🚀 EDDI 6.5.0

19 LLM providers, knowledge bases that crawl your site and read your files, and conversations that follow compatible agent versionsWhat's new

Managed Cloud Get Started
All integrations
Data and RAGstoreType: mongodb-atlas

MongoDB Atlas Vector Search

MongoDB Atlas Vector Search as the vector store for an EDDI knowledge base, a natural fit if you already run on Atlas.

ConfigurationDocs ↗

What you get

  • A knowledge base in the Atlas cluster you already operate
  • Configuration by connection string, database, collection and index name
  • The same agent configuration as every other store

How it works in EDDI

  1. Create a vector search index in Atlas and note the database, collection and index names.
  2. Create a RagConfiguration with storeType: "mongodb-atlas" and the store parameters.
  3. Bind it with an eddi://ai.labs.rag workflow step.
  4. Select it by name in the LLM task and ingest documents.

Configuration

Taken from the EDDI documentation. Placeholders such as your-agent-id are yours to replace.

RagConfiguration (POST /ragstore/rags)The connection string carries credentials, so it is a vault reference here.
{
  "name": "product-docs",
  "embeddingProvider": "openai",
  "embeddingParameters": {
    "model": "text-embedding-3-small",
    "apiKey": "${vault:openai-key}"
  },
  "storeType": "mongodb-atlas",
  "storeParameters": {
    "connectionString": "${vault:atlas-connection-string}",
    "databaseName": "eddi",
    "collectionName": "product_docs",
    "indexName": "vector_index"
  },
  "chunkStrategy": "recursive",
  "chunkSize": 512,
  "chunkOverlap": 64,
  "maxResults": 5,
  "minScore": 0.6
}
workflow step + langchain.json taskBinding the knowledge base to the agent and using it in a task.
// 1. workflow step: binds the knowledge base to the agent
{ "type": "eddi://ai.labs.rag",
  "extensions": {},
  "config": { "uri": "eddi://ai.labs.rag/ragstore/rags/{ragId}?version=1" } }

// 2. LLM task: selects it by the "name" of the RagConfiguration
{ "tasks": [{
    "actions": ["*"],
    "type": "openai",
    "knowledgeBases": [{ "name": "product-docs", "maxResults": 5, "minScore": 0.7 }],
    "parameters": { "systemMessage": "You are a helpful assistant." }
} ] }

Governance

  • Keep the connection string in the vault, not in the configuration.
  • Embedding calls send document text to the embedding provider you configure.
  • Atlas access control and network rules apply to the vectors.

Good to know

  • Replacing a document's chunks is expected to work with Atlas but is not covered by tests. Without it, re-ingested documents can leave stale chunks.
Get startedDocs ↗

Related integrations

Data and RAGpgvectorPostgreSQL with pgvector as the vector store for an EDDI knowledge base. The recommended persistent choice when you already run PostgreSQL.Data and RAGElasticsearchElasticsearch as the vector store for an EDDI knowledge base, useful when you already run it and want keyword and vector search in one place.Data and RAGChromaChroma as the vector store for an EDDI knowledge base. The lowest-friction option when you have no existing infrastructure to reuse.

Configuration and behavior on this page follow the EDDI documentation, checked on 2026-10-14. Field names and defaults can change between releases, so confirm them in the docs for your version.