Rename the build package name and refactored the local runner

.env.template

@@ -7,7 +7,6 @@ POSTGRES_PASSWORD = bla
 POSTGRES_DB = bubu
 POSTGRES_HOST = localhost
 POSTGRES_HOST_DOCKER = postgres
-SEGMENT_KEY = Etl4WJwzOkeDPAjaOXOMgyU16hO7mV7B
 COG_ARCH_DIR = cognitive_architecture
 GRAPH_DB_URL =
 GRAPH_DB_PW =

cognitive_architecture/database/graph_database/graph.py

@@ -602,6 +602,40 @@ class Neo4jGraphDB(AbstractGraphDB):
 
         return cypher_query
 
+    def construct_merge_query(self, user_id: str, relationship_type: str, memory_type: str,
+                              similarity_threshold: float) -> str:
+        """
+        Constructs a Cypher query to merge nodes in a Neo4j database based on a similarity threshold.
+
+        This method creates a Cypher query that finds pairs of nodes with a specified memory type
+        connected via a specified relationship type to the same 'Memory' node. If the Levenshtein
+        similarity between the 'description' properties of these nodes is greater than the
+        specified threshold, the nodes are merged using the apoc.refactor.mergeNodes procedure.
+
+        Parameters:
+        user_id (str): The ID of the user whose related nodes are to be merged.
+        relationship_type (str): The type of relationship between 'Memory' nodes and the nodes to be merged.
+        memory_type (str): The memory type property of the nodes to be merged.
+        similarity_threshold (float): The threshold above which nodes will be considered similar enough to be merged.
+
+        Returns:
+        str: A Cypher query string that can be executed in a Neo4j session.
+        """
+        query = f"""
+            MATCH (u:User {{userId: '{user_id}'}})-[:HAS_MEMORY]->(m:Memory)
+            MATCH (m)-[r:HAS_KNOWLEDGE]->(n1), (m)-[r2:HAS_KNOWLEDGE]->(n2)
+            WHERE id(n1) < id(n2) AND 
+                  {relationship_type} = TYPE(r) AND 
+                  {relationship_type} = TYPE(r2) AND 
+                  n1.memory_type = {memory_type} AND 
+                  n2.memory_type = {memory_type} AND 
+                  apoc.text.levenshteinSimilarity(toLower(n1.description), toLower(n2.description)) > {str(similarity_threshold)}
+            WITH n1, n2
+            CALL apoc.refactor.mergeNodes([n1, n2], {{mergeRels: true}}) YIELD node
+            RETURN node
+        """
+        return query
+
     def get_namespaces_by_document_category(self, user_id: str, category: str):
         """
         Retrieve a list of Vectordb namespaces for documents of a specified category associated with a given user.

docker-compose.yml

@@ -11,11 +11,11 @@ services:
       - NEO4J_AUTH=neo4j/pleaseletmein
       - NEO4J_PLUGINS=["apoc"]
     networks:
-      - promethai_mem_backend
+      - cognee_backend
 
-  promethai_mem:
+  cognee:
     networks:
-      - promethai_mem_backend
+      - cognee_backend
     build:
       context: ./
     volumes:
@@ -24,6 +24,7 @@ services:
 
     environment:
       - HOST=0.0.0.0
+      - ENVIRONMENT=local
     profiles: ["exclude-from-up"]
     ports:
       - 8000:8000
@@ -49,7 +50,7 @@ services:
       - POSTGRES_PASSWORD=bla
       - POSTGRES_DB=bubu
     networks:
-      - promethai_mem_backend
+      - cognee_backend
     ports:
       - "5432:5432"
 
@@ -74,6 +75,6 @@ services:
 #      - postgres
 
 networks:
-  promethai_mem_backend:
-    name: promethai_mem_backend
+  cognee_backend:
+    name: cognee_backend
 

entrypoint.sh

@@ -2,10 +2,15 @@
 export ENVIRONMENT
 # Run Python scripts with error handling
 echo "Running fetch_secret.py"
-python cognitive_architecture/fetch_secret.py
-if [ $? -ne 0 ]; then
+if [ "$ENVIRONMENT" != "local" ]; then
+    echo "Running fetch_secret.py"
+    python cognitive_architecture/fetch_secret.py
+    if [ $? -ne 0 ]; then
         echo "Error: fetch_secret.py failed"
         exit 1
+    fi
+else
+    echo "ENVIRONMENT ($ENVIRONMENT) is active, skipping fetch_secret.py"
 fi
 
 echo "Running create_database.py"

iterations/level_3/vectordb/basevectordb.py

@@ -276,7 +276,7 @@ class BaseMemory:
         n_of_observations: Optional[int] = 2,
     ):
         logging.info(namespace)
-        logging.info("The search type is %", search_type)
+        logging.info("The search type is %", str(search_type))
         logging.info(params)
         logging.info(observation)
 

iterations/level_3/vectordb/vectordb.py

@@ -185,7 +185,7 @@ class WeaviateVectorDB(VectorDB):
         client = self.init_weaviate(namespace =self.namespace)
         if search_type is None:
             search_type = 'hybrid'
-        logging.info("The search type is 2 %", search_type)
+        logging.info("The search type is %s", str(search_type))
 
         if not namespace:
             namespace = self.namespace

iterations/level_3/vectorstore_manager.py

@@ -340,7 +340,7 @@ class Memory:
         )
 
     async def add_dynamic_memory_class(self, class_name: str, namespace: str):
-        logging.info("Here is the memory id %s", self.memory_id[0])
+        logging.info("Here is the memory id %s", str(self.memory_id[0]))
         new_memory_class = DynamicBaseMemory(
             class_name,
             self.user_id,

pyproject.toml

@@ -1,12 +1,12 @@
 [tool.poetry]
-name = "PromethAI_memory"
+name = "cognee"
 version = "0.1.0"
-description = "PromethAI cognitive architecture is a library for enriching LLM context by managing AI cognitive architecture"
+description = "Cognee cognitive architecture is a library for enriching LLM context with a semantic layer"
 authors = ["Vasilije Markovic"]
 readme = "README.md"
 license = "Apache-2.0"
-homepage = "https://github.com/topoteretes/PromethAI-Memory"
-repository = "https://www.prometh.ai"
+homepage = "https://github.com/topoteretes/cognee"
+repository = "https://www.cognee.ai"
 classifiers = [
     "Development Status :: 4 - Beta",
     "Intended Audience :: Developers",
@@ -50,7 +50,6 @@ dash = "^2.14.0"
 unstructured = {extras = ["pdf"], version = "^0.10.23"}
 sentence-transformers = "2.2.2"
 torch = "2.0.*"
-segment-analytics-python = "^2.2.3"
 pdf2image = "^1.16.3"
 instructor = "^0.3.4"
 networkx = "^3.2.1"