add return of ids (#254)

not actually sure the desired return in add_example to example selector
is actually general/good - whats the use case?

langchain/prompts/example_selector/base.py

@@ -1,13 +1,13 @@
 """Interface for selecting examples to include in prompts."""
 from abc import ABC, abstractmethod
-from typing import Dict, List
+from typing import Any, Dict, List
 
 
 class BaseExampleSelector(ABC):
     """Interface for selecting examples to include in prompts."""
 
     @abstractmethod
-    def add_example(self, example: Dict[str, str]) -> None:
+    def add_example(self, example: Dict[str, str]) -> Any:
         """Add new example to store for a key."""
 
     @abstractmethod

langchain/prompts/example_selector/semantic_similarity.py

@@ -31,10 +31,11 @@ class SemanticSimilarityExampleSelector(BaseExampleSelector, BaseModel):
         extra = Extra.forbid
         arbitrary_types_allowed = True
 
-    def add_example(self, example: Dict[str, str]) -> None:
+    def add_example(self, example: Dict[str, str]) -> str:
         """Add new example to vectorstore."""
         string_example = " ".join(sorted_values(example))
-        self.vectorstore.add_texts([string_example], metadatas=[example])
+        ids = self.vectorstore.add_texts([string_example], metadatas=[example])
+        return ids[0]
 
     def select_examples(self, input_variables: Dict[str, str]) -> List[dict]:
         """Select which examples to use based on semantic similarity."""

langchain/vectorstores/base.py

@@ -14,8 +14,16 @@ class VectorStore(ABC):
     @abstractmethod
     def add_texts(
         self, texts: Iterable[str], metadatas: Optional[List[dict]] = None
-    ) -> None:
+    ) -> List[str]:
-        """Run more texts through the embeddings and add to the vectorstore."""
+        """Run more texts through the embeddings and add to the vectorstore.
+
+        Args:
+            texts: Iterable of strings to add to the vectorstore.
+            metadatas: Optional list of metadatas associated with the texts.
+
+        Returns:
+            List of ids from adding the texts into the vectorstore.
+        """
 
     @abstractmethod
     def similarity_search(self, query: str, k: int = 4) -> List[Document]:

langchain/vectorstores/elastic_vector_search.py

@@ -55,7 +55,7 @@ class ElasticVectorSearch(VectorStore):
         except ImportError:
             raise ValueError(
                 "Could not import elasticsearch python package. "
-                "Please install it with `pip install elasticearch`."
+                "Please install it with `pip install elasticsearch`."
             )
         self.embedding_function = embedding_function
         self.index_name = index_name
@@ -69,29 +69,42 @@ class ElasticVectorSearch(VectorStore):
 
     def add_texts(
         self, texts: Iterable[str], metadatas: Optional[List[dict]] = None
-    ) -> None:
+    ) -> List[str]:
-        """Run more texts through the embeddings and add to the vectorstore."""
+        """Run more texts through the embeddings and add to the vectorstore.
+
+        Args:
+            texts: Iterable of strings to add to the vectorstore.
+            metadatas: Optional list of metadatas associated with the texts.
+
+        Returns:
+            List of ids from adding the texts into the vectorstore.
+        """
         try:
             from elasticsearch.helpers import bulk
         except ImportError:
             raise ValueError(
                 "Could not import elasticsearch python package. "
-                "Please install it with `pip install elasticearch`."
+                "Please install it with `pip install elasticsearch`."
             )
         requests = []
+        ids = []
         for i, text in enumerate(texts):
             metadata = metadatas[i] if metadatas else {}
+            _id = str(uuid.uuid4())
             request = {
                 "_op_type": "index",
                 "_index": self.index_name,
                 "vector": self.embedding_function(text),
                 "text": text,
                 "metadata": metadata,
+                "_id": _id,
             }
+            ids.append(_id)
             requests.append(request)
         bulk(self.client, requests)
         # TODO: add option not to refresh
         self.client.indices.refresh(index=self.index_name)
+        return ids
 
     def similarity_search(self, query: str, k: int = 4) -> List[Document]:
         """Return docs most similar to query.

langchain/vectorstores/faiss.py

@@ -41,8 +41,16 @@ class FAISS(VectorStore):
 
     def add_texts(
         self, texts: Iterable[str], metadatas: Optional[List[dict]] = None
-    ) -> None:
+    ) -> List[str]:
-        """Run more texts through the embeddings and add to the vectorstore."""
+        """Run more texts through the embeddings and add to the vectorstore.
+
+        Args:
+            texts: Iterable of strings to add to the vectorstore.
+            metadatas: Optional list of metadatas associated with the texts.
+
+        Returns:
+            List of ids from adding the texts into the vectorstore.
+        """
         if not isinstance(self.docstore, AddableMixin):
             raise ValueError(
                 "If trying to add texts, the underlying docstore should support "
@@ -66,6 +74,7 @@ class FAISS(VectorStore):
         self.docstore.add({_id: doc for _, _id, doc in full_info})
         index_to_id = {index: _id for index, _id, _ in full_info}
         self.index_to_docstore_id.update(index_to_id)
+        return [_id for _, _id, _ in full_info]
 
     def similarity_search(self, query: str, k: int = 4) -> List[Document]:
         """Return docs most similar to query.