str = "ollama"
EMBEDDINGS_MODEL: str = "mxbai-embed-large"
EMBEDDINGS_VECTOR_DIM: int = 1024
CHUNK_SIZE: int = 256
CHUNK_OVERLAP: int = 32

14
src/haiku/rag/embeddings/__init__.py
View file

@ -8,10 +8,10 @@ def get_embedder() -> EmbedderBase:
Factory function to get the appropriate embedder based on the configuration.
"""
if Config.EMBEDDING_PROVIDER == "ollama":
return OllamaEmbedder(Config.EMBEDDING_MODEL, Config.EMBEDDING_VECTOR_DIM)
if Config.EMBEDDINGS_PROVIDER == "ollama":
return OllamaEmbedder(Config.EMBEDDINGS_MODEL, Config.EMBEDDINGS_VECTOR_DIM)
if Config.EMBEDDING_PROVIDER == "voyageai":
if Config.EMBEDDINGS_PROVIDER == "voyageai":
try:
from haiku.rag.embeddings.voyageai import Embedder as VoyageAIEmbedder
except ImportError:
@ -20,9 +20,9 @@ def get_embedder() -> EmbedderBase:
"Please install haiku.rag with the 'voyageai' extra:"
"uv pip install haiku.rag --extra voyageai"
)
return VoyageAIEmbedder(Config.EMBEDDING_MODEL, Config.EMBEDDING_VECTOR_DIM)
return VoyageAIEmbedder(Config.EMBEDDINGS_MODEL, Config.EMBEDDINGS_VECTOR_DIM)
if Config.EMBEDDING_PROVIDER == "openai":
if Config.EMBEDDINGS_PROVIDER == "openai":
try:
from haiku.rag.embeddings.openai import Embedder as OpenAIEmbedder
except ImportError:
@ -31,6 +31,6 @@ def get_embedder() -> EmbedderBase:
"Please install haiku.rag with the 'openai' extra:"
"uv pip install haiku.rag --extra openai"
)
return OpenAIEmbedder(Config.EMBEDDING_MODEL, Config.EMBEDDING_VECTOR_DIM)
return OpenAIEmbedder(Config.EMBEDDINGS_MODEL, Config.EMBEDDINGS_VECTOR_DIM)
raise ValueError(f"Unsupported embedding provider: {Config.EMBEDDING_PROVIDER}")
raise ValueError(f"Unsupported embedding provider: {Config.EMBEDDINGS_PROVIDER}")

2
src/haiku/rag/embeddings/ollama.py
View file

@ -5,7 +5,7 @@ from haiku.rag.embeddings.base import EmbedderBase
class Embedder(EmbedderBase):
_model: str = Config.EMBEDDING_MODEL
_model: str = Config.EMBEDDINGS_MODEL
_vector_dim: int = 1024
async def embed(self, text: str) -> list[float]:

2
src/haiku/rag/embeddings/openai.py
View file

@ -5,7 +5,7 @@ try:
from haiku.rag.embeddings.base import EmbedderBase
class Embedder(EmbedderBase):
_model: str = Config.EMBEDDING_MODEL
_model: str = Config.EMBEDDINGS_MODEL
_vector_dim: int = 1536
async def embed(self, text: str) -> list[float]:

2
src/haiku/rag/embeddings/voyageai.py
View file

@ -5,7 +5,7 @@ try:
from haiku.rag.embeddings.base import EmbedderBase
class Embedder(EmbedderBase):
_model: str = Config.EMBEDDING_MODEL
_model: str = Config.EMBEDDINGS_MODEL
_vector_dim: int = 1024
async def embed(self, text: str) -> list[float]:

8
tests/test_embedder.py
View file

@ -50,8 +50,8 @@ async def test_similarity():
@pytest.mark.asyncio
async def test_openai_embedder(monkeypatch):
monkeypatch.setenv("EMBEDDING_PROVIDER", "openai")
monkeypatch.setenv("EMBEDDING_MODEL", "text-embedding-3-small")
monkeypatch.setenv("EMBEDDINGS_PROVIDER", "openai")
monkeypatch.setenv("EMBEDDINGS_MODEL", "text-embedding-3-small")
try:
from haiku.rag.embeddings.openai import Embedder as OpenAIEmbedder
@ -94,8 +94,8 @@ async def test_openai_embedder(monkeypatch):
@pytest.mark.asyncio
async def test_voyageai_embedder(monkeypatch):
monkeypatch.setenv("EMBEDDING_PROVIDER", "voyageai")
monkeypatch.setenv("EMBEDDING_MODEL", "voyage-3.5")
monkeypatch.setenv("EMBEDDINGS_PROVIDER", "voyageai")
monkeypatch.setenv("EMBEDDINGS_MODEL", "voyage-3.5")
try:
from haiku.rag.embeddings.voyageai import Embedder as VoyageAIEmbedder