Bagatur/from texts bug fix (#8394)

---------

Co-authored-by: Davit Buniatyan <davit@loqsh.com>
Co-authored-by: Davit Buniatyan <d@activeloop.ai>
Co-authored-by: adilkhan <adilkhan.sarsen@nu.edu.kz>
Co-authored-by: Ivo Stranic <istranic@gmail.com>

libs/langchain/langchain/vectorstores/deeplake.py

@@ -56,6 +56,7 @@ class DeepLake(VectorStore):
         self,
         dataset_path: str = _LANGCHAIN_DEFAULT_DEEPLAKE_PATH,
         token: Optional[str] = None,
+        embedding: Optional[Embeddings] = None,
         embedding_function: Optional[Embeddings] = None,
         read_only: bool = False,
         ingestion_batch_size: int = 1000,
@@ -86,8 +87,11 @@ class DeepLake(VectorStore):
             token (str, optional):  Activeloop token, for fetching credentials
                 to the dataset at path if it is a Deep Lake dataset.
                 Tokens are normally autogenerated. Optional.
-            embedding_function (str, optional): Function to convert
+            embedding (Embeddings, optional): Function to convert
                 either documents or query. Optional.
+            embedding_function (Embeddings, optional): Function to convert
+                either documents or query. Optional. Deprecated: keeping this
+                parameter for backwards compatibility.
             read_only (bool): Open dataset in read-only mode. Default is False.
             ingestion_batch_size (int): During data ingestion, data is divided
                 into batches. Batch size is the size of each batch.
@@ -138,9 +142,14 @@ class DeepLake(VectorStore):
 
         self.dataset_path = dataset_path
 
+        logger.warning(
+            "Using embedding function is deprecated and will be removed "
+            "in the future. Please use embedding instead."
+        )
+
         self.vectorstore = DeepLakeVectorStore(
             path=self.dataset_path,
-            embedding_function=embedding_function,
+            embedding_function=embedding_function or embedding,
             read_only=read_only,
             token=token,
             exec_option=exec_option,
@@ -148,7 +157,7 @@ class DeepLake(VectorStore):
             **kwargs,
         )
 
-        self._embedding_function = embedding_function
+        self._embedding_function = embedding_function or embedding
         self._id_tensor_name = "ids" if "ids" in self.vectorstore.tensors() else "id"
 
     @property
@@ -719,7 +728,6 @@ class DeepLake(VectorStore):
         metadatas: Optional[List[dict]] = None,
         ids: Optional[List[str]] = None,
         dataset_path: str = _LANGCHAIN_DEFAULT_DEEPLAKE_PATH,
-        embedding_function: Optional[Embeddings] = None,
         **kwargs: Any,
     ) -> DeepLake:
         """Create a Deep Lake dataset from a raw documents.
@@ -761,20 +769,8 @@ class DeepLake(VectorStore):
 
         Returns:
             DeepLake: Deep Lake dataset.
-
-        Raises:
-            ValueError: If 'embedding' is provided in kwargs. This is deprecated,
-                please use `embedding_function` instead.
         """
-        if embedding:
-            raise ValueError(
-                "using embedding as embedidng_functions is deprecated. "
-                "Please use `embedding_function` instead."
-            )
-
-        deeplake_dataset = cls(
-            dataset_path=dataset_path, embedding_function=embedding_function, **kwargs
-        )
+        deeplake_dataset = cls(dataset_path=dataset_path, embedding=embedding, **kwargs)
         deeplake_dataset.add_texts(
             texts=texts,
             metadatas=metadatas,

libs/langchain/tests/integration_tests/vectorstores/test_deeplake.py

@@ -137,10 +137,11 @@ def test_similarity_search(deeplake_datastore: DeepLake, distance_metric: str) -
         f"SELECT * WHERE "
         f"id=='{deeplake_datastore.vectorstore.dataset.id[0].numpy()[0]}'"
     )
-    with pytest.raises(ValueError):
-        output = deeplake_datastore.similarity_search(
-            query="foo", tql_query=tql_query, k=1, distance_metric=distance_metric
-        )
+
+    output = deeplake_datastore.similarity_search(
+        query="foo", tql_query=tql_query, k=1, distance_metric=distance_metric
+    )
+    assert len(output) == 1
     deeplake_datastore.delete_dataset()