Used Embedding model through API

my_agent/utils/models_loader.py

@@ -1,16 +1,17 @@
 
 from langchain_groq import ChatGroq
 from sentence_transformers import SentenceTransformer
+from huggingface_hub import InferenceClient
 from huggingface_hub import login
 from dotenv import load_dotenv
 load_dotenv()
 import os
+import requests
 # from langchain_huggingface import HuggingFaceEndpoint
 os.environ['HUGGINGFACEHUB_ACCESS_TOKEN']=os.getenv('HUGGINGFACEHUB_ACCESS_TOKEN')
 login(os.environ['HUGGINGFACEHUB_ACCESS_TOKEN'])
 os.environ['GROQ_API_KEY']=os.getenv('GROQ_API_KEY')
 
-ST = SentenceTransformer("mixedbread-ai/mxbai-embed-large-v1")
 
 llm = ChatGroq(
     model="llama3-8b-8192",
@@ -21,6 +22,30 @@ llm = ChatGroq(
 
 )
 
+class HFEmbeddingAPI:
+    def __init__(self, api_url, token):
+        self.api_url = api_url
+        self.headers = {
+            "Authorization": f"Bearer {os.environ.get("HUGGINGFACEHUB_ACCESS_TOKEN")}",
+        }
+
+    def encode(self, texts):
+        if isinstance(texts, str):
+            texts = [texts]
+        response = requests.post(
+            self.api_url,
+            headers=self.headers,
+            json={"inputs": texts}
+        )
+        response.raise_for_status()
+        return response.json()
+
+# Instantiate your API-backed "SentenceTransformer"
+ST = HFEmbeddingAPI(
+    api_url="https://router.huggingface.co/hf-inference/models/mixedbread-ai/mxbai-embed-large-v1/pipeline/feature-extraction",
+    token="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"
+)
+