diff --git a/README.md b/README.md index cef142c..4a837c6 100644 --- a/README.md +++ b/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 diff --git a/ai-integrations/README.md b/ai-integrations/README.md index c7e7c58..c5e7d7e 100644 --- a/ai-integrations/README.md +++ b/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 | diff --git a/ai-integrations/haystack.ipynb b/ai-integrations/haystack.ipynb index 4ba81ad..5b4837f 100644 --- a/ai-integrations/haystack.ipynb +++ b/ai-integrations/haystack.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Haystack Integration" + "# MongoDB Vector Search - Haystack Integration" ] }, { diff --git a/ai-integrations/langchain-graphrag.ipynb b/ai-integrations/langchain-graphrag.ipynb index 8ef1026..0397fac 100644 --- a/ai-integrations/langchain-graphrag.ipynb +++ b/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", "\n", " \"Open\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/))" ] }, @@ -51,9 +51,9 @@ "import os\n", "\n", "os.environ[\"OPENAI_API_KEY\"] = \"\"\n", - "ATLAS_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 = \"\"\n", + "DB_NAME = \"langchain_db\" # MongoDB database to store the knowledge graph\n", + "COLLECTION = \"wikipedia\" # MongoDB collection to store the knowledge graph" ] }, { @@ -61,7 +61,7 @@ "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))" diff --git a/ai-integrations/langchain-hybrid-search.ipynb b/ai-integrations/langchain-hybrid-search.ipynb index 2ad2643..aee75b5 100644 --- a/ai-integrations/langchain-hybrid-search.ipynb +++ b/ai-integrations/langchain-hybrid-search.ipynb @@ -41,7 +41,7 @@ "\n", "os.environ[\"OPENAI_API_KEY\"] = \"\"\n", "os.environ[\"VOYAGE_API_KEY\"] = \"\"\n", - "ATLAS_CONNECTION_STRING = \"\"" + "MONGODB_URI = \"\"" ] }, { @@ -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", diff --git a/ai-integrations/langchain-local-rag.ipynb b/ai-integrations/langchain-local-rag.ipynb index 190319b..c4af000 100644 --- a/ai-integrations/langchain-local-rag.ipynb +++ b/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", diff --git a/ai-integrations/langchain-natural-language.ipynb b/ai-integrations/langchain-natural-language.ipynb index 93ac987..66e2d64 100644 --- a/ai-integrations/langchain-natural-language.ipynb +++ b/ai-integrations/langchain-natural-language.ipynb @@ -5,7 +5,7 @@ "id": "f9696293", "metadata": {}, "source": [ - "# Query Atlas with Natural Language Using LangChain and LangGraph" + "# Query MongoDB with Natural Language Using LangChain and LangGraph" ] }, { @@ -13,9 +13,9 @@ "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", "\n", " \"Open\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\"] = ''\n", - "ATLAS_CONNECTION_STRING = ''\n", - "ATLAS_DB_NAME = 'sample_restaurants'\n", + "MONGODB_URI = ''\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 +} diff --git a/ai-integrations/langchain-parent-document-retrieval.ipynb b/ai-integrations/langchain-parent-document-retrieval.ipynb index 8813dc8..709998a 100644 --- a/ai-integrations/langchain-parent-document-retrieval.ipynb +++ b/ai-integrations/langchain-parent-document-retrieval.ipynb @@ -41,7 +41,7 @@ "\n", "os.environ[\"VOYAGE_API_KEY\"] = \"\"\n", "os.environ[\"OPENAI_API_KEY\"] = \"\"\n", - "ATLAS_CONNECTION_STRING = \"\"" + "MONGODB_URI = \"\"" ] }, { @@ -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", diff --git a/ai-integrations/langchain-self-query-retrieval.ipynb b/ai-integrations/langchain-self-query-retrieval.ipynb index 1fab672..b02e975 100644 --- a/ai-integrations/langchain-self-query-retrieval.ipynb +++ b/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" ] }, { diff --git a/ai-integrations/langchain.ipynb b/ai-integrations/langchain.ipynb index 4779bac..4cc08ca 100644 --- a/ai-integrations/langchain.ipynb +++ b/ai-integrations/langchain.ipynb @@ -41,7 +41,7 @@ "\n", "os.environ[\"VOYAGE_API_KEY\"] = \"\"\n", "os.environ[\"OPENAI_API_KEY\"] = \"\"\n", - "ATLAS_CONNECTION_STRING = \"\"" + "MONGODB_URI = \"\"" ] }, { @@ -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", diff --git a/ai-integrations/langgraph.ipynb b/ai-integrations/langgraph.ipynb index 68f75df..7bfa59d 100644 --- a/ai-integrations/langgraph.ipynb +++ b/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", "\n", " \"Open\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", diff --git a/ai-integrations/llamaindex.ipynb b/ai-integrations/llamaindex.ipynb index d580eed..404cbff 100644 --- a/ai-integrations/llamaindex.ipynb +++ b/ai-integrations/llamaindex.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - LlamaIndex Integration" + "# MongoDB Vector Search - LlamaIndex Integration" ] }, { @@ -41,7 +41,7 @@ "\n", "os.environ[\"VOYAGEAI_API_KEY\"] = \"\"\n", "os.environ[\"OPENAI_API_KEY\"] = \"\"\n", - "ATLAS_CONNECTION_STRING = \"\"" + "MONGODB_URI = \"\"" ] }, { @@ -92,8 +92,8 @@ "from llama_index.core import StorageContext\n", "from llama_index.vector_stores.mongodb import MongoDBAtlasVectorSearch\n", "\n", - "# Connect to your Atlas cluster\n", - "mongo_client = pymongo.MongoClient(ATLAS_CONNECTION_STRING)\n", + "# Connect to your MongoDB cluster\n", + "mongo_client = pymongo.MongoClient(MONGODB_URI)\n", "\n", "# Instantiate the vector store\n", "atlas_vector_store = MongoDBAtlasVectorSearch(\n", @@ -229,7 +229,7 @@ "from llama_index.core.query_engine import RetrieverQueryEngine\n", "import pprint\n", "\n", - "# Instantiate Atlas Vector Search as a retriever\n", + "# Instantiate MongoDB Vector Search as a retriever\n", "vector_store_retriever = VectorIndexRetriever(index=vector_store_index, similarity_top_k=5)\n", "\n", "# Pass the retriever into the query engine\n", @@ -265,7 +265,7 @@ " filters=[ExactMatchFilter(key=\"metadata.page_label\", value=\"2\")]\n", ")\n", "\n", - "# Instantiate Atlas Vector Search as a retriever\n", + "# Instantiate MongoDB Vector Search as a retriever\n", "vector_store_retriever = VectorIndexRetriever(index=vector_store_index, filters=metadata_filters, similarity_top_k=5)\n", "\n", "# Pass the retriever into the query engine\n", diff --git a/ai-integrations/semantic-kernel.ipynb b/ai-integrations/semantic-kernel.ipynb index 0c1aff5..a8a5ad0 100644 --- a/ai-integrations/semantic-kernel.ipynb +++ b/ai-integrations/semantic-kernel.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Semantic Kernel Integration" + "# MongoDB Vector Search - Semantic Kernel Integration" ] }, { @@ -55,7 +55,7 @@ "outputs": [], "source": [ "OPENAI_API_KEY = \"\"\n", - "ATLAS_CONNECTION_STRING = \"\"" + "MONGODB_URI = \"\"" ] }, { @@ -93,7 +93,7 @@ "outputs": [], "source": [ "mongodb_atlas_memory_store = MongoDBAtlasMemoryStore(\n", - " connection_string=ATLAS_CONNECTION_STRING,\n", + " connection_string=MONGODB_URI,\n", " database_name=\"semantic_kernel_db\",\n", " index_name=\"vector_index\"\n", ")\n", @@ -136,8 +136,8 @@ "metadata": {}, "outputs": [], "source": [ - "# Connect to your Atlas cluster and specify the collection\n", - "client = MongoClient(ATLAS_CONNECTION_STRING)\n", + "# Connect to your MongoDB cluster and specify the collection\n", + "client = MongoClient(MONGODB_URI)\n", "collection = client[\"semantic_kernel_db\"][\"test\"]\n", "\n", "# Create your index model, then create the search index\n", diff --git a/create-embeddings/README.md b/create-embeddings/README.md index dc2b977..62febaf 100644 --- a/create-embeddings/README.md +++ b/create-embeddings/README.md @@ -5,13 +5,13 @@ vector embeddings. Select one of the following notebooks based on your preferred embedding model, and whether you're generating embeddings from -new data or from data you already have in MongoDB Atlas. +new data or from data you already have in MongoDB. | Notebook | Description | |----------|-------------| | [open-source-new-data](https://github.com/mongodb/docs-notebooks/blob/main/create-embeddings/open-source-new-data.ipynb) | Generate embeddings from new data using an open-source embedding model | -| [open-source-existing-data](https://github.com/mongodb/docs-notebooks/blob/main/create-embeddings/open-source-existing-data.ipynb) | Generate embeddings from existing data in Atlas using an open-source embedding model | +| [open-source-existing-data](https://github.com/mongodb/docs-notebooks/blob/main/create-embeddings/open-source-existing-data.ipynb) | Generate embeddings from existing data in MongoDB using an open-source embedding model | | [voyage-new-data](https://github.com/mongodb/docs-notebooks/blob/main/create-embeddings/voyage-new-data.ipynb) | Generate embeddings from new data using an embedding model from Voyage AI | -| [voyage-existing-data](https://github.com/mongodb/docs-notebooks/blob/main/create-embeddings/voyage-existing-data.ipynb) | Generate embeddings from existing data in Atlas using an embedding model from Voyage AI | +| [voyage-existing-data](https://github.com/mongodb/docs-notebooks/blob/main/create-embeddings/voyage-existing-data.ipynb) | Generate embeddings from existing data in MongoDB using an embedding model from Voyage AI | | [openai-new-data](https://github.com/mongodb/docs-notebooks/blob/main/create-embeddings/openai-new-data.ipynb) | Generate embeddings from new data using an embedding model from OpenAI | -| [openai-existing-data](https://github.com/mongodb/docs-notebooks/blob/main/create-embeddings/voyage-existing-data.ipynb) | Generate embeddings from existing data in Atlas using an embedding model from OpenAI | +| [openai-existing-data](https://github.com/mongodb/docs-notebooks/blob/main/create-embeddings/voyage-existing-data.ipynb) | Generate embeddings from existing data in MongoDB using an embedding model from OpenAI | diff --git a/create-embeddings/open-source-existing-data.ipynb b/create-embeddings/open-source-existing-data.ipynb index d592840..4b39b1e 100644 --- a/create-embeddings/open-source-existing-data.ipynb +++ b/create-embeddings/open-source-existing-data.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Create Embeddings - Open Source - Existing Data" + "# MongoDB Vector Search - Create Embeddings - Open Source - Existing Data" ] }, { @@ -13,7 +13,7 @@ "source": [ "This notebook is a companion to the [Create Embeddings](https://www.mongodb.com/docs/atlas/atlas-vector-search/create-embeddings/) page. Refer to the page for set-up instructions and detailed explanations.\n", "\n", - "This notebook takes you through how to generate embeddings from **existing data in Atlas** by using the open-source ``nomic-embed-text-v1`` model.\n", + "This notebook takes you through how to generate embeddings from **existing data in MongoDB** by using the open-source ``nomic-embed-text-v1`` model.\n", "\n", "\n", " \"Open\n", @@ -108,7 +108,7 @@ "source": [ "import pymongo\n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "mongo_client = pymongo.MongoClient(\"\")\n", "db = mongo_client[\"sample_airbnb\"]\n", "collection = db[\"listingsAndReviews\"]\n", diff --git a/create-embeddings/open-source-new-data.ipynb b/create-embeddings/open-source-new-data.ipynb index 5116174..741635c 100644 --- a/create-embeddings/open-source-new-data.ipynb +++ b/create-embeddings/open-source-new-data.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Create Embeddings - Open Source - New Data" + "# MongoDB Vector Search - Create Embeddings - Open Source - New Data" ] }, { @@ -139,7 +139,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Ingest Embeddings into Atlas" + "## Ingest Embeddings into MongoDB" ] }, { @@ -178,12 +178,12 @@ "source": [ "import pymongo\n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "mongo_client = pymongo.MongoClient(\"\")\n", "db = mongo_client[\"sample_db\"]\n", "collection = db[\"embeddings\"]\n", "\n", - "# Ingest data into Atlas\n", + "# Ingest data into MongoDB\n", "collection.insert_many(docs)" ] }, diff --git a/create-embeddings/openai-existing-data.ipynb b/create-embeddings/openai-existing-data.ipynb index 4591c6e..3fd4e1c 100644 --- a/create-embeddings/openai-existing-data.ipynb +++ b/create-embeddings/openai-existing-data.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Create Embeddings - OpenAI - Existing Data" + "# MongoDB Vector Search - Create Embeddings - OpenAI - Existing Data" ] }, { @@ -13,7 +13,7 @@ "source": [ "This notebook is a companion to the [Create Embeddings](https://www.mongodb.com/docs/atlas/atlas-vector-search/create-embeddings/) page. Refer to the page for set-up instructions and detailed explanations.\n", "\n", - "This notebook takes you through how to generate embeddings from **existing data in Atlas** by using OpenAI's ``text-embedding-3-small`` model.\n", + "This notebook takes you through how to generate embeddings from **existing data in MongoDB** by using OpenAI's ``text-embedding-3-small`` model.\n", "\n", "\n", " \"Open\n", @@ -114,7 +114,7 @@ "source": [ "import pymongo\n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "mongo_client = pymongo.MongoClient(\"\")\n", "db = mongo_client[\"sample_airbnb\"]\n", "collection = db[\"listingsAndReviews\"]\n", diff --git a/create-embeddings/openai-new-data.ipynb b/create-embeddings/openai-new-data.ipynb index 09b09cd..0682bb6 100644 --- a/create-embeddings/openai-new-data.ipynb +++ b/create-embeddings/openai-new-data.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Create Embeddings - OpenAI - New Data" + "# MongoDB Vector Search - Create Embeddings - OpenAI - New Data" ] }, { @@ -145,7 +145,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Ingest Embeddings into Atlas" + "## Ingest Embeddings into MongoDB" ] }, { @@ -184,12 +184,12 @@ "source": [ "import pymongo\n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "mongo_client = pymongo.MongoClient(\"\")\n", "db = mongo_client[\"sample_db\"]\n", "collection = db[\"embeddings\"]\n", "\n", - "# Ingest data into Atlas\n", + "# Ingest data into MongoDB\n", "collection.insert_many(docs)" ] }, diff --git a/create-embeddings/voyage-existing-data.ipynb b/create-embeddings/voyage-existing-data.ipynb index 30fe05b..063eaef 100644 --- a/create-embeddings/voyage-existing-data.ipynb +++ b/create-embeddings/voyage-existing-data.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Create Embeddings - Voyage AI - Existing Data" + "# MongoDB Vector Search - Create Embeddings - Voyage AI - Existing Data" ] }, { @@ -13,7 +13,7 @@ "source": [ "This notebook is a companion to the [Create Embeddings](https://www.mongodb.com/docs/atlas/atlas-vector-search/create-embeddings/) page. Refer to the page for set-up instructions and detailed explanations.\n", "\n", - "This notebook takes you through how to generate embeddings from **existing data in Atlas** by using the ``voyage-3-large`` model from Voyage AI.\n", + "This notebook takes you through how to generate embeddings from **existing data in MongoDB** by using the ``voyage-3-large`` model from Voyage AI.\n", "\n", "\n", " \"Open\n", @@ -114,7 +114,7 @@ "source": [ "import pymongo\n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "mongo_client = pymongo.MongoClient(\"\")\n", "db = mongo_client[\"sample_airbnb\"]\n", "collection = db[\"listingsAndReviews\"]\n", diff --git a/create-embeddings/voyage-new-data.ipynb b/create-embeddings/voyage-new-data.ipynb index 4197639..64155be 100644 --- a/create-embeddings/voyage-new-data.ipynb +++ b/create-embeddings/voyage-new-data.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Create Embeddings - Voyage AI - New Data" + "# MongoDB Vector Search - Create Embeddings - Voyage AI - New Data" ] }, { @@ -145,7 +145,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "## Ingest Embeddings into Atlas" + "## Ingest Embeddings into MongoDB" ] }, { @@ -184,12 +184,12 @@ "source": [ "import pymongo\n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "mongo_client = pymongo.MongoClient(\"\")\n", "db = mongo_client[\"sample_db\"]\n", "collection = db[\"embeddings\"]\n", "\n", - "# Ingest data into Atlas\n", + "# Ingest data into MongoDB\n", "collection.insert_many(docs)" ] }, diff --git a/get-started/quick-start.ipynb b/get-started/quick-start.ipynb index 4f3240e..04d4e07 100644 --- a/get-started/quick-start.ipynb +++ b/get-started/quick-start.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search Quick Start" + "# MongoDB Vector Search Quick Start" ] }, { @@ -41,7 +41,7 @@ "from pymongo.operations import SearchIndexModel\n", "import time\n", "\n", - "# Connect to your Atlas deployment\n", + "# Connect to your MongoDB cluster\n", "uri = \"\"\n", "client = MongoClient(uri)\n", "\n", diff --git a/manage-indexes/create-indexes-basic.ipynb b/manage-indexes/create-indexes-basic.ipynb index d253117..84727c3 100644 --- a/manage-indexes/create-indexes-basic.ipynb +++ b/manage-indexes/create-indexes-basic.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Create Vector Indexes - Basic Example" + "# MongoDB Vector Search - Create Vector Indexes - Basic Example" ] }, { @@ -41,7 +41,7 @@ "from pymongo.operations import SearchIndexModel\n", "import time\n", "\n", - "# Connect to your Atlas deployment\n", + "# Connect to your MongoDB cluster\n", "uri = \"\"\n", "client = MongoClient(uri)\n", "\n", diff --git a/manage-indexes/create-indexes-filter.ipynb b/manage-indexes/create-indexes-filter.ipynb index 4226e4a..35fdbd4 100644 --- a/manage-indexes/create-indexes-filter.ipynb +++ b/manage-indexes/create-indexes-filter.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Create Vector Indexes - Filter Example" + "# MongoDB Vector Search - Create Vector Indexes - Filter Example" ] }, { @@ -41,7 +41,7 @@ "from pymongo.operations import SearchIndexModel\n", "import time\n", "\n", - "# Connect to your Atlas deployment\n", + "# Connect to your MongoDB cluster\n", "uri = \"\"\n", "client = MongoClient(uri)\n", "\n", diff --git a/manage-indexes/delete-indexes.ipynb b/manage-indexes/delete-indexes.ipynb index 3b92a03..66f6389 100644 --- a/manage-indexes/delete-indexes.ipynb +++ b/manage-indexes/delete-indexes.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Delete Vector Indexes" + "# MongoDB Vector Search - Delete Vector Indexes" ] }, { @@ -39,7 +39,7 @@ "source": [ "from pymongo.mongo_client import MongoClient\n", "\n", - "# Connect to your Atlas deployment\n", + "# Connect to your MongoDB cluster\n", "uri = \"\"\n", "client = MongoClient(uri)\n", "\n", diff --git a/manage-indexes/edit-indexes.ipynb b/manage-indexes/edit-indexes.ipynb index bbcb64d..8af4647 100644 --- a/manage-indexes/edit-indexes.ipynb +++ b/manage-indexes/edit-indexes.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Edit Vector Indexes" + "# MongoDB Vector Search - Edit Vector Indexes" ] }, { @@ -39,7 +39,7 @@ "source": [ "from pymongo.mongo_client import MongoClient\n", "\n", - "# Connect to your Atlas deployment\n", + "# Connect to your MongoDB cluster\n", "uri = \"\"\n", "client = MongoClient(uri)\n", "\n", diff --git a/manage-indexes/view-indexes.ipynb b/manage-indexes/view-indexes.ipynb index ac1e35f..c45b833 100644 --- a/manage-indexes/view-indexes.ipynb +++ b/manage-indexes/view-indexes.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - View Vector Indexes" + "# MongoDB Vector Search - View Vector Indexes" ] }, { @@ -39,7 +39,7 @@ "source": [ "from pymongo.mongo_client import MongoClient\n", "\n", - "# Connect to your Atlas deployment\n", + "# Connect to your MongoDB cluster\n", "uri = \"\"\n", "client = MongoClient(uri)\n", "\n", diff --git a/quantization/existing-data.ipynb b/quantization/existing-data.ipynb index 228f454..fd74527 100644 --- a/quantization/existing-data.ipynb +++ b/quantization/existing-data.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Vector Quantization - Existing Data" + "# MongoDB Vector Search - Vector Quantization - Existing Data" ] }, { @@ -73,7 +73,7 @@ "source": [ "import pymongo \n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "mongo_client = pymongo.MongoClient(\"\")\n", "db = mongo_client[\"sample_airbnb\"]\n", "collection = db[\"listingsAndReviews\"]\n", diff --git a/quantization/new-data.ipynb b/quantization/new-data.ipynb index 55bb0dd..e238a44 100644 --- a/quantization/new-data.ipynb +++ b/quantization/new-data.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Vector Quantization - New Data" + "# MongoDB Vector Search - Vector Quantization - New Data" ] }, { diff --git a/run-queries/ann-basic.ipynb b/run-queries/ann-basic.ipynb index cad7471..878c4f2 100644 --- a/run-queries/ann-basic.ipynb +++ b/run-queries/ann-basic.ipynb @@ -8,7 +8,7 @@ } }, "source": [ - "# Atlas Vector Search - Run Queries - ANN Basic" + "# MongoDB Vector Search - Run Queries - ANN Basic" ] }, { @@ -47,7 +47,7 @@ "source": [ "import pymongo\n", "\n", - "# connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "client = pymongo.MongoClient(\"\")\n", "\n", "# define pipeline\n", diff --git a/run-queries/ann-filter.ipynb b/run-queries/ann-filter.ipynb index 25eff0f..a8fb720 100644 --- a/run-queries/ann-filter.ipynb +++ b/run-queries/ann-filter.ipynb @@ -8,7 +8,7 @@ } }, "source": [ - "# Atlas Vector Search - Run Queries - ANN with Filter" + "# MongoDB Vector Search - Run Queries - ANN with Filter" ] }, { @@ -47,7 +47,7 @@ "source": [ "import pymongo\n", "\n", - "# connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "client = pymongo.MongoClient(\"\")\n", "\n", "# define pipeline\n", diff --git a/run-queries/enn.ipynb b/run-queries/enn.ipynb index 0178ee3..a961d4c 100644 --- a/run-queries/enn.ipynb +++ b/run-queries/enn.ipynb @@ -8,7 +8,7 @@ } }, "source": [ - "# Atlas Vector Search - Run Queries - ENN" + "# MongoDB Vector Search - Run Queries - ENN" ] }, { @@ -47,7 +47,7 @@ "source": [ "import pymongo\n", "\n", - "# connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "client = pymongo.MongoClient(\"\")\n", "\n", "# define pipeline\n", diff --git a/run-queries/semantic-search.ipynb b/run-queries/semantic-search.ipynb index 7266f5f..f3ff553 100644 --- a/run-queries/semantic-search.ipynb +++ b/run-queries/semantic-search.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Semantic Search for Text" + "# MongoDB Vector Search - Semantic Search for Text" ] }, { @@ -41,7 +41,7 @@ "from pymongo.operations import SearchIndexModel\n", "import time\n", "\n", - "# Connect to your Atlas deployment\n", + "# Connect to your MongoDB cluster\n", "uri = \"\"\n", "client = MongoClient(uri)\n", "\n", diff --git a/use-cases/ai-agent.ipynb b/use-cases/ai-agent.ipynb index 26b5174..79c72cd 100644 --- a/use-cases/ai-agent.ipynb +++ b/use-cases/ai-agent.ipynb @@ -6,16 +6,16 @@ "id": "3kMALXaMv-MS" }, "source": [ - "# Build an AI Agent with MongoDB Atlas" + "# Build an AI Agent with MongoDB" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "This notebook is a companion to the [Build AI Agents with MongoDB Atlas](https://www.mongodb.com/docs/atlas/atlas-vector-search/build-agents) page. For a more traditional Python development example and detailed explanations of the code, refer to the tutorial on the page.\n", + "This notebook is a companion to the [Build AI Agents with MongoDB](https://www.mongodb.com/docs/atlas/atlas-vector-search/ai-agents) page. For a more traditional Python development example and detailed explanations of the code, refer to the tutorial on the page.\n", "\n", - "This notebook demonstrates an AI agent that uses MongoDB Atlas as the database for both agentic RAG and agent memory.\n", + "This notebook demonstrates an AI agent that uses MongoDB as the database for both agentic RAG and agent memory.\n", "\n", "\n", " \"Open\n", @@ -66,8 +66,8 @@ "id": "UUf3jtFzO4-V" }, "source": [ - "## Use Atlas as a vector database\n", - "In this section, you configure the embedding model, chunk and ingest your data into a collection in Atlas, and then create a vector search index on your data to enable vector search." + "## Use MongoDB as a vector database\n", + "In this section, you configure the embedding model, chunk and ingest your data into a MongoDB collection, and then create a vector search index on your data to enable vector search." ] }, { @@ -100,7 +100,7 @@ "from langchain_community.document_loaders import PyPDFLoader\n", "from langchain.text_splitter import RecursiveCharacterTextSplitter\n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "mongo_client = MongoClient(MONGODB_URI)\n", "collection = mongo_client[\"agent_db\"][\"test\"]\n", "\n", diff --git a/use-cases/local-rag.ipynb b/use-cases/local-rag.ipynb index 14b7c94..580db8e 100644 --- a/use-cases/local-rag.ipynb +++ b/use-cases/local-rag.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Local Retrieval-Augmented Generation (RAG)" + "# MongoDB Vector Search - Local Retrieval-Augmented Generation (RAG)" ] }, { @@ -13,7 +13,7 @@ "source": [ "This notebook is a companion to the [Local Retrieval-Augmented Generation (RAG)](https://www.mongodb.com/docs/atlas/atlas-vector-search/tutorials/local-rag/) page. Refer to the page for set-up instructions and detailed explanations.\n", "\n", - "This notebook takes you a RAG implementation with Atlas Vector Search that you can run **completely locally** by using models from Hugging Face and GPT4All.\n", + "This notebook takes you a RAG implementation with MongoDB Vector Search that you can run **completely locally** by using models from Hugging Face and GPT4All.\n", "\n", "\n", " \"Open\n", @@ -67,7 +67,7 @@ "from pymongo import MongoClient\n", "from sentence_transformers import SentenceTransformer\n", "\n", - "# Connect to your local Atlas deployment or Atlas Cluster\n", + "# Connect to your local Atlas deployment or MongoDB cluster\n", "client = MongoClient(MONGODB_URI)\n", "\n", "# Select the sample_airbnb.listingsAndReviews collection\n", diff --git a/use-cases/rag-with-voyage.ipynb b/use-cases/rag-with-voyage.ipynb index 7c8f227..2a07e1b 100644 --- a/use-cases/rag-with-voyage.ipynb +++ b/use-cases/rag-with-voyage.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Retrieval-Augmented Generation (RAG)" + "# MongoDB Vector Search - Retrieval-Augmented Generation (RAG)" ] }, { @@ -13,7 +13,7 @@ "source": [ "This notebook is a companion to the [Retrieval-Augmented Generation (RAG)](https://www.mongodb.com/docs/atlas/atlas-vector-search/rag/#get-started) tutorial. Refer to the page for set-up instructions and detailed explanations.\n", "\n", - "This notebook takes you through how to implement RAG with Atlas Vector Search by using the ``voyage-3-large`` embedding model from Voyage AI and an open-source generative model from Hugging Face.\n", + "This notebook takes you through how to implement RAG with MongoDB Vector Search by using the ``voyage-3-large`` embedding model from Voyage AI and an open-source generative model from Hugging Face.\n", "\n", "\n", " \"Open\n", @@ -105,7 +105,7 @@ "source": [ "from pymongo import MongoClient\n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "client = MongoClient(\"\")\n", "collection = client[\"rag_db\"][\"test\"]\n", "\n", diff --git a/use-cases/rag.ipynb b/use-cases/rag.ipynb index 479bb45..ca88d86 100644 --- a/use-cases/rag.ipynb +++ b/use-cases/rag.ipynb @@ -4,7 +4,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "# Atlas Vector Search - Retrieval-Augmented Generation (RAG)" + "# MongoDB Vector Search - Retrieval-Augmented Generation (RAG)" ] }, { @@ -13,7 +13,7 @@ "source": [ "This notebook is a companion to the [Retrieval-Augmented Generation (RAG)](https://www.mongodb.com/docs/atlas/atlas-vector-search/rag/#get-started) tutorial. Refer to the page for set-up instructions and detailed explanations.\n", "\n", - "This notebook takes you through how to implement RAG with Atlas Vector Search by using open-source models from Hugging Face.\n", + "This notebook takes you through how to implement RAG with MongoDB Vector Search by using open-source models from Hugging Face.\n", "\n", "\n", " \"Open\n", @@ -103,7 +103,7 @@ "source": [ "from pymongo import MongoClient\n", "\n", - "# Connect to your Atlas cluster\n", + "# Connect to your MongoDB cluster\n", "client = MongoClient(\"\")\n", "collection = client[\"rag_db\"][\"test\"]\n", "\n",