fix: use HuggingFaceEmbeddingFunction for embeddings, update keys and add tests (#4005)

lib/crewai/src/crewai/rag/embeddings/providers/huggingface/huggingface_provider.py

@@ -1,21 +1,35 @@
 """HuggingFace embeddings provider."""
 
 from chromadb.utils.embedding_functions.huggingface_embedding_function import (
-    HuggingFaceEmbeddingServer,
+    HuggingFaceEmbeddingFunction,
 )
 from pydantic import AliasChoices, Field
 
 from crewai.rag.core.base_embeddings_provider import BaseEmbeddingsProvider
 
 
-class HuggingFaceProvider(BaseEmbeddingsProvider[HuggingFaceEmbeddingServer]):
-    """HuggingFace embeddings provider."""
+class HuggingFaceProvider(BaseEmbeddingsProvider[HuggingFaceEmbeddingFunction]):
+    """HuggingFace embeddings provider for the HuggingFace Inference API."""
 
-    embedding_callable: type[HuggingFaceEmbeddingServer] = Field(
-        default=HuggingFaceEmbeddingServer,
+    embedding_callable: type[HuggingFaceEmbeddingFunction] = Field(
+        default=HuggingFaceEmbeddingFunction,
         description="HuggingFace embedding function class",
     )
-    url: str = Field(
-        description="HuggingFace API URL",
-        validation_alias=AliasChoices("EMBEDDINGS_HUGGINGFACE_URL", "HUGGINGFACE_URL"),
+    api_key: str | None = Field(
+        default=None,
+        description="HuggingFace API key",
+        validation_alias=AliasChoices(
+            "EMBEDDINGS_HUGGINGFACE_API_KEY",
+            "HUGGINGFACE_API_KEY",
+            "HF_TOKEN",
+        ),
+    )
+    model_name: str = Field(
+        default="sentence-transformers/all-MiniLM-L6-v2",
+        description="Model name to use for embeddings",
+        validation_alias=AliasChoices(
+            "EMBEDDINGS_HUGGINGFACE_MODEL_NAME",
+            "HUGGINGFACE_MODEL_NAME",
+            "model",
+        ),
     )

lib/crewai/src/crewai/rag/embeddings/providers/huggingface/types.py

@@ -1,6 +1,6 @@
 """Type definitions for HuggingFace embedding providers."""
 
-from typing import Literal
+from typing import Annotated, Literal
 
 from typing_extensions import Required, TypedDict
 
@@ -8,7 +8,11 @@ from typing_extensions import Required, TypedDict
 class HuggingFaceProviderConfig(TypedDict, total=False):
     """Configuration for HuggingFace provider."""
 
-    url: str
+    api_key: str
+    model: Annotated[
+        str, "sentence-transformers/all-MiniLM-L6-v2"
+    ]  # alias for model_name for backward compat
+    model_name: Annotated[str, "sentence-transformers/all-MiniLM-L6-v2"]
 
 
 class HuggingFaceProviderSpec(TypedDict, total=False):