Fix authorization header setup logic in text embeddings inference (#19979)

Author: jeesonwang

llama-index-integrations/embeddings/llama-index-embeddings-text-embeddings-inference/llama_index/embeddings/text_embeddings_inference/base.py

@@ -100,9 +100,10 @@ async def _acall_api(self, texts: List[str]) -> List[List[float]]:
         headers = {"Content-Type": "application/json"}
         if self.auth_token is not None:
             if callable(self.auth_token):
-                headers["Authorization"] = self.auth_token(self.base_url)
+                auth_token = self.auth_token(self.base_url)
             else:
-                headers["Authorization"] = self.auth_token
+                auth_token = self.auth_token
+            headers["Authorization"] = f"Bearer {auth_token}"
         json_data = {"inputs": texts, "truncate": self.truncate_text}
 
         async with httpx.AsyncClient() as client:

llama-index-integrations/embeddings/llama-index-embeddings-text-embeddings-inference/pyproject.toml

@@ -26,7 +26,7 @@ dev = [
 
 [project]
 name = "llama-index-embeddings-text-embeddings-inference"
-version = "0.4.1"
+version = "0.4.2"
 description = "llama-index embeddings text embeddings inference integration"
 authors = [{name = "Your Name", email = "[email protected]"}]
 requires-python = ">=3.9,<4.0"