docs: integrations updates 21

docs/docs/integrations/providers/byte_dance.mdx

@@ -8,15 +8,23 @@ Get the access token.
 You can find the access instructions [here](https://open.larksuite.com/document)
 
 
-## Document Loader
-
-### Lark Suite
+## Document Loaders
 
 >[Lark Suite](https://www.larksuite.com/) is an enterprise collaboration platform 
 > developed by `ByteDance`.
 
-See a [usage example](/docs/integrations/document_loaders/larksuite).
+### Lark Suite for Document
+
+See a [usage example](/docs/integrations/document_loaders/larksuite/#load-from-document).
 
 ```python
 from langchain_community.document_loaders.larksuite import LarkSuiteDocLoader
 ```
+
+### Lark Suite for Wiki
+
+See a [usage example](/docs/integrations/document_loaders/larksuite/#load-from-wiki).
+
+```python
+from langchain_community.document_loaders.larksuite import LarkSuiteWikiLoader
+```

docs/docs/integrations/providers/localai.mdx

@@ -0,0 +1,24 @@
+# LocalAI
+
+>[LocalAI](https://localai.io/) is the free, Open Source OpenAI alternative. 
+> `LocalAI` act as a drop-in replacement REST API that’s compatible with OpenAI API 
+> specifications for local inferencing. It allows you to run LLMs, generate images, 
+> audio (and not only) locally or on-prem with consumer grade hardware, 
+> supporting multiple model families and architectures.
+
+## Installation and Setup
+
+We have to install several python packages: 
+
+```bash
+pip install tenacity openai
+```
+
+
+## Embedding models
+
+See a [usage example](/docs/integrations/text_embedding/localai).
+
+```python
+from langchain_community.embeddings import LocalAIEmbeddings
+```

docs/docs/integrations/providers/milvus.mdx

@@ -9,17 +9,25 @@
 Install the Python SDK:
 
 ```bash
-pip install pymilvus
+pip install pymilvus langchain-milvus
 ```
 
 ## Vector Store
 
-There exists a wrapper around `Milvus` indexes, allowing you to use it as a vectorstore,
-whether for semantic search or example selection.
+See a [usage example](/docs/integrations/vectorstores/milvus).
 
 To import this vectorstore:
 ```python
-from langchain_community.vectorstores import Milvus
+from langchain_milvus import Milvus
+```
+
+## Retrievers
+
+See a [usage example](/docs/integrations/retrievers/milvus_hybrid_search).
+
+To import this vectorstore:
+```python
+from langchain_milvus.retrievers import MilvusCollectionHybridSearchRetriever
+from langchain_milvus.utils.sparse import BM25SparseEmbedding
 ```
 
-For a more detailed walkthrough of the `Miluvs` wrapper, see [this notebook](/docs/integrations/vectorstores/milvus)

docs/docs/integrations/providers/mongodb.mdx

@@ -0,0 +1,24 @@
+# MongoDB
+
+>[MongoDB](https://www.mongodb.com/) is a NoSQL, document-oriented 
+> database that supports JSON-like documents with a dynamic schema.
+
+**NOTE:** 
+- See other `MongoDB` integrations on the [MongoDB Atlas page](/docs/integrations/providers/mongodb_atlas).
+
+## Installation and Setup
+
+Install the Python package:
+
+```bash
+pip install langchain-mongodb
+```
+
+## Message Histories
+
+See a [usage example](/docs/integrations/memory/mongodb_chat_message_history).
+
+To import this vectorstore:
+```python
+from langchain_mongodb.chat_message_histories import MongoDBChatMessageHistory
+```

docs/docs/integrations/providers/mongodb_atlas.mdx

@@ -22,10 +22,30 @@ See a [usage example](/docs/integrations/vectorstores/mongodb_atlas).
 from langchain_mongodb import MongoDBAtlasVectorSearch
 ```
 
+## Retrievers
 
-## LLM Caches
+### Full Text Search Retriever
+
+>`Hybrid Search Retriever` performs full-text searches using 
+> Lucene’s standard (`BM25`) analyzer.
+
+```python
+from langchain_mongodb.retrievers.full_text_search import MongoDBAtlasFullTextSearchRetriever
+```
+
+### Hybrid Search Retriever
+
+>`Hybrid Search Retriever` combines vector and full-text searches weighting 
+> them the via `Reciprocal Rank Fusion` (`RRF`) algorithm.
+
+```python
+from langchain_mongodb.retrievers.hybrid_search import MongoDBAtlasHybridSearchRetriever
+```
+
+## Model Caches
 
 ### MongoDBCache
+
 An abstraction to store a simple cache in MongoDB. This does not use Semantic Caching, nor does it require an index to be made on the collection before generation.
 
 To import this cache: