Skip to content

The agent engineering platform.

docs: `integrations` reference updates 10 (#25556)

Leonid Ganeline624e0747b987
diff --git a/docs/docs/integrations/platforms/google.mdx b/docs/docs/integrations/platforms/google.mdx
index 19da4679c5..bc8d17d257 100644
--- a/docs/docs/integrations/platforms/google.mdx
+++ b/docs/docs/integrations/platforms/google.mdx
@@ -625,6 +625,7 @@ from langchain.retrievers import GoogleVertexAISearchRetriever
> from Google Cloud allows enterprises to search, store, govern, and manage documents and their AI-extracted
> data and metadata in a single platform.
+Note: `GoogleDocumentAIWarehouseRetriever` is deprecated, use `DocumentAIWarehouseRetriever` (see below).
```python
from langchain.retrievers import GoogleDocumentAIWarehouseRetriever
docai_wh_retriever = GoogleDocumentAIWarehouseRetriever(
@@ -636,6 +637,10 @@ documents = docai_wh_retriever.invoke(
)
```
+```python
+from langchain_google_community.documentai_warehouse import DocumentAIWarehouseRetriever
+```
+
## Tools
### Text-to-Speech
diff --git a/docs/docs/integrations/platforms/microsoft.mdx b/docs/docs/integrations/platforms/microsoft.mdx
index a0d6807ed7..ed282710cc 100644
--- a/docs/docs/integrations/platforms/microsoft.mdx
+++ b/docs/docs/integrations/platforms/microsoft.mdx
@@ -466,6 +466,22 @@ See a [usage example](/docs/integrations/tools/playwright).
from langchain_community.agent_toolkits import PlayWrightBrowserToolkit
```
+#### PlayWright Browser individual tools
+
+You can use individual tools from the PlayWright Browser Toolkit.
+
+```python
+from langchain_community.tools.playwright import ClickTool
+from langchain_community.tools.playwright import CurrentWebPageTool
+from langchain_community.tools.playwright import ExtractHyperlinksTool
+from langchain_community.tools.playwright import ExtractTextTool
+from langchain_community.tools.playwright import GetElementsTool
+from langchain_community.tools.playwright import NavigateTool
+from langchain_community.tools.playwright import NavigateBackTool
+```
+
+
+```python
## Graphs
### Azure Cosmos DB for Apache Gremlin
diff --git a/docs/docs/integrations/providers/connery.mdx b/docs/docs/integrations/providers/connery.mdx
new file mode 100644
index 0000000000..36684a97fa
--- /dev/null
+++ b/docs/docs/integrations/providers/connery.mdx
@@ -0,0 +1,28 @@
+# Connery
+
+>[Connery SDK](https://github.com/connery-io/connery-sdk) is an NPM package that
+> includes both an SDK and a CLI, designed for the development of plugins and actions.
+>
+>The CLI automates many things in the development process. The SDK
+> offers a JavaScript API for defining plugins and actions and packaging them
+> into a plugin server with a standardized REST API generated from the metadata.
+> The plugin server handles authorization, input validation, and logging.
+> So you can focus on the logic of your actions.
+>
+> See the use cases and examples in the [Connery SDK documentation](https://sdk.connery.io/docs/use-cases/)
+
+## Toolkit
+
+See [usage example](/docs/integrations/tools/connery).
+
+```python
+from langchain_community.agent_toolkits.connery import ConneryToolkit
+```
+
+## Tools
+
+### ConneryAction
+
+```python
+from langchain_community.tools.connery import ConneryService
+```
diff --git a/docs/docs/integrations/providers/dashvector.mdx b/docs/docs/integrations/providers/dashvector.mdx
index b18fca590b..b7ded751dd 100644
--- a/docs/docs/integrations/providers/dashvector.mdx
+++ b/docs/docs/integrations/providers/dashvector.mdx
@@ -6,12 +6,27 @@ This document demonstrates to leverage DashVector within the LangChain ecosystem
It is broken into two parts: installation and setup, and then references to specific DashVector wrappers.
## Installation and Setup
+
+
Install the Python SDK:
+
```bash
pip install dashvector
```
-## VectorStore
+You must have an API key. Here are the [installation instructions](https://help.aliyun.com/document_detail/2510223.html).
+
+
+## Embedding models
+
+```python
+from langchain_community.embeddings import DashScopeEmbeddings
+```
+
+See the [use example](/docs/integrations/vectorstores/dashvector).
+
+
+## Vector Store
A DashVector Collection is wrapped as a familiar VectorStore for native usage within LangChain,
which allows it to be readily used for various scenarios, such as semantic search or example selection.
diff --git a/docs/docs/integrations/providers/dataforseo.mdx b/docs/docs/integrations/providers/dataforseo.mdx
index 3be8ed0f2b..37d8884fa4 100644
--- a/docs/docs/integrations/providers/dataforseo.mdx
+++ b/docs/docs/integrations/providers/dataforseo.mdx
@@ -19,7 +19,7 @@ os.environ["DATAFORSEO_PASSWORD"] = "your_password"
## Utility
-The DataForSEO utility wraps the API. To import this utility, use:
+The `DataForSEO` utility wraps the API. To import this utility, use:
```python
from langchain_community.utilities.dataforseo_api_search import DataForSeoAPIWrapper
@@ -36,6 +36,13 @@ from langchain.agents import load_tools
tools = load_tools(["dataforseo-api-search"])
```
+This will load the following tools:
+
+```python
+from langchain_community.tools import DataForSeoAPISearchRun
+from langchain_community.tools import DataForSeoAPISearchResults
+```
+
## Example usage
```python
diff --git a/docs/docs/integrations/providers/dingo.mdx b/docs/docs/integrations/providers/dingo.mdx
index be0c9f83fa..b12a6a72cb 100644
--- a/docs/docs/integrations/providers/dingo.mdx
+++ b/docs/docs/integrations/providers/dingo.mdx
@@ -1,10 +1,21 @@
# DingoDB
-This page covers how to use the DingoDB ecosystem within LangChain.
-It is broken into two parts: installation and setup, and then references to specific DingoDB wrappers.
+>[DingoDB](https://github.com/dingodb) is a distributed multi-modal vector
+> database. It combines the features of a data lake and a vector database,
+> allowing for the storage of any type of data (key-value, PDF, audio,
+> video, etc.) regardless of its size. Utilizing DingoDB, you can construct
+> your own Vector Ocean (the next-generation data architecture following data
+> warehouse and data lake). This enables
+> the analysis of both structured and unstructured data through
+> a singular SQL with exceptionally low latency in real time.
## Installation and Setup
-- Install the Python SDK with `pip install dingodb`
+
+Install the Python SDK
+
+```bash
+pip install dingodb
+```
## VectorStore
@@ -12,6 +23,7 @@ There exists a wrapper around DingoDB indexes, allowing you to use it as a vecto
whether for semantic search or example selection.
To import this vectorstore:
+
```python
from langchain_community.vectorstores import Dingo
```
diff --git a/docs/docs/integrations/providers/docarray.mdx b/docs/docs/integrations/providers/docarray.mdx
index 5895fa30f7..d1d41a1983 100644
--- a/docs/docs/integrations/providers/docarray.mdx
+++ b/docs/docs/integrations/providers/docarray.mdx
@@ -20,7 +20,7 @@ LangChain provides an access to the `In-memory` and `HNSW` vector stores from th
See a [usage example](/docs/integrations/vectorstores/docarray_hnsw).
```python
-from langchain_community.vectorstores DocArrayHnswSearch
+from langchain_community.vectorstores import DocArrayHnswSearch
```
See a [usage example](/docs/integrations/vectorstores/docarray_in_memory).
@@ -28,3 +28,10 @@ See a [usage example](/docs/integrations/vectorstores/docarray_in_memory).
from langchain_community.vectorstores DocArrayInMemorySearch
```
+## Retriever
+
+See a [usage example](/docs/integrations/retrievers/docarray_retriever).
+
+```python
+from langchain_community.retrievers import DocArrayRetriever
+```
diff --git a/docs/docs/integrations/providers/pandas.mdx b/docs/docs/integrations/providers/pandas.mdx
new file mode 100644
index 0000000000..15519b0b0f
--- /dev/null
+++ b/docs/docs/integrations/providers/pandas.mdx
@@ -0,0 +1,29 @@
+# Pandas
+
+>[pandas](https://pandas.pydata.org) is a fast, powerful, flexible and easy to use open source data analysis and manipulation tool,
+built on top of the `Python` programming language.
+
+## Installation and Setup
+
+Install the `pandas` package using `pip`:
+
+```bash
+pip install pandas
+```
+
+
+## Document loader
+
+See a [usage example](/docs/integrations/document_loaders/pandas_dataframe).
+
+```python
+from langchain_community.document_loaders import DataFrameLoader
+```
+
+## Toolkit
+
+See a [usage example](/docs/integrations/tools/pandas).
+
+```python
+from langchain_experimental.agents.agent_toolkits import create_pandas_dataframe_agent
+```