Fix HF endpoint returns blank for text-generation (#7386)

Description: Current `_call` function in the
`langchain.llms.HuggingFaceEndpoint` class truncates response when
`task=text-generation`. Same error discussed a few days ago on Hugging
Face: https://huggingface.co/tiiuae/falcon-40b-instruct/discussions/51
Issue: Fixes #7353 
Tag maintainer: @hwchase17 @baskaryan @hinthornw

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

langchain/llms/huggingface_endpoint.py

@@ -137,8 +137,10 @@ class HuggingFaceEndpoint(LLM):
                 f"Error raised by inference API: {generated_text['error']}"
             )
         if self.task == "text-generation":
-            # Text generation return includes the starter text.
-            text = generated_text[0]["generated_text"][len(prompt) :]
+            text = generated_text[0]["generated_text"]
+            # Remove prompt if included in generated text.
+            if text.startswith(prompt):
+                text = text[len(prompt) :]
         elif self.task == "text2text-generation":
             text = generated_text[0]["generated_text"]
         elif self.task == "summarization":

tests/integration_tests/vectorstores/test_pinecone.py

@@ -2,9 +2,9 @@ import importlib
 import os
 import time
 import uuid
-import numpy as np
 from typing import List
 
+import numpy as np
 import pinecone
 import pytest
 

tests/integration_tests/vectorstores/test_qdrant.py

@@ -1,8 +1,8 @@
 """Test Qdrant functionality."""
 import tempfile
 from typing import Callable, Optional
-import numpy as np
 
+import numpy as np
 import pytest
 from qdrant_client.http import models as rest