Support similarity search by vector (in FAISS) (#961)

Alternate implementation to PR #960 Again - only FAISS is implemented.
If accepted can add this to other vectorstores or leave as
NotImplemented? Suggestions welcome...

docs/modules/utils/combine_docs_examples/vectorstores.ipynb

@@ -297,6 +297,26 @@
     "docs_and_scores[0]"
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "id": "d5170563",
+   "metadata": {},
+   "source": [
+    "It is also possible to do a search for documents similar to a given embedding vector using `similarity_search_by_vector` which accepts an embedding vector as a parameter instead of a string."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7675b0aa",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "embedding_vector = embeddings.embed_query(query)\n",
+    "docs_and_scores = docsearch.similarity_search_by_vector(embedding_vector)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "b386dbb8",