@@ -828,11 +828,25 @@ The Mem0 Memory Tool supports three different backend configurations:
828828 - Uses FAISS as the local vector store backend
829829 - Requires faiss-cpu package for local vector storage
830830
831+ 4 . ** Neptune Analytics** (Optional Graph backend for search enhancement):
832+ - Uses Neptune Analytics as the graph store backend to enhance memory recall.
833+ - Requires AWS credentials and Neptune Analytics configuration
834+ ```
835+ # Configure your Neptune Analytics graph ID in the .env file:
836+ export NEPTUNE_ANALYTICS_GRAPH_IDENTIFIER=sample-graph-id
837+
838+ # Configure your Neptune Analytics graph ID in Python code:
839+ import os
840+ os.environ['NEPTUNE_ANALYTICS_GRAPH_IDENTIFIER'] = "g-sample-graph-id"
841+
842+ ```
843+
831844| Environment Variable | Description | Default | Required For |
832845| ----------------------| -------------| ---------| --------------|
833846| MEM0_API_KEY | Mem0 Platform API key | None | Mem0 Platform |
834847| OPENSEARCH_HOST | OpenSearch Host URL | None | OpenSearch |
835848| AWS_REGION | AWS Region for OpenSearch | us-west-2 | OpenSearch |
849+ | NEPTUNE_ANALYTICS_GRAPH_IDENTIFIER | Neptune Analytics Graph Identifier | None | Neptune Analytics |
836850| DEV | Enable development mode (bypasses confirmations) | false | All modes |
837851| MEM0_LLM_PROVIDER | LLM provider for memory processing | aws_bedrock | All modes |
838852| MEM0_LLM_MODEL | LLM model for memory processing | anthropic.claude-3-5-haiku-20241022-v1:0 | All modes |
@@ -846,6 +860,7 @@ The Mem0 Memory Tool supports three different backend configurations:
846860- If ` MEM0_API_KEY ` is set, the tool will use the Mem0 Platform
847861- If ` OPENSEARCH_HOST ` is set, the tool will use OpenSearch
848862- If neither is set, the tool will default to FAISS (requires ` faiss-cpu ` package)
863+ - If ` NEPTUNE_ANALYTICS_GRAPH_IDENTIFIER ` is set, the tool will configure Neptune Analytics as graph store to enhance memory search
849864- LLM configuration applies to all backend modes and allows customization of the language model used for memory processing
850865
851866#### Bright Data Tool
0 commit comments