Merge branch 'master' into jacob/hotfix

docs/docs/integrations/adapters/openai-old.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# OpenAI Adapter(Old)\n",
     "\n",
-    "**Please ensure OpenAI library is less than 1.0.0; otherwise, refer to the newer doc [OpenAI Adapter](./openai.ipynb).**\n",
+    "**Please ensure OpenAI library is less than 1.0.0; otherwise, refer to the newer doc [OpenAI Adapter](./openai).**\n",
     "\n",
     "A lot of people get started with OpenAI but want to explore other models. LangChain's integrations with many model providers make this easy to do so. While LangChain has it's own message and model APIs, we've also made it as easy as possible to explore other models by exposing an adapter to adapt LangChain models to the OpenAI api.\n",
     "\n",

docs/docs/integrations/adapters/openai.ipynb

@@ -7,7 +7,7 @@
    "source": [
     "# OpenAI Adapter\n",
     "\n",
-    "**Please ensure OpenAI library is version 1.0.0 or higher; otherwise, refer to the older doc [OpenAI Adapter(Old)](./openai-old.ipynb).**\n",
+    "**Please ensure OpenAI library is version 1.0.0 or higher; otherwise, refer to the older doc [OpenAI Adapter(Old)](./openai-old).**\n",
     "\n",
     "A lot of people get started with OpenAI but want to explore other models. LangChain's integrations with many model providers make this easy to do so. While LangChain has it's own message and model APIs, we've also made it as easy as possible to explore other models by exposing an adapter to adapt LangChain models to the OpenAI api.\n",
     "\n",

docs/docs/integrations/providers/alibabacloud_opensearch.md

@@ -24,7 +24,7 @@ supported functions:
 - `delete_doc_by_texts`
 
 
-For a more detailed walk through of the Alibaba Cloud OpenSearch wrapper, see [this notebook](../modules/indexes/vectorstores/examples/alibabacloud_opensearch.ipynb)
+For a more detailed walk through of the Alibaba Cloud OpenSearch wrapper, see [this notebook](/docs/integrations/vectorstores/alibabacloud_opensearch)
 
 If you encounter any problems during use, please feel free to contact [[email protected]]([email protected]) , and we will do our best to provide you with assistance and support.
 

docs/docs/integrations/providers/dataforseo.mdx

@@ -16,7 +16,7 @@ The DataForSEO utility wraps the API. To import this utility, use:
 from langchain.utilities.dataforseo_api_search import DataForSeoAPIWrapper
 ```
 
-For a detailed walkthrough of this wrapper, see [this notebook](/docs/integrations/tools/dataforseo.ipynb).
+For a detailed walkthrough of this wrapper, see [this notebook](/docs/integrations/tools/dataforseo).
 
 ### Tool
 

docs/docs/integrations/providers/jina.mdx

@@ -17,4 +17,4 @@ embeddings = JinaEmbeddings(jina_api_key='jina_**', model_name='jina-embeddings-
 
 You can check the list of available models from [here](https://jina.ai/embeddings/)
 
-For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/jina.ipynb)
+For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/jina)

docs/docs/integrations/providers/vearch.md

@@ -8,7 +8,7 @@ Vearch Python SDK enables vearch to use locally. Vearch python sdk can be instal
 
 # Vectorstore
 
-Vearch also can used as vectorstore. Most detalis in [this notebook](docs/modules/indexes/vectorstores/examples/vearch.ipynb)
+Vearch also can used as vectorstore. Most detalis in [this notebook](/docs/integrations/vectorstores/vearch)
 
 ```python
 from langchain.vectorstores import Vearch

libs/core/langchain_core/runnables/history.py

@@ -46,8 +46,9 @@ class RunnableWithMessageHistory(RunnableBindingBase):
 
             from typing import Optional
 
-            from langchain_core.chat_models import ChatAnthropic
-            from langchain_core.memory.chat_message_histories import RedisChatMessageHistory
+            from langchain.chat_models import ChatAnthropic
+            from langchain.memory.chat_message_histories import RedisChatMessageHistory
+
             from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
             from langchain_core.runnables.history import RunnableWithMessageHistory
 

libs/langchain/langchain/chat_models/baidu_qianfan_endpoint.py

@@ -13,7 +13,8 @@
     SystemMessage,
 )
 from langchain_core.outputs import ChatGeneration, ChatGenerationChunk, ChatResult
-from langchain_core.pydantic_v1 import Field, root_validator
+from langchain_core.pydantic_v1 import Field, SecretStr, root_validator
+from langchain_core.utils import convert_to_secret_str
 
 from langchain.callbacks.manager import (
     AsyncCallbackManagerForLLMRun,
@@ -88,8 +89,8 @@ class QianfanChatEndpoint(BaseChatModel):
 
     client: Any
 
-    qianfan_ak: Optional[str] = None
-    qianfan_sk: Optional[str] = None
+    qianfan_ak: Optional[SecretStr] = None
+    qianfan_sk: Optional[SecretStr] = None
 
     streaming: Optional[bool] = False
     """Whether to stream the results or not."""
@@ -118,19 +119,23 @@ class QianfanChatEndpoint(BaseChatModel):
 
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict:
-        values["qianfan_ak"] = get_from_dict_or_env(
-            values,
-            "qianfan_ak",
-            "QIANFAN_AK",
+        values["qianfan_ak"] = convert_to_secret_str(
+            get_from_dict_or_env(
+                values,
+                "qianfan_ak",
+                "QIANFAN_AK",
+            )
         )
-        values["qianfan_sk"] = get_from_dict_or_env(
-            values,
-            "qianfan_sk",
-            "QIANFAN_SK",
+        values["qianfan_sk"] = convert_to_secret_str(
+            get_from_dict_or_env(
+                values,
+                "qianfan_sk",
+                "QIANFAN_SK",
+            )
         )
         params = {
-            "ak": values["qianfan_ak"],
-            "sk": values["qianfan_sk"],
+            "ak": values["qianfan_ak"].get_secret_value(),
+            "sk": values["qianfan_sk"].get_secret_value(),
             "model": values["model"],
             "stream": values["streaming"],
         }

libs/langchain/langchain/llms/cerebriumai.py

@@ -1,22 +1,23 @@
 import logging
-from typing import Any, Dict, List, Mapping, Optional
+from typing import Any, Dict, List, Mapping, Optional, cast
 
 import requests
-from langchain_core.pydantic_v1 import Extra, Field, root_validator
+from langchain_core.pydantic_v1 import Extra, Field, SecretStr, root_validator
 
 from langchain.callbacks.manager import CallbackManagerForLLMRun
 from langchain.llms.base import LLM
 from langchain.llms.utils import enforce_stop_tokens
-from langchain.utils import get_from_dict_or_env
+from langchain.utils import convert_to_secret_str, get_from_dict_or_env
 
 logger = logging.getLogger(__name__)
 
 
 class CerebriumAI(LLM):
     """CerebriumAI large language models.
 
-    To use, you should have the ``cerebrium`` python package installed, and the
-    environment variable ``CEREBRIUMAI_API_KEY`` set with your API key.
+    To use, you should have the ``cerebrium`` python package installed.
+    You should also have the environment variable ``CEREBRIUMAI_API_KEY``
+    set with your API key or pass it as a named argument in the constructor.
 
     Any parameters that are valid to be passed to the call can be passed
     in, even if not explicitly saved on this class.
@@ -25,7 +26,7 @@ class CerebriumAI(LLM):
         .. code-block:: python
 
             from langchain.llms import CerebriumAI
-            cerebrium = CerebriumAI(endpoint_url="")
+            cerebrium = CerebriumAI(endpoint_url="", cerebriumai_api_key="my-api-key")
 
     """
 
@@ -36,7 +37,7 @@ class CerebriumAI(LLM):
     """Holds any model parameters valid for `create` call not
     explicitly specified."""
 
-    cerebriumai_api_key: Optional[str] = None
+    cerebriumai_api_key: Optional[SecretStr] = None
 
     class Config:
         """Configuration for this pydantic config."""
@@ -64,8 +65,8 @@ def build_extra(cls, values: Dict[str, Any]) -> Dict[str, Any]:
     @root_validator()
     def validate_environment(cls, values: Dict) -> Dict:
         """Validate that api key and python package exists in environment."""
-        cerebriumai_api_key = get_from_dict_or_env(
-            values, "cerebriumai_api_key", "CEREBRIUMAI_API_KEY"
+        cerebriumai_api_key = convert_to_secret_str(
+            get_from_dict_or_env(values, "cerebriumai_api_key", "CEREBRIUMAI_API_KEY")
         )
         values["cerebriumai_api_key"] = cerebriumai_api_key
         return values
@@ -91,7 +92,9 @@ def _call(
         **kwargs: Any,
     ) -> str:
         headers: Dict = {
-            "Authorization": self.cerebriumai_api_key,
+            "Authorization": cast(
+                SecretStr, self.cerebriumai_api_key
+            ).get_secret_value(),
             "Content-Type": "application/json",
         }
         params = self.model_kwargs or {}

libs/langchain/langchain/vectorstores/qdrant.py

@@ -82,17 +82,17 @@ class Qdrant(VectorStore):
             qdrant = Qdrant(client, collection_name, embedding_function)
     """
 
-    CONTENT_KEY = "page_content"
-    METADATA_KEY = "metadata"
+    CONTENT_KEY = ["page_content"]
+    METADATA_KEY = ["metadata"]
     VECTOR_NAME = None
 
     def __init__(
         self,
         client: Any,
         collection_name: str,
         embeddings: Optional[Embeddings] = None,
-        content_payload_key: str = CONTENT_KEY,
-        metadata_payload_key: str = METADATA_KEY,
+        content_payload_key: Union[list, str] = CONTENT_KEY,
+        metadata_payload_key: Union[list, str] = METADATA_KEY,
         distance_strategy: str = "COSINE",
         vector_name: Optional[str] = VECTOR_NAME,
         embedding_function: Optional[Callable] = None,  # deprecated
@@ -112,6 +112,12 @@ def __init__(
                 f"got {type(client)}"
             )
 
+        if isinstance(content_payload_key, str):  # Ensuring Backward compatibility
+            content_payload_key = [content_payload_key]
+
+        if isinstance(metadata_payload_key, str):  # Ensuring Backward compatibility
+            metadata_payload_key = [metadata_payload_key]
+
         if embeddings is None and embedding_function is None:
             raise ValueError(
                 "`embeddings` value can't be None. Pass `Embeddings` instance."
@@ -127,8 +133,14 @@ def __init__(
         self._embeddings_function = embedding_function
         self.client: qdrant_client.QdrantClient = client
         self.collection_name = collection_name
-        self.content_payload_key = content_payload_key or self.CONTENT_KEY
-        self.metadata_payload_key = metadata_payload_key or self.METADATA_KEY
+        self.content_payload_key = (
+            content_payload_key if content_payload_key is not None else self.CONTENT_KEY
+        )
+        self.metadata_payload_key = (
+            metadata_payload_key
+            if metadata_payload_key is not None
+            else self.METADATA_KEY
+        )
         self.vector_name = vector_name or self.VECTOR_NAME
 
         if embedding_function is not None:
@@ -1178,8 +1190,8 @@ def from_texts(
         path: Optional[str] = None,
         collection_name: Optional[str] = None,
         distance_func: str = "Cosine",
-        content_payload_key: str = CONTENT_KEY,
-        metadata_payload_key: str = METADATA_KEY,
+        content_payload_key: List[str] = CONTENT_KEY,
+        metadata_payload_key: List[str] = METADATA_KEY,
         vector_name: Optional[str] = VECTOR_NAME,
         batch_size: int = 64,
         shard_number: Optional[int] = None,
@@ -1354,8 +1366,8 @@ async def afrom_texts(
         path: Optional[str] = None,
         collection_name: Optional[str] = None,
         distance_func: str = "Cosine",
-        content_payload_key: str = CONTENT_KEY,
-        metadata_payload_key: str = METADATA_KEY,
+        content_payload_key: List[str] = CONTENT_KEY,
+        metadata_payload_key: List[str] = METADATA_KEY,
         vector_name: Optional[str] = VECTOR_NAME,
         batch_size: int = 64,
         shard_number: Optional[int] = None,
@@ -1527,8 +1539,8 @@ def construct_instance(
         path: Optional[str] = None,
         collection_name: Optional[str] = None,
         distance_func: str = "Cosine",
-        content_payload_key: str = CONTENT_KEY,
-        metadata_payload_key: str = METADATA_KEY,
+        content_payload_key: List[str] = CONTENT_KEY,
+        metadata_payload_key: List[str] = METADATA_KEY,
         vector_name: Optional[str] = VECTOR_NAME,
         shard_number: Optional[int] = None,
         replication_factor: Optional[int] = None,
@@ -1691,8 +1703,8 @@ async def aconstruct_instance(
         path: Optional[str] = None,
         collection_name: Optional[str] = None,
         distance_func: str = "Cosine",
-        content_payload_key: str = CONTENT_KEY,
-        metadata_payload_key: str = METADATA_KEY,
+        content_payload_key: List[str] = CONTENT_KEY,
+        metadata_payload_key: List[str] = METADATA_KEY,
         vector_name: Optional[str] = VECTOR_NAME,
         shard_number: Optional[int] = None,
         replication_factor: Optional[int] = None,
@@ -1888,11 +1900,11 @@ def _similarity_search_with_relevance_scores(
 
     @classmethod
     def _build_payloads(
-        cls,
+        cls: Type[Qdrant],
         texts: Iterable[str],
         metadatas: Optional[List[dict]],
-        content_payload_key: str,
-        metadata_payload_key: str,
+        content_payload_key: list[str],
+        metadata_payload_key: list[str],
     ) -> List[dict]:
         payloads = []
         for i, text in enumerate(texts):
@@ -1913,29 +1925,67 @@ def _build_payloads(
 
     @classmethod
     def _document_from_scored_point(
-        cls,
+        cls: Type[Qdrant],
         scored_point: Any,
-        content_payload_key: str,
-        metadata_payload_key: str,
+        content_payload_key: list[str],
+        metadata_payload_key: list[str],
     ) -> Document:
-        return Document(
-            page_content=scored_point.payload.get(content_payload_key),
-            metadata=scored_point.payload.get(metadata_payload_key) or {},
+        payload = scored_point.payload
+        return Qdrant._document_from_payload(
+            payload=payload,
+            content_payload_key=content_payload_key,
+            metadata_payload_key=metadata_payload_key,
         )
 
     @classmethod
     def _document_from_scored_point_grpc(
-        cls,
+        cls: Type[Qdrant],
         scored_point: Any,
-        content_payload_key: str,
-        metadata_payload_key: str,
+        content_payload_key: list[str],
+        metadata_payload_key: list[str],
     ) -> Document:
         from qdrant_client.conversions.conversion import grpc_to_payload
 
         payload = grpc_to_payload(scored_point.payload)
+        return Qdrant._document_from_payload(
+            payload=payload,
+            content_payload_key=content_payload_key,
+            metadata_payload_key=metadata_payload_key,
+        )
+
+    @classmethod
+    def _document_from_payload(
+        cls: Type[Qdrant],
+        payload: Any,
+        content_payload_key: list[str],
+        metadata_payload_key: list[str],
+    ) -> Document:
+        if len(content_payload_key) == 1:
+            content = payload.get(
+                content_payload_key
+            )  # Ensuring backward compatibility
+        elif len(content_payload_key) > 1:
+            content = {
+                content_key: payload.get(content_key)
+                for content_key in content_payload_key
+            }
+            content = str(content)  # Ensuring str type output
+        else:
+            content = ""
+        if len(metadata_payload_key) == 1:
+            metadata = payload.get(
+                metadata_payload_key
+            )  # Ensuring backward compatibility
+        elif len(metadata_payload_key) > 1:
+            metadata = {
+                metadata_key: payload.get(metadata_key)
+                for metadata_key in metadata_payload_key
+            }
+        else:
+            metadata = {}
         return Document(
-            page_content=payload[content_payload_key],
-            metadata=payload.get(metadata_payload_key) or {},
+            page_content=content,
+            metadata=metadata,
         )
 
     def _build_condition(self, key: str, value: Any) -> List[rest.FieldCondition]: