Adding model_kwargs for huggingface embedders. (#1450)

embedchain/config/embedder/base.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Any, Dict, Optional
 
 from embedchain.helpers.json_serializable import register_deserializable
 
@@ -13,6 +13,7 @@ class BaseEmbedderConfig:
         endpoint: Optional[str] = None,
         api_key: Optional[str] = None,
         api_base: Optional[str] = None,
+        model_kwargs: Optional[Dict[str, Any]] = None,
     ):
         """
         Initialize a new instance of an embedder config class.
@@ -29,6 +30,8 @@ class BaseEmbedderConfig:
         :type api_key: Optional[str], optional
         :param api_base: huggingface api base, defaults to None
         :type api_base: Optional[str], optional
+        :param model_kwargs: key-value arguments for the embedding model, defaults a dict inside init.
+        :type model_kwargs: Optional[Dict[str, Any]], defaults a dict inside init.
         """
         self.model = model
         self.deployment_name = deployment_name
@@ -36,3 +39,4 @@ class BaseEmbedderConfig:
         self.endpoint = endpoint
         self.api_key = api_key
         self.api_base = api_base
+        self.model_kwargs = model_kwargs or {}

embedchain/embedder/huggingface.py

@@ -31,7 +31,8 @@ class HuggingFaceEmbedder(BaseEmbedder):
                 huggingfacehub_api_token=self.config.api_key or os.getenv("HUGGINGFACE_ACCESS_TOKEN"),
             )
         else:
-            embeddings = HuggingFaceEmbeddings(model_name=self.config.model)
+            embeddings = HuggingFaceEmbeddings(model_name=self.config.model, model_kwargs=self.config.model_kwargs)
+
         embedding_fn = BaseEmbedder._langchain_default_concept(embeddings)
         self.set_embedding_fn(embedding_fn=embedding_fn)
 

embedchain/utils/misc.py

@@ -474,6 +474,7 @@ def validate_config(config_data):
                     Optional("vector_dimension"): int,
                     Optional("base_url"): str,
                     Optional("endpoint"): str,
+                    Optional("model_kwargs"): dict,
                 },
             },
             Optional("embedding_model"): {