FalkorDB graph database integration

README.md

@@ -160,7 +160,7 @@ history = m.history(memory_id=<memory_id_1>)
 
 ### Graph Memory
 To initialize Graph Memory you'll need to set up your configuration with graph store providers.
-Currently, we support Neo4j as a graph store provider. You can setup [Neo4j](https://neo4j.com/) locally or use the hosted [Neo4j AuraDB](https://neo4j.com/product/auradb/). 
+Currently, we support FalkorDB and Neo4j as a graph store providers. You can set up [FalkorDB](https://www.falkordb.com/) or [Neo4j](https://neo4j.com/) locally or use the hosted [FalkorDB Cloud](https://app.falkordb.cloud/) or [Neo4j AuraDB](https://neo4j.com/product/auradb/). 
 Moreover, you also need to set the version to `v1.1` (*prior versions are not supported*). 
 Here's how you can do it:
 
@@ -169,11 +169,12 @@ from mem0 import Memory
 
 config = {
     "graph_store": {
-        "provider": "neo4j",
+        "provider": "falkordb",
         "config": {
-            "url": "neo4j+s://xxx",
-            "username": "neo4j",
-            "password": "xxx"
+            "host": "---"
+            "username": "---",
+            "password": "---",
+            "port": "---"
         }
     },
     "version": "v1.1"

cookbooks/mem0_graph_memory.py

@@ -0,0 +1,40 @@
+# This example shows how to use graph config to use falkordb graph databese
+import os
+from mem0 import Memory
+from dotenv import load_dotenv
+
+# Loading OpenAI API Key
+load_dotenv()
+OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY')
+USER_ID = "test"
+
+# Creating the config dict from the environment variables
+config = {
+    "llm": { # This is the language model configuration, use your carditionals
+        "provider": "openai",
+        "config": {
+            "model": "gpt-4o-mini",
+            "temperature": 0
+        }
+    },
+    "graph_store": { # See https://app.falkordb.cloud/ for the carditionals
+        "provider": "falkordb",
+        "config": {
+            "host": os.environ['HOST'],
+            "username": os.environ['USERNAME'],
+            "password": os.environ['PASSWORD'],
+            "port": os.environ['PORT']
+        }
+    },
+    "version": "v1.1"
+}
+
+# Create the memory class using from config
+memory = Memory.from_config(config_dict=config)
+
+# Use the Mem0 to add and search memories
+memory.add("I like painting", user_id=USER_ID)
+memory.add("I hate playing badminton", user_id=USER_ID)
+print(memory.get_all(user_id=USER_ID))
+memory.add("My friend name is john and john has a dog named tommy", user_id=USER_ID)
+print(memory.search("What I like to do", user_id=USER_ID))

docs/open-source/graph_memory/features.mdx

@@ -19,11 +19,13 @@ from mem0 import Memory
 
 config = {
     "graph_store": {
-        "provider": "neo4j",
+        "provider": "falkordb",
         "config": {
-            "url": "neo4j+s://xxx",
-            "username": "neo4j",
-            "password": "xxx"
+            "Database": "falkordb",
+            "host": "---"
+            "username": "---",
+            "password": "---",
+            "port": "---"
         },
         "custom_prompt": "Please only extract entities containing sports related relationships and nothing else.",
     },

docs/open-source/graph_memory/overview.mdx

@@ -36,12 +36,11 @@ allowfullscreen
 ## Initialize Graph Memory
 
 To initialize Graph Memory you'll need to set up your configuration with graph store providers.
-Currently, we support Neo4j as a graph store provider. You can setup [Neo4j](https://neo4j.com/) locally or use the hosted [Neo4j AuraDB](https://neo4j.com/product/auradb/). 
-Moreover, you also need to set the version to `v1.1` (*prior versions are not supported*).
+Currently, we support FalkorDB and Neo4j as a graph store providers. You can set up [FalkorDB](https://www.falkordb.com/) or [Neo4j](https://neo4j.com/) locally or use the hosted [FalkorDB Cloud](https://app.falkordb.cloud/) or [Neo4j AuraDB](https://neo4j.com/product/auradb/). 
+Moreover, you also need to set the version to `v1.1` (*prior versions are not supported*). 
 
 <Note>If you are using Neo4j locally, then you need to install [APOC plugins](https://neo4j.com/labs/apoc/4.1/installation/).</Note>
 
-
 User can also customize the LLM for Graph Memory from the [Supported LLM list](https://docs.mem0.ai/components/llms/overview) with three levels of configuration:
 
 1. **Main Configuration**: If `llm` is set in the main config, it will be used for all graph operations.
@@ -57,11 +56,13 @@ from mem0 import Memory
 
 config = {
     "graph_store": {
-        "provider": "neo4j",
+        "provider": "falkordb",
         "config": {
-            "url": "neo4j+s://xxx",
-            "username": "neo4j",
-            "password": "xxx"
+            "Database": "falkordb",
+            "host": "---"
+            "username": "---",
+            "password": "---",
+            "port": "---"
         }
     },
     "version": "v1.1"
@@ -83,11 +84,13 @@ config = {
         }
     },
     "graph_store": {
-        "provider": "neo4j",
+        "provider": "falkordb",
         "config": {
-            "url": "neo4j+s://xxx",
-            "username": "neo4j",
-            "password": "xxx"
+            "Database": "falkordb",
+            "host": "---"
+            "username": "---",
+            "password": "---",
+            "port": "---"
         },
         "llm" : {
             "provider": "openai",

docs/open-source/quickstart.mdx

@@ -63,11 +63,13 @@ from mem0 import Memory
 
 config = {
     "graph_store": {
-        "provider": "neo4j",
+        "provider": "falkordb",
         "config": {
-            "url": "neo4j+s://---",
-            "username": "neo4j",
-            "password": "---"
+            "Database": "falkordb",
+            "host": "---"
+            "username": "---",
+            "password": "---",
+            "port": "---"
         }
     },
     "version": "v1.1"

mem0/graphs/configs.py

@@ -1,4 +1,4 @@
-from typing import Optional
+from typing import Optional, Union
 
 from pydantic import BaseModel, Field, field_validator, model_validator
 
@@ -20,11 +20,31 @@ def check_host_port_or_path(cls, values):
         if not url or not username or not password:
             raise ValueError("Please provide 'url', 'username' and 'password'.")
         return values
+
+class FalkorDBConfig(BaseModel):
+    host: Optional[str] = Field(None, description="Host address for the graph database")
+    username: Optional[str] = Field(None, description="Username for the graph database")
+    password: Optional[str] = Field(None, description="Password for the graph database")
+    port: Optional[int] = Field(None, description="Port for the graph database")
+    # Default database name is mandatory in langchain
+    database: str = "_default_"
+
+    @model_validator(mode="before")
+    def check_host_port_or_path(cls, values):
+        host, port = (
+            values.get("host"),
+            values.get("port"),
+        )
+        if not host or not port:
+            raise ValueError(
+                "Please provide 'host' and 'port'."
+            )
+        return values
 
 
 class GraphStoreConfig(BaseModel):
-    provider: str = Field(description="Provider of the data store (e.g., 'neo4j')", default="neo4j")
-    config: Neo4jConfig = Field(description="Configuration for the specific data store", default=None)
+    provider: str = Field(description="Provider of the data store (e.g., 'falkordb', 'neo4j')", default="falkordb")
+    config: Union[FalkorDBConfig, Neo4jConfig] = Field(description="Configuration for the specific data store", default=None)
     llm: Optional[LlmConfig] = Field(description="LLM configuration for querying the graph store", default=None)
     custom_prompt: Optional[str] = Field(
         description="Custom prompt to fetch entities from the given text", default=None
@@ -35,5 +55,11 @@ def validate_config(cls, v, values):
         provider = values.data.get("provider")
         if provider == "neo4j":
             return Neo4jConfig(**v.model_dump())
+        elif provider == "falkordb":
+            config = v.model_dump()
+            # In case the user try to use diffrent database name
+            config["database"] = "_default_"
+
+            return FalkorDBConfig(**config)
         else:
             raise ValueError(f"Unsupported graph store provider: {provider}")

mem0/graphs/utils.py

@@ -53,6 +53,52 @@
 
 Adhere strictly to these guidelines to ensure high-quality knowledge graph extraction."""
 
+FALKORDB_QUERY = """
+MATCH (n)
+WHERE n.embedding IS NOT NULL AND n.user_id = $user_id
+WITH n, 
+    reduce(dot = 0.0, i IN range(0, size(n.embedding)-1) | dot + n.embedding[i] * $n_embedding[i]) / 
+    (sqrt(reduce(l2 = 0.0, i IN range(0, size(n.embedding)-1) | l2 + n.embedding[i] * n.embedding[i])) * 
+    sqrt(reduce(l2 = 0.0, i IN range(0, size($n_embedding)-1) | l2 + $n_embedding[i] * $n_embedding[i]))) AS similarity
+WHERE similarity >= $threshold
+MATCH (n)-[r]->(m)
+RETURN n.name AS source, Id(n) AS source_id, type(r) AS relation, Id(r) AS relation_id, m.name AS destination, Id(m) AS destination_id, similarity
+UNION
+MATCH (n)
+WHERE n.embedding IS NOT NULL AND n.user_id = $user_id
+WITH n, 
+    reduce(dot = 0.0, i IN range(0, size(n.embedding)-1) | dot + n.embedding[i] * $n_embedding[i]) / 
+    (sqrt(reduce(l2 = 0.0, i IN range(0, size(n.embedding)-1) | l2 + n.embedding[i] * n.embedding[i])) * 
+    sqrt(reduce(l2 = 0.0, i IN range(0, size($n_embedding)-1) | l2 + $n_embedding[i] * $n_embedding[i]))) AS similarity
+WHERE similarity >= $threshold
+MATCH (m)-[r]->(n)
+RETURN m.name AS source, Id(m) AS source_id, type(r) AS relation, Id(r) AS relation_id, n.name AS destination, Id(n) AS destination_id, similarity
+ORDER BY similarity DESC
+"""
+
+
+NEO4J_QUERY = """
+MATCH (n)
+WHERE n.embedding IS NOT NULL AND n.user_id = $user_id
+WITH n, 
+    round(reduce(dot = 0.0, i IN range(0, size(n.embedding)-1) | dot + n.embedding[i] * $n_embedding[i]) / 
+    (sqrt(reduce(l2 = 0.0, i IN range(0, size(n.embedding)-1) | l2 + n.embedding[i] * n.embedding[i])) * 
+    sqrt(reduce(l2 = 0.0, i IN range(0, size($n_embedding)-1) | l2 + $n_embedding[i] * $n_embedding[i]))), 4) AS similarity
+WHERE similarity >= $threshold
+MATCH (n)-[r]->(m)
+RETURN n.name AS source, elementId(n) AS source_id, type(r) AS relation, elementId(r) AS relation_id, m.name AS destination, elementId(m) AS destination_id, similarity
+UNION
+MATCH (n)
+WHERE n.embedding IS NOT NULL AND n.user_id = $user_id
+WITH n, 
+    round(reduce(dot = 0.0, i IN range(0, size(n.embedding)-1) | dot + n.embedding[i] * $n_embedding[i]) / 
+    (sqrt(reduce(l2 = 0.0, i IN range(0, size(n.embedding)-1) | l2 + n.embedding[i] * n.embedding[i])) * 
+    sqrt(reduce(l2 = 0.0, i IN range(0, size($n_embedding)-1) | l2 + $n_embedding[i] * $n_embedding[i]))), 4) AS similarity
+WHERE similarity >= $threshold
+MATCH (m)-[r]->(n)
+RETURN m.name AS source, elementId(m) AS source_id, type(r) AS relation, elementId(r) AS relation_id, n.name AS destination, elementId(n) AS destination_id, similarity
+ORDER BY similarity DESC
+"""
 
 def get_update_memory_prompt(existing_memories, memory, template):
     return template.format(existing_memories=existing_memories, memory=memory)