From 9e649462cefdcba1ffb9ecb2e7fd0e98a1d79411 Mon Sep 17 00:00:00 2001
From: Shawn91 <vuyuxl199199@gmail.com>
Date: Tue, 23 May 2023 03:35:52 +0800
Subject: [PATCH] fix: add_texts method of Weaviate vector store creats wrong
 embeddings (#4933)

# fix a bug in the add_texts method of Weaviate vector store that creats
wrong embeddings

The following is the original code in the `add_texts` method of the
Weaviate vector store, from line 131 to 153, which contains a bug. The
code here includes some extra explanations in the form of comments and
some omissions.

```python
            for i, doc in enumerate(texts):

                # some code omitted

                if self._embedding is not None:
                    # variable texts is a list of string and doc here is just a string.
                    # list(doc) actually breaks up the string into characters.
                    # so, embeddings[0] is just the embedding of the first character
                    embeddings = self._embedding.embed_documents(list(doc))
                    batch.add_data_object(
                        data_object=data_properties,
                        class_name=self._index_name,
                        uuid=_id,
                        vector=embeddings[0],
                    )
```

To fix this bug, I pulled the embedding operation out of the for loop
and embed all texts at once.

Co-authored-by: Shawn91 <zyx199199@qq.com>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
---
 langchain/vectorstores/weaviate.py | 52 +++++++++++++-----------------
 1 file changed, 23 insertions(+), 29 deletions(-)

diff --git a/langchain/vectorstores/weaviate.py b/langchain/vectorstores/weaviate.py
index 9d2a168b..a7398ae7 100644
--- a/langchain/vectorstores/weaviate.py
+++ b/langchain/vectorstores/weaviate.py
@@ -63,6 +63,12 @@ def _default_score_normalizer(val: float) -> float:
     return 1 - 1 / (1 + np.exp(val))
 
 
+def _json_serializable(value: Any) -> Any:
+    if isinstance(value, datetime.datetime):
+        return value.isoformat()
+    return value
+
+
 class Weaviate(VectorStore):
     """Wrapper around Weaviate vector database.
 
@@ -121,42 +127,30 @@ class Weaviate(VectorStore):
         """Upload texts with metadata (properties) to Weaviate."""
         from weaviate.util import get_valid_uuid
 
-        def json_serializable(value: Any) -> Any:
-            if isinstance(value, datetime.datetime):
-                return value.isoformat()
-            return value
-
+        ids = []
         with self._client.batch as batch:
-            ids = []
-            for i, doc in enumerate(texts):
-                data_properties = {
-                    self._text_key: doc,
-                }
+            for i, text in enumerate(texts):
+                data_properties = {self._text_key: text}
                 if metadatas is not None:
-                    for key in metadatas[i].keys():
-                        data_properties[key] = json_serializable(metadatas[i][key])
+                    for key, val in metadatas[i].items():
+                        data_properties[key] = _json_serializable(val)
 
                 # If the UUID of one of the objects already exists
-                # then the existing objectwill be replaced by the new object.
-                if "uuids" in kwargs:
-                    _id = kwargs["uuids"][i]
-                else:
-                    _id = get_valid_uuid(uuid4())
+                # then the existing object will be replaced by the new object.
+                _id = (
+                    kwargs["uuids"][i] if "uuids" in kwargs else get_valid_uuid(uuid4())
+                )
 
                 if self._embedding is not None:
-                    embeddings = self._embedding.embed_documents(list(doc))
-                    batch.add_data_object(
-                        data_object=data_properties,
-                        class_name=self._index_name,
-                        uuid=_id,
-                        vector=embeddings[0],
-                    )
+                    vector = self._embedding.embed_documents([text])[0]
                 else:
-                    batch.add_data_object(
-                        data_object=data_properties,
-                        class_name=self._index_name,
-                        uuid=_id,
-                    )
+                    vector = None
+                batch.add_data_object(
+                    data_object=data_properties,
+                    class_name=self._index_name,
+                    uuid=_id,
+                    vector=vector,
+                )
                 ids.append(_id)
         return ids