Max marginal relecance search fails if there are not enough docs (#1117)

Implementation fails if there are not enough documents. Added the same
check as used for similarity search.

Current implementation raises
```  
File ".venv/lib/python3.9/site-packages/langchain/vectorstores/faiss.py", line 160, in max_marginal_relevance_search
    _id = self.index_to_docstore_id[i]
KeyError: -1
```

langchain/vectorstores/faiss.py

@@ -189,6 +189,9 @@ class FAISS(VectorStore):
         docs = []
         for i in selected_indices:
             _id = self.index_to_docstore_id[i]
+            if _id == -1:
+                # This happens when not enough docs are returned.
+                continue
             doc = self.docstore.search(_id)
             if not isinstance(doc, Document):
                 raise ValueError(f"Could not find document for id {_id}, got {doc}")