(DOCSP-53507): update notebooks for search in community

README.md

@@ -1,7 +1,7 @@
 # MongoDB Documentation Notebooks
 
 This repository contains Jupyter Notebooks that follow
-tutorials and code examples in MongoDB's official [Atlas Vector Search documentation](https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/). You can run, download, and modify these notebooks as you learn how to use MongoDB Atlas Vector Search for your use case.
+tutorials and code examples in the official [MongoDB Vector Search documentation](https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/). You can run, download, and modify these notebooks as you learn how to use MongoDB Vector Search for your use case.
 
 ## Overview
 
@@ -22,7 +22,7 @@ The following table summarizes the contents of the notebooks in each directory:
 
 ## Other Resources
 
-- [MongoDB Official Documentation](https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/)
+- [MongoDB Vector Search Documentation](https://www.mongodb.com/docs/atlas/atlas-vector-search/vector-search-overview/)
 - [Generative AI Use Cases Repository](https://github.com/mongodb-developer/GenAI-Showcase/tree/main)
 
 ## License

ai-integrations/README.md

@@ -1,10 +1,10 @@
 # AI Integrations
 
-This folder contains Jupyter Notebooks that demonstrate how to integrate various AI frameworks with MongoDB. These notebooks show you how to implement RAG and other features for your AI-powered and agentic applications by leveraging MongoDB Atlas as both a vector database and document database.
+This folder contains Jupyter Notebooks that demonstrate how to integrate various AI frameworks with MongoDB. These notebooks show you how to implement RAG and other features for your AI-powered and agentic applications by leveraging MongoDB as both a vector database and document database.
 
 | Notebook | Description |
 |----------|-------------|
-| [langchain](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/langchain.ipynb) | Implement basic RAG with LangChain and MongoDB Atlas Vector Search |
+| [langchain](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/langchain.ipynb) | Implement basic RAG with LangChain and MongoDB Vector Search |
 | [langchain-memory-semantic-cache](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/langchain-memory-semantic-cache.ipynb) | Implement RAG with memory with LangChain and MongoDB |
 | [langchain-hybrid-search](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/langchain-hybrid-search.ipynb) | Combine vector search with full-text search using LangChain and MongoDB |
 | [langchain-parent-document-retrieval](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/langchain-parent-document-retrieval.ipynb) | Perform parent-document retrieval with LangChain and MongoDB |
@@ -13,6 +13,6 @@ This folder contains Jupyter Notebooks that demonstrate how to integrate various
 | [langchain-graphrag](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/langchain-graphrag.ipynb) | Implement graph-based RAG with LangChain and MongoDB |
 | [langchain-natural-language](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/langchain-natural-language.ipynb) | Perform natural language querying with LangChain and MongoDB |
 | [langgraph](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/langgraph.ipynb) | Build an AI agent with LangGraph and MongoDB |
-| [llamaindex](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/llamaindex.ipynb) | Implement basic RAG with LlamaIndex and MongoDB Atlas |
-| [haystack](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/haystack.ipynb) | Implement basic RAG with Haystack and MongoDB Atlas |
-| [semantic-kernel](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/semantic-kernel.ipynb) | Implement basic RAG with Microsoft Semantic Kernel and MongoDB Atlas |
+| [llamaindex](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/llamaindex.ipynb) | Implement basic RAG with LlamaIndex and MongoDB |
+| [haystack](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/haystack.ipynb) | Implement basic RAG with Haystack and MongoDB |
+| [semantic-kernel](https://github.com/mongodb/docs-notebooks/blob/main/ai-integrations/semantic-kernel.ipynb) | Implement basic RAG with Microsoft Semantic Kernel and MongoDB |

ai-integrations/haystack.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Atlas Vector Search - Haystack Integration"
+    "# MongoDB Vector Search - Haystack Integration"
    ]
   },
   {

ai-integrations/langchain-graphrag.ipynb

@@ -9,7 +9,7 @@
     "\n",
     "This notebook is a companion to the [GraphRAG with MongoDB and LangChain](https://www.mongodb.com/docs/atlas/ai-integrations/langchain/graph-rag/) tutorial. Refer to the page for set-up instructions and detailed explanations.\n",
     "\n",
-    "This notebook demonstrates a GraphRAG implementation using MongoDB Atlas and LangChain. Compared to vector-based RAG, which structures your data as vector embeddings, GraphRAG structures data as a knowledge graph with entities and their relationships. This enables relationship-aware retrieval and multi-hop reasoning.\n",
+    "This notebook demonstrates a GraphRAG implementation using MongoDB and LangChain. Compared to vector-based RAG, which structures your data as vector embeddings, GraphRAG structures data as a knowledge graph with entities and their relationships. This enables relationship-aware retrieval and multi-hop reasoning.\n",
     "\n",
     "<a target=\"_blank\" href=\"https://colab.research.google.com/github/mongodb/docs-notebooks/blob/main/ai-integrations/langchain-graphrag.ipynb\">\n",
     "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
@@ -37,7 +37,7 @@
     "\n",
     "Before you begin, make sure you have the following:\n",
     "\n",
-    "- An Atlas cluster up and running (you'll need the [connection string](https://www.mongodb.com/docs/guides/atlas/connection-string/))\n",
+    "- A MongoDB cluster up and running (you'll need the [connection string](https://www.mongodb.com/docs/manual/reference/connection-string/))\n",
     "- An API key to access an LLM (This tutorial uses a model from OpenAI, but you can use any model [supported by LangChain](https://python.langchain.com/docs/integrations/chat/))"
    ]
   },
@@ -51,17 +51,17 @@
     "import os\n",
     "\n",
     "os.environ[\"OPENAI_API_KEY\"] = \"<api-key>\"\n",
-    "ATLAS_CONNECTION_STRING = \"<connection-string>\"\n",
-    "ATLAS_DB_NAME = \"langchain_db\"    # MongoDB database to store the knowledge graph\n",
-    "ATLAS_COLLECTION = \"wikipedia\"    # MongoDB collection to store the knowledge graph"
+    "MONGODB_URI = \"<connection-string>\"\n",
+    "DB_NAME = \"langchain_db\"    # MongoDB database to store the knowledge graph\n",
+    "COLLECTION = \"wikipedia\"    # MongoDB collection to store the knowledge graph"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "0adf66a8",
    "metadata": {},
    "source": [
-    "## Use MongoDB Atlas as a knowledge graph\n",
+    "## Use MongoDB as a knowledge graph\n",
     "\n",
     "Use the `MongoDBGraphStore` component to store your data as a knowledge graph. This component allows you to implement GraphRAG by storing entities (nodes) and their relationships (edges) in a MongoDB collection. It stores each entity as a document with relationship fields that reference other documents in your collection."
    ]
@@ -111,9 +111,9 @@
     "from langchain_mongodb.graphrag.graph import MongoDBGraphStore\n",
     "\n",
     "graph_store = MongoDBGraphStore(\n",
-    "    connection_string = ATLAS_CONNECTION_STRING,\n",
-    "    database_name = ATLAS_DB_NAME,\n",
-    "    collection_name = ATLAS_COLLECTION,\n",
+    "    connection_string = MONGODB_URI,\n",
+    "    database_name = DB_NAME,\n",
+    "    collection_name = COLLECTION,\n",
     "    entity_extraction_model = chat_model\n",
     ")"
    ]
@@ -125,7 +125,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Extract entities and create knowledge graph in Atlas\n",
+    "# Extract entities and create knowledge graph in MongoDB\n",
     "# This might take a few minutes; you can ignore any warnings\n",
     "graph_store.add_documents(wikipedia_docs)"
    ]
@@ -222,9 +222,9 @@
     "from IPython.display import HTML, display\n",
     "from pymongo import MongoClient\n",
     "\n",
-    "client = MongoClient(ATLAS_CONNECTION_STRING)\n",
+    "client = MongoClient(MONGODB_URI)\n",
     "\n",
-    "collection = client[ATLAS_DB_NAME][ATLAS_COLLECTION]\n",
+    "collection = client[DB_NAME][COLLECTION]\n",
     "html = visualize_graph(collection)\n",
     "\n",
     "display(HTML(html))"

ai-integrations/langchain-hybrid-search.ipynb

@@ -41,7 +41,7 @@
     "\n",
     "os.environ[\"OPENAI_API_KEY\"] = \"<api-key>\"\n",
     "os.environ[\"VOYAGE_API_KEY\"] = \"<voyage-api-key>\"\n",
-    "ATLAS_CONNECTION_STRING = \"<connection-string>\""
+    "MONGODB_URI = \"<connection-string>\""
    ]
   },
   {
@@ -55,7 +55,7 @@
     "\n",
     "# Create the vector store\n",
     "vector_store = MongoDBAtlasVectorSearch.from_connection_string(\n",
-    "   connection_string = ATLAS_CONNECTION_STRING,\n",
+    "   connection_string = MONGODB_URI,\n",
     "   embedding = VoyageAIEmbeddings(model = \"voyage-3-large\", output_dimension = 2048),\n",
     "   namespace = \"sample_mflix.embedded_movies\",\n",
     "   text_key = \"plot\",\n",
@@ -87,7 +87,7 @@
     "from pymongo import MongoClient\n",
     "\n",
     "# Connect to your cluster\n",
-    "client = MongoClient(ATLAS_CONNECTION_STRING)\n",
+    "client = MongoClient(MONGODB_URI)\n",
     "\n",
     "# Use helper method to create the search index\n",
     "create_fulltext_search_index(\n",

ai-integrations/langchain-local-rag.ipynb

@@ -167,7 +167,7 @@
     "from langchain_core.runnables import RunnablePassthrough\n",
     "import pprint\n",
     "\n",
-    "# Instantiate Atlas Vector Search as a retriever\n",
+    "# Instantiate MongoDB Vector Search as a retriever\n",
     "retriever = vector_store.as_retriever()\n",
     "\n",
     "# Define prompt template\n",

ai-integrations/langchain-natural-language.ipynb

@@ -5,17 +5,17 @@
    "id": "f9696293",
    "metadata": {},
    "source": [
-    "# Query Atlas with Natural Language Using LangChain and LangGraph"
+    "# Query MongoDB with Natural Language Using LangChain and LangGraph"
    ]
   },
   {
    "cell_type": "markdown",
    "id": "e696dea0",
    "metadata": {},
    "source": [
-    "This notebook is a companion to the [Query Atlas with Natural Language Using LangChain and LangGraph](https://www.mongodb.com/docs/atlas/ai-integrations/langchain/natural-language-to-mql/) tutorial. Refer to the page for set-up instructions and detailed explanations.\n",
+    "This notebook is a companion to the [Query MongoDB with Natural Language Using LangChain and LangGraph](https://www.mongodb.com/docs/atlas/ai-integrations/langchain/natural-language-to-mql/) tutorial. Refer to the page for set-up instructions and detailed explanations.\n",
     "\n",
-    "This notebook demonstrates how to query an Atlas cluster with a natural language prompt using an AI agent built with the [LangChain MongoDB Toolkit](https://langchain-mongodb.readthedocs.io/en/latest/langchain_mongodb/agent_toolkit/langchain_mongodb.agent_toolkit.toolkit.MongoDBDatabaseToolkit.html#langchain_mongodb.agent_toolkit.toolkit.MongoDBDatabaseToolkit) and the [LangGraph ReAct Agent Framework](https://langchain-ai.github.io/langgraph/agents/agents/).\n",
+    "This notebook demonstrates how to query a MongoDB cluster with a natural language prompt using an AI agent built with the [LangChain MongoDB Toolkit](https://langchain-mongodb.readthedocs.io/en/latest/langchain_mongodb/agent_toolkit/langchain_mongodb.agent_toolkit.toolkit.MongoDBDatabaseToolkit.html#langchain_mongodb.agent_toolkit.toolkit.MongoDBDatabaseToolkit) and the [LangGraph ReAct Agent Framework](https://langchain-ai.github.io/langgraph/agents/agents/).\n",
     "\n",
     "<a target=\"_blank\" href=\"https://colab.research.google.com/github/mongodb/docs-notebooks/blob/main/ai-integrations/langchain-natural-language.ipynb\">\n",
     "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
@@ -45,7 +45,7 @@
     "\n",
     "Before you begin, make sure you have the following:\n",
     "\n",
-    "- An Atlas cluster up and running (you'll need the [connection string](https://www.mongodb.com/docs/guides/atlas/connection-string/))\n",
+    "- A MongoDB cluster up and running (you'll need the [connection string](https://www.mongodb.com/docs/manual/reference/connection-string/))\n",
     "- An API key to access an LLM (This tutorial uses a model from OpenAI, but you can use any model [supported by LangChain](https://python.langchain.com/docs/integrations/chat/))"
    ]
   },
@@ -57,8 +57,8 @@
    "outputs": [],
    "source": [
     "os.environ[\"OPENAI_API_KEY\"] = '<api-key>'\n",
-    "ATLAS_CONNECTION_STRING = '<atlas-connection-string>'\n",
-    "ATLAS_DB_NAME = 'sample_restaurants'\n",
+    "MONGODB_URI = '<connection-string>'\n",
+    "DB_NAME = 'sample_restaurants'\n",
     "NATURAL_LANGUAGE_QUERY = 'Find all restaurants that serve hamburgers.'"
    ]
   },
@@ -107,8 +107,8 @@
     "        self.llm = ChatOpenAI(model=\"gpt-4o-mini\", timeout=60)\n",
     "        self.system_message = MONGODB_AGENT_SYSTEM_PROMPT.format(top_k=5)\n",
     "        self.db_wrapper = MongoDBDatabase.from_connection_string(\n",
-    "                            ATLAS_CONNECTION_STRING, \n",
-    "                            database=ATLAS_DB_NAME)\n",
+    "                            MONGODB_URI, \n",
+    "                            database=DB_NAME)\n",
     "        self.toolkit = MongoDBDatabaseToolkit(db=self.db_wrapper, llm=self.llm)\n",
     "        self.agent = create_react_agent(\n",
     "                        self.llm, \n",
@@ -158,25 +158,25 @@
    ]
   }
  ],
-"metadata": {
-   "kernelspec": {
-    "display_name": "Python 3",
-    "language": "python",
-    "name": "python3"
-   },
-   "language_info": {
-    "codemirror_mode": {
-     "name": "ipython",
-     "version": 3
-    },
-    "file_extension": ".py",
-    "mimetype": "text/x-python",
-    "name": "python",
-    "nbconvert_exporter": "python",
-    "pygments_lexer": "ipython3",
-    "version": "3.10.12"
-   }
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
   },
-  "nbformat": 4,
-  "nbformat_minor": 2
- }
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

ai-integrations/langchain-parent-document-retrieval.ipynb

@@ -41,7 +41,7 @@
     "\n",
     "os.environ[\"VOYAGE_API_KEY\"] = \"<voyage-api-key>\"\n",
     "os.environ[\"OPENAI_API_KEY\"] = \"<openai-api-key>\"\n",
-    "ATLAS_CONNECTION_STRING = \"<connection-string>\""
+    "MONGODB_URI = \"<connection-string>\""
    ]
   },
   {
@@ -86,7 +86,7 @@
     "\n",
     "# Create the parent document retriever\n",
     "parent_doc_retriever = MongoDBAtlasParentDocumentRetriever.from_connection_string(\n",
-    "    connection_string = ATLAS_CONNECTION_STRING,\n",
+    "    connection_string = MONGODB_URI,\n",
     "    child_splitter = child_splitter,\n",
     "    embedding_model = embedding_model,\n",
     "    database_name = database_name,\n",

ai-integrations/langchain-self-query-retrieval.ipynb

@@ -154,7 +154,7 @@
    "id": "a5762ee0",
    "metadata": {},
    "source": [
-    "## Create the Atlas Vector Search index with filters"
+    "## Create the Vector Search index with filters"
    ]
   },
   {

ai-integrations/langchain.ipynb

@@ -41,7 +41,7 @@
     "\n",
     "os.environ[\"VOYAGE_API_KEY\"] = \"<voyage-api-key>\"\n",
     "os.environ[\"OPENAI_API_KEY\"] = \"<openai-api-key>\"\n",
-    "ATLAS_CONNECTION_STRING = \"<connection-string>\""
+    "MONGODB_URI = \"<connection-string>\""
    ]
   },
   {
@@ -76,7 +76,7 @@
     "\n",
     "# Instantiate the vector store using your MongoDB connection string\n",
     "vector_store = MongoDBAtlasVectorSearch.from_connection_string(\n",
-    "  connection_string = ATLAS_CONNECTION_STRING,\n",
+    "  connection_string = MONGODB_URI,\n",
     "  namespace = \"langchain_db.test\",\n",
     "  embedding =  VoyageAIEmbeddings(model=\"voyage-3-large\"),\n",
     "  index_name = \"vector_index\"\n",
@@ -184,7 +184,7 @@
     "from langchain_openai import ChatOpenAI\n",
     "from langchain.prompts import PromptTemplate\n",
     "\n",
-    "# Instantiate Atlas Vector Search as a retriever\n",
+    "# Instantiate MongoDB Vector Search as a retriever\n",
     "retriever = vector_store.as_retriever(\n",
     "   search_type = \"similarity\",\n",
     "   search_kwargs = { \"k\": 10 }\n",
@@ -241,7 +241,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "# Instantiate Atlas Vector Search as a retriever\n",
+    "# Instantiate MongoDB Vector Search as a retriever\n",
     "retriever = vector_store.as_retriever(\n",
     "   search_type = \"similarity\",\n",
     "   search_kwargs = {\n",

ai-integrations/langgraph.ipynb

@@ -16,7 +16,7 @@
     "This notebook is a companion to the [Build AI Agents with LangGraph and MongoDB](https://www.mongodb.com/docs/atlas/ai-integrations/langgraph/build-agents) page. For the complete Python application and detailed explanations of the code, refer to the tutorial on the page.\n",
     "\n",
     "This notebook takes you through how to use LangGraph to implement agentic RAG and agent memory (short and long-term) \n",
-    "by using MongoDB Atlas as the vector database, LangChain to implement retrieval tools, and LangGraph to orchestrate the agent workflow.\n",
+    "by using MongoDB as the vector database, LangChain to implement retrieval tools, and LangGraph to orchestrate the agent workflow.\n",
     "\n",
     "<a target=\"_blank\" href=\"https://colab.research.google.com/github/mongodb/docs-notebooks/blob/main/ai-integrations/langgraph.ipynb\">\n",
     "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
@@ -33,7 +33,7 @@
     "[langchain-voyageai](https://pypi.org/project/langchain-voyageai/) package\n",
     "to ensure you're using a compatible Python version.\n",
     "\n",
-    "Before you begin, load the `sample_mflix` dataset into your Atlas cluster if you haven't already. To learn more, see [Load Data into Atlas](https://www.mongodb.com/docs/atlas/sample-data/)."
+    "Before you begin, load the `sample_mflix` dataset into your MongoDB cluster if you haven't already. To learn more, see [Sample Data](https://www.mongodb.com/docs/atlas/sample-data/)."
    ]
   },
   {
@@ -75,7 +75,7 @@
     "id": "UUf3jtFzO4-V"
    },
    "source": [
-    "## Use Atlas as a vector database"
+    "## Use MongoDB as a vector database"
    ]
   },
   {
@@ -195,7 +195,7 @@
     "    \n",
     "    # Initialize the retriever\n",
     "    retriever = MongoDBAtlasFullTextSearchRetriever(\n",
-    "       collection = collection,            # MongoDB Collection in Atlas\n",
+    "       collection = collection,            # MongoDB Collection\n",
     "       search_field = \"title\",             # Name of the field to search\n",
     "       search_index_name = \"search_index\", # Name of the search index\n",
     "       top_k = 1,                          # Number of top results to return       \n",