Hotfix: Qdrant.from_text embeddings (#713)

I'm providing a hotfix for Qdrant integration. Calculating a single
embedding to obtain the vector size was great idea. However, that change
introduced a bug trying to put only that single embedding into the
database. It's fixed. Right now all the embeddings will be pushed to
Qdrant.

langchain/vectorstores/qdrant.py

@@ -177,8 +177,8 @@ class Qdrant(VectorStore):
         from qdrant_client.http import models as rest
 
         # Just do a single quick embedding to get vector size
-        embeddings = embedding.embed_documents(texts[:1])
-        vector_size = len(embeddings[0])
+        partial_embeddings = embedding.embed_documents(texts[:1])
+        vector_size = len(partial_embeddings[0])
 
         qdrant_host = get_from_dict_or_env(kwargs, "host", "QDRANT_HOST")
         kwargs.pop("host")
@@ -194,6 +194,9 @@ class Qdrant(VectorStore):
             ),
         )
 
+        # Now generate the embeddings for all the texts
+        embeddings = embedding.embed_documents(texts)
+
         client.upsert(
             collection_name=collection_name,
             points=rest.Batch(