community[patch]: update for compatibility with latest Meilisearch version (#18970)

- **Description:** Updates Meilisearch vectorstore for compatibility
with v1.6 and above. Adds embedders settings and embedder_name which are
now required.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

libs/community/langchain_community/vectorstores/meilisearch.py

@@ -65,8 +65,15 @@ class Meilisearch(VectorStore):
             # api_key is optional; provide it if your meilisearch instance requires it
             client = meilisearch.Client(url='http://127.0.0.1:7700', api_key='***')
             embeddings = OpenAIEmbeddings()
+            embedders = {
+                "theEmbedderName": {
+                    "source": "userProvided",
+                    "dimensions": "1536"
+                }
+            }
             vectorstore = Meilisearch(
                 embedding=embeddings,
+                embedders=embedders,
                 client=client,
                 index_name='langchain_demo',
                 text_key='text')
@@ -81,6 +88,8 @@ class Meilisearch(VectorStore):
         index_name: str = "langchain-demo",
         text_key: str = "text",
         metadata_key: str = "metadata",
+        *,
+        embedders: Optional[Dict[str, Any]] = None,
     ):
         """Initialize with Meilisearch client."""
         client = _create_client(client=client, url=url, api_key=api_key)
@@ -90,18 +99,24 @@ class Meilisearch(VectorStore):
         self._embedding = embedding
         self._text_key = text_key
         self._metadata_key = metadata_key
+        self._embedders = embedders
+        self._embedders_settings = self._client.index(
+            str(self._index_name)
+        ).update_embedders(embedders)
 
     def add_texts(
         self,
         texts: Iterable[str],
         metadatas: Optional[List[dict]] = None,
         ids: Optional[List[str]] = None,
+        embedder_name: Optional[str] = "default",
         **kwargs: Any,
     ) -> List[str]:
         """Run more texts through the embedding and add them to the vector store.
 
         Args:
             texts (Iterable[str]): Iterable of strings/text to add to the vectorstore.
+            embedder_name: Name of the embedder. Defaults to "default".
             metadatas (Optional[List[dict]]): Optional list of metadata.
                 Defaults to None.
             ids Optional[List[str]]: Optional list of IDs.
@@ -128,7 +143,7 @@ class Meilisearch(VectorStore):
             docs.append(
                 {
                     "id": id,
-                    "_vectors": embedding,
+                    "_vectors": {f"{embedder_name}": embedding},
                     f"{self._metadata_key}": metadata,
                 }
             )
@@ -142,12 +157,14 @@ class Meilisearch(VectorStore):
         query: str,
         k: int = 4,
         filter: Optional[Dict[str, str]] = None,
+        embedder_name: Optional[str] = "default",
         **kwargs: Any,
     ) -> List[Document]:
         """Return meilisearch documents most similar to the query.
 
         Args:
             query (str): Query text for which to find similar documents.
+            embedder_name: Name of the embedder to be used. Defaults to "default".
             k (int): Number of documents to return. Defaults to 4.
             filter (Optional[Dict[str, str]]): Filter by metadata.
                 Defaults to None.
@@ -158,6 +175,7 @@ class Meilisearch(VectorStore):
         """
         docs_and_scores = self.similarity_search_with_score(
             query=query,
+            embedder_name=embedder_name,
             k=k,
             filter=filter,
             kwargs=kwargs,
@@ -169,12 +187,14 @@ class Meilisearch(VectorStore):
         query: str,
         k: int = 4,
         filter: Optional[Dict[str, str]] = None,
+        embedder_name: Optional[str] = "default",
         **kwargs: Any,
     ) -> List[Tuple[Document, float]]:
         """Return meilisearch documents most similar to the query, along with scores.
 
         Args:
             query (str): Query text for which to find similar documents.
+            embedder_name: Name of the embedder to be used. Defaults to "default".
             k (int): Number of documents to return. Defaults to 4.
             filter (Optional[Dict[str, str]]): Filter by metadata.
                 Defaults to None.
@@ -187,6 +207,7 @@ class Meilisearch(VectorStore):
 
         docs = self.similarity_search_by_vector_with_scores(
             embedding=_query,
+            embedder_name=embedder_name,
             k=k,
             filter=filter,
             kwargs=kwargs,
@@ -196,6 +217,7 @@ class Meilisearch(VectorStore):
     def similarity_search_by_vector_with_scores(
         self,
         embedding: List[float],
+        embedder_name: Optional[str] = "default",
         k: int = 4,
         filter: Optional[Dict[str, Any]] = None,
         **kwargs: Any,
@@ -204,6 +226,7 @@ class Meilisearch(VectorStore):
 
         Args:
             embedding (List[float]): Embedding to look up similar documents.
+            embedder_name: Name of the embedder to be used. Defaults to "default".
             k (int): Number of documents to return. Defaults to 4.
             filter (Optional[Dict[str, str]]): Filter by metadata.
                 Defaults to None.
@@ -214,7 +237,13 @@ class Meilisearch(VectorStore):
         """
         docs = []
         results = self._client.index(str(self._index_name)).search(
-            "", {"vector": embedding, "limit": k, "filter": filter}
+            "",
+            {
+                "vector": embedding,
+                "hybrid": {"semanticRatio": 1.0, "embedder": embedder_name},
+                "limit": k,
+                "filter": filter,
+            },
         )
 
         for result in results["hits"]:
@@ -233,12 +262,14 @@ class Meilisearch(VectorStore):
         embedding: List[float],
         k: int = 4,
         filter: Optional[Dict[str, str]] = None,
+        embedder_name: Optional[str] = "default",
         **kwargs: Any,
     ) -> List[Document]:
         """Return meilisearch documents most similar to embedding vector.
 
         Args:
             embedding (List[float]): Embedding to look up similar documents.
+            embedder_name: Name of the embedder to be used. Defaults to "default".
             k (int): Number of documents to return. Defaults to 4.
             filter (Optional[Dict[str, str]]): Filter by metadata.
                 Defaults to None.
@@ -249,6 +280,7 @@ class Meilisearch(VectorStore):
         """
         docs = self.similarity_search_by_vector_with_scores(
             embedding=embedding,
+            embedder_name=embedder_name,
             k=k,
             filter=filter,
             kwargs=kwargs,
@@ -268,6 +300,8 @@ class Meilisearch(VectorStore):
         ids: Optional[List[str]] = None,
         text_key: Optional[str] = "text",
         metadata_key: Optional[str] = "metadata",
+        embedders: Dict[str, Any] = {},
+        embedder_name: Optional[str] = "default",
         **kwargs: Any,
     ) -> Meilisearch:
         """Construct Meilisearch wrapper from raw documents.
@@ -288,21 +322,25 @@ class Meilisearch(VectorStore):
                 # The environment should be the one specified next to the API key
                 # in your Meilisearch console
                 client = meilisearch.Client(url='http://127.0.0.1:7700', api_key='***')
-                embeddings = OpenAIEmbeddings()
+                embedding = OpenAIEmbeddings()
+                embedders: Embedders index setting.
+                embedder_name: Name of the embedder. Defaults to "default".
                 docsearch = Meilisearch.from_texts(
                     client=client,
-                    embeddings=embeddings,
+                    embedding=embedding,
                 )
         """
         client = _create_client(client=client, url=url, api_key=api_key)
 
         vectorstore = cls(
             embedding=embedding,
+            embedders=embedders,
             client=client,
             index_name=index_name,
         )
         vectorstore.add_texts(
             texts=texts,
+            embedder_name=embedder_name,
             metadatas=metadatas,
             ids=ids,
             text_key=text_key,