Merge branch 'master' into nc/20dec/runnable-chain

libs/community/langchain_community/chat_models/azure_openai.py

@@ -26,7 +26,7 @@ class AzureChatOpenAI(ChatOpenAI):
     In addition, you should have the ``openai`` python package installed, and the
     following environment variables set or passed in constructor in lower case:
     - ``AZURE_OPENAI_API_KEY``
-    - ``AZURE_OPENAI_API_ENDPOINT``
+    - ``AZURE_OPENAI_ENDPOINT``
     - ``AZURE_OPENAI_AD_TOKEN``
     - ``OPENAI_API_VERSION``
     - ``OPENAI_PROXY``

libs/community/langchain_community/vectorstores/jaguar.py

@@ -2,10 +2,7 @@ from __future__ import annotations
 
 import json
 import logging
-from typing import TYPE_CHECKING, Any, List, Optional, Tuple
-
-if TYPE_CHECKING:
-    from jaguardb_http_client.JaguarHttpClient import JaguarHttpClient
+from typing import Any, List, Optional, Tuple
 
 from langchain_core.documents import Document
 from langchain_core.embeddings import Embeddings
@@ -23,7 +20,7 @@ class Jaguar(VectorStore):
     Example:
        .. code-block:: python
 
-           from langchain.vectorstores import Jaguar
+           from langchain_community.vectorstores.jaguar import Jaguar
 
            vectorstore = Jaguar(
                pod = 'vdb',
@@ -53,6 +50,13 @@ class Jaguar(VectorStore):
         self._vector_dimension = vector_dimension
 
         self._embedding = embedding
+        try:
+            from jaguardb_http_client.JaguarHttpClient import JaguarHttpClient
+        except ImportError:
+            raise ValueError(
+                "Could not import jaguardb-http-client python package. "
+                "Please install it with `pip install -U jaguardb-http-client`"
+            )
 
         self._jag = JaguarHttpClient(url)
         self._token = ""

libs/community/langchain_community/vectorstores/momento_vector_index.py

@@ -306,8 +306,13 @@ class MomentoVectorIndex(VectorStore):
 
         if "top_k" in kwargs:
             k = kwargs["k"]
+        filter_expression = kwargs.get("filter_expression", None)
         response = self._client.search(
-            self.index_name, embedding, top_k=k, metadata_fields=ALL_METADATA
+            self.index_name,
+            embedding,
+            top_k=k,
+            metadata_fields=ALL_METADATA,
+            filter_expression=filter_expression,
         )
 
         if not isinstance(response, Search.Success):
@@ -366,8 +371,13 @@ class MomentoVectorIndex(VectorStore):
         from momento.requests.vector_index import ALL_METADATA
         from momento.responses.vector_index import SearchAndFetchVectors
 
+        filter_expression = kwargs.get("filter_expression", None)
         response = self._client.search_and_fetch_vectors(
-            self.index_name, embedding, top_k=fetch_k, metadata_fields=ALL_METADATA
+            self.index_name,
+            embedding,
+            top_k=fetch_k,
+            metadata_fields=ALL_METADATA,
+            filter_expression=filter_expression,
         )
 
         if isinstance(response, SearchAndFetchVectors.Success):

libs/community/tests/integration_tests/vectorstores/test_momento_vector_index.py

@@ -1,10 +1,12 @@
+import os
 import time
 import uuid
-from typing import Iterator, List
+from typing import Generator, Iterator, List
 
 import pytest
 from langchain_core.documents import Document
 
+from langchain_community.document_loaders import TextLoader
 from langchain_community.embeddings import OpenAIEmbeddings
 from langchain_community.vectorstores import MomentoVectorIndex
 
@@ -24,6 +26,23 @@ def wait() -> None:
     time.sleep(1)
 
 
+@pytest.fixture(scope="module")
+def embedding_openai() -> OpenAIEmbeddings:
+    if not os.environ.get("OPENAI_API_KEY"):
+        raise ValueError("OPENAI_API_KEY is not set")
+    return OpenAIEmbeddings()
+
+
+@pytest.fixture(scope="function")
+def texts() -> Generator[List[str], None, None]:
+    # Load the documents from a file located in the fixtures directory
+    documents = TextLoader(
+        os.path.join(os.path.dirname(__file__), "fixtures", "sharks.txt")
+    ).load()
+
+    yield [doc.page_content for doc in documents]
+
+
 @pytest.fixture(scope="function")
 def vector_store(
     embedding_openai: OpenAIEmbeddings, random_index_name: str

libs/core/langchain_core/env.py

@@ -10,7 +10,7 @@ def get_runtime_environment() -> dict:
 
     return {
         "library_version": __version__,
-        "library": "langchain",
+        "library": "langchain-core",
         "platform": platform.platform(),
         "runtime": "python",
         "runtime_version": platform.python_version(),