# Local Ollama embeddings into MongoDB Atlas Vector Search > Everything the scanned sources say about Local Ollama embeddings into MongoDB Atlas Vector Search: 22 source-anchored units across 4 sources, grouped by facet. Parent: [Ollama deployment, cloud, security and operations](https://llms-explorer.com/tree/ollama-deployment-cloud-security-and-operations/) · 6 facets · 22 facts · page: https://llms-explorer.com/tree/local-embeddings-from-ollama-into-mongodb-atlas-vector-search/ ## Definitions - modelName is the name you use in the autoEmbed index. — [source](https://docs.percona.com/percona-search-for-mongodb/configure-automatic-embedding-ollama.html) ## Structure and components - The catalog embedding-service-configs.yml is installed next to the mongot binary and already contains two ready-to-use local models pointed at Ollama: bge-m3 at 1024 dimensions and nomic-embed-text at 768 dimensions. — [source](https://docs.percona.com/percona-search-for-mongodb/configure-automatic-embedding-ollama.html) ## How-to and procedures - Create a local Atlas deployment. — [source](https://www.mongodb.com/docs/vector-search/tutorials/local-rag/) - Create a MongoDB Vector Search index on your data. — [source](https://www.mongodb.com/docs/vector-search/tutorials/local-rag/) ## Measurements and reference values - Index quantization: scalar cuts vector size 4x and mongot RAM about 3.75x; binary cuts vector size 32x and RAM about 24x (HNSW graph not compressed). MongoDB recommends it for collections over ~100,000 vectors, binary with rescoring for most models, scalar for low-dimension non-QAT models. Query vectors are quantized automatically. — [source](https://www.mongodb.com/docs/vector-search/about/vector-quantization.md) ## Problems, failure modes and limitations - nomic-embed-text is asymmetric: Percona's config sets documentPrefix 'search_document: ' and queryPrefix 'search_query: '. Ollama passes input through unchanged, so omitting prefixes gives no error but degraded retrieval. — [source](https://docs.percona.com/percona-search-for-mongodb/configure-automatic-embedding-ollama.html) ## Facts and statements - mongot autoEmbed can be pointed at Ollama via embeddingProvider OPENAI_COMPATIBLE, providerEndpoint http://localhost:11434/v1/embeddings, modelName nomic-embed-text, outputDimensions 768, empty credentials; catalog file embedding-service-configs.yml (custom via embedding.modelConfigFile, restart mongot). This is Percona's documentation. — [source](https://docs.percona.com/percona-search-for-mongodb/configure-automatic-embedding-ollama.html) - MongoDB's official local-RAG tutorial uses Ollama: it pulls nomic-embed-text for embeddings and Mistral 7B as the generator, with the Atlas CLI (v1.14.3+) and a local Atlas deployment. This applies to the .NET, Go and Java variants of the tutorial; the Node.js variant uses mxbai-embed-large-v1 and GPT4All, and the Python variant uses atlas-local-lib-py without the CLI. — [source](https://www.mongodb.com/docs/vector-search/tutorials/local-rag/) - Ollama's /api/embed returns L2-normalized (unit-length) vectors and accepts a list in input for batching, so dotProduct (which requires unit-length vectors) is valid with Ollama output; cosine also works. — [source](https://docs.ollama.com/capabilities/embeddings) - nomic-embed-text produces 768-dimension vectors, so the index needs type vector, numDimensions 768, path to the embedding field, similarity cosine; a wrong index name returns no results silently. — [source](https://dev.to/franckpachot/vector-search-index-in-mongodb-with-local-atlas-and-ollama-1p8j) - numDimensions is required and max 8192; binary quantization needs numDimensions to be a multiple of 8; cosine rejects zero-magnitude vectors. Query vectors must have the same dimension and come from the same model as stored vectors, so a model change means re-embedding and reindexing. — [source](https://www.mongodb.com/docs/vector-search/indexes/vector-search-type.md) - I create a vector search index (Ollama nomic-embed-text, like BERT, has 768 dimensions): — [source](https://dev.to/franckpachot/vector-search-index-in-mongodb-with-local-atlas-and-ollama-1p8j) - Pre-quantized ingestion: embeddings can be stored as BSON binData (float32, int8, int1); int1 supports euclidean only and needs numDimensions multiple of 8; PyMongo 4.10+, Node 6.11+ etc. MongoDB lists nomic-embed-text-v1.5 and mxbai-embed-large-v1 among models that output byte vectors. — [source](https://www.mongodb.com/docs/vector-search/about/vector-quantization.md) - Build a Local RAG Implementation with MongoDB Vector Search — [source](https://www.mongodb.com/docs/vector-search/tutorials/local-rag/) - db.eurovision.createSearchIndex( "vectorSearchOnLyrics", "vectorSearch", { fields: [ { type: "vector", numDimensions: 768, path: "embedding", similarity: "cosine" } ] } ) — [source](https://dev.to/franckpachot/vector-search-index-in-mongodb-with-local-atlas-and-ollama-1p8j) - Local Atlas deployments are intended for testing only; MongoDB says to deploy a cluster for production. A MongoDB Community or Enterprise cluster with Search and Vector Search installed is the alternative. — [source](https://www.mongodb.com/docs/vector-search/tutorials/local-rag/) - The following example uses nomic-embed-text, which produces 768-dimensional vectors in the Percona model catalog. — [source](https://docs.percona.com/percona-search-for-mongodb/configure-automatic-embedding-ollama.html) - MongoDB Vector Search Index, With Local Atlas and Ollama — [source](https://dev.to/franckpachot/vector-search-index-in-mongodb-with-local-atlas-and-ollama-1p8j) - This article discusses implementing vector search in a local MongoDB Atlas setup using Ollama and the Eurovision song lyrics dataset. We populated the database with vectorized data embedded in the documents and created a vector search index for retrieving songs based on semantic similarity. — [source](https://dev.to/franckpachot/vector-search-index-in-mongodb-with-local-atlas-and-ollama-1p8j) - Follow the Install and configure mongot procedure to set up Percona Search for MongoDB. Configure PSMDB as a replica set, point the search parameters to mongot, and create a user with the searchCoordinator role. — [source](https://docs.percona.com/percona-search-for-mongodb/configure-automatic-embedding-ollama.html) - You can use Ollama to generate embeddings locally for Percona Search for MongoDB. — [source](https://docs.percona.com/percona-search-for-mongodb/configure-automatic-embedding-ollama.html) - Local Atlas deployments are intended for testing only. For production environments, deploy a cluster. — [source](https://www.mongodb.com/docs/vector-search/tutorials/local-rag/) ## Related concepts - [ollama](https://llms-explorer.com/tree/ollama/) — is a related of Local Ollama embeddings into MongoDB Atlas Vector Search - nomic-embed-text — is a instance of Local Ollama embeddings into MongoDB Atlas Vector Search - numDimensions — is a part of Local Ollama embeddings into MongoDB Atlas Vector Search - percona — is a instance of Local Ollama embeddings into MongoDB Atlas Vector Search - mongot — is a part of Local Ollama embeddings into MongoDB Atlas Vector Search - l2-normalized — is a measure of Local Ollama embeddings into MongoDB Atlas Vector Search - search_document: — is a part of Local Ollama embeddings into MongoDB Atlas Vector Search - vector quantization — is a hyponym of Local Ollama embeddings into MongoDB Atlas Vector Search - 11434 — is a related of Local Ollama embeddings into MongoDB Atlas Vector Search