Merge branch 'dev' into COG-975

.github/workflows/dockerhub.yml

@@ -7,7 +7,7 @@ on:
 
 jobs:
   docker-build-and-push:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
 
     steps:
     - name: Checkout repository

.github/workflows/py_lint.yml

@@ -16,7 +16,7 @@ jobs:
       fail-fast: true
       matrix:
         os:
-          - ubuntu-22.04
+          - ubuntu-latest
         python-version: ["3.10.x", "3.11.x"]
 
     defaults:

.github/workflows/reusable_notebook.yml

@@ -51,6 +51,7 @@ jobs:
         env:
           ENV: 'dev'
           LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
           GRAPHISTRY_USERNAME: ${{ secrets.GRAPHISTRY_USERNAME }}
           GRAPHISTRY_PASSWORD: ${{ secrets.GRAPHISTRY_PASSWORD }}
         run: |

.github/workflows/ruff_format.yaml

@@ -3,7 +3,7 @@ on: [ pull_request ]
 
 jobs:
   ruff:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
       - uses: astral-sh/ruff-action@v2

.github/workflows/ruff_lint.yaml

@@ -3,7 +3,7 @@ on: [ pull_request ]
 
 jobs:
   ruff:
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
       - uses: astral-sh/ruff-action@v2

.github/workflows/test_deduplication.yml

@@ -16,7 +16,7 @@ env:
 jobs:
   run_deduplication_test:
     name: test
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     defaults:
       run:
         shell: bash

.github/workflows/test_llama_index_cognee_integration_notebook.yml

@@ -0,0 +1,20 @@
+name: test | llama index cognee integration notebook
+
+on:
+  workflow_dispatch:
+  pull_request:
+    types: [labeled, synchronize]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  run_notebook_test:
+      uses: ./.github/workflows/reusable_notebook.yml
+      with:
+        notebook-location: notebooks/llama_index_cognee_integration.ipynb
+      secrets:
+        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        GRAPHISTRY_USERNAME: ${{ secrets.GRAPHISTRY_USERNAME }}
+        GRAPHISTRY_PASSWORD: ${{ secrets.GRAPHISTRY_PASSWORD }}

.github/workflows/test_qdrant.yml

@@ -17,7 +17,7 @@ jobs:
 
   run_qdrant_integration_test:
     name: test
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     defaults:
       run:
         shell: bash

.github/workflows/test_weaviate.yml

@@ -17,7 +17,7 @@ jobs:
 
   run_weaviate_integration_test:
     name: test
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-latest
     defaults:
       run:
         shell: bash

README.md

@@ -101,15 +101,9 @@ cognee.config.set_graphistry_config({
 })
 ```
 
-(Optional) To run the UI, go to cognee-frontend directory and run:
-```
-npm run dev
-```
-or run everything in a docker container:
-```
-docker-compose up
-```
-Then navigate to localhost:3000
+(Optional) To run the with an UI, go to cognee-mcp directory and follow the instructions.
+You will be able to use cognee as mcp tool and create graphs and query them.
+
 
 If you want to use Cognee with PostgreSQL, make sure to set the following values in the .env file:
 ```

cognee-mcp/pyproject.toml

@@ -3,7 +3,8 @@ name = "cognee-mcp"
 version = "0.1.0"
 description = "A MCP server project"
 readme = "README.md"
-requires-python = ">=3.11.0"
+requires-python = ">=3.10"
+
 dependencies = [
     "mcp>=1.1.1",
     "openai==1.59.4",

cognee/modules/graph/cognee_graph/CogneeGraph.py

@@ -8,7 +8,7 @@ from cognee.infrastructure.databases.graph.graph_db_interface import GraphDBInte
 from cognee.modules.graph.cognee_graph.CogneeGraphElements import Node, Edge
 from cognee.modules.graph.cognee_graph.CogneeAbstractGraph import CogneeAbstractGraph
 import heapq
-from graphistry import edges
+import asyncio
 
 
 class CogneeGraph(CogneeAbstractGraph):
@@ -127,51 +127,25 @@ class CogneeGraph(CogneeAbstractGraph):
                 else:
                     print(f"Node with id {node_id} not found in the graph.")
 
-    async def map_vector_distances_to_graph_edges(
-        self, vector_engine, query
-    ) -> None:  # :TODO: When we calculate edge embeddings in vector db change this similarly to node mapping
+    async def map_vector_distances_to_graph_edges(self, vector_engine, query) -> None:
         try:
-            # Step 1: Generate the query embedding
             query_vector = await vector_engine.embed_data([query])
             query_vector = query_vector[0]
             if query_vector is None or len(query_vector) == 0:
                 raise ValueError("Failed to generate query embedding.")
 
-            # Step 2: Collect all unique relationship types
-            unique_relationship_types = set()
-            for edge in self.edges:
-                relationship_type = edge.attributes.get("relationship_type")
-                if relationship_type:
-                    unique_relationship_types.add(relationship_type)
+            edge_distances = await vector_engine.get_distance_from_collection_elements(
+                "edge_type_relationship_name", query_text=query
+            )
 
-            # Step 3: Embed all unique relationship types
-            unique_relationship_types = list(unique_relationship_types)
-            relationship_type_embeddings = await vector_engine.embed_data(unique_relationship_types)
+            embedding_map = {result.payload["text"]: result.score for result in edge_distances}
 
-            # Step 4: Map relationship types to their embeddings and calculate distances
-            embedding_map = {}
-            for relationship_type, embedding in zip(
-                unique_relationship_types, relationship_type_embeddings
-            ):
-                edge_vector = np.array(embedding)
-
-                # Calculate cosine similarity
-                similarity = np.dot(query_vector, edge_vector) / (
-                    np.linalg.norm(query_vector) * np.linalg.norm(edge_vector)
-                )
-                distance = 1 - similarity
-
-                # Round the distance to 4 decimal places and store it
-                embedding_map[relationship_type] = round(distance, 4)
-
-            # Step 4: Assign precomputed distances to edges
             for edge in self.edges:
                 relationship_type = edge.attributes.get("relationship_type")
                 if not relationship_type or relationship_type not in embedding_map:
                     print(f"Edge {edge} has an unknown or missing relationship type.")
                     continue
 
-                # Assign the precomputed distance
                 edge.attributes["vector_distance"] = embedding_map[relationship_type]
 
         except Exception as ex:

cognee/modules/retrieval/brute_force_triplet_search.py

@@ -62,24 +62,6 @@ async def brute_force_triplet_search(
     return retrieved_results
 
 
-def delete_duplicated_vector_db_elements(
-    collections, results
-):  #:TODO: This is just for now to fix vector db duplicates
-    results_dict = {}
-    for collection, results in zip(collections, results):
-        seen_ids = set()
-        unique_results = []
-        for result in results:
-            if result.id not in seen_ids:
-                unique_results.append(result)
-                seen_ids.add(result.id)
-            else:
-                print(f"Duplicate found in collection '{collection}': {result.id}")
-        results_dict[collection] = unique_results
-
-    return results_dict
-
-
 async def brute_force_search(
     query: str, user: User, top_k: int, collections: List[str] = None
 ) -> list:
@@ -125,10 +107,7 @@ async def brute_force_search(
             ]
         )
 
-        ############################################# :TODO: Change when vector db does not contain duplicates
-        node_distances = delete_duplicated_vector_db_elements(collections, results)
-        # node_distances = {collection: result for collection, result in zip(collections, results)}
-        ##############################################
+        node_distances = {collection: result for collection, result in zip(collections, results)}
 
         memory_fragment = CogneeGraph()
 
@@ -140,14 +119,12 @@ async def brute_force_search(
 
         await memory_fragment.map_vector_distances_to_graph_nodes(node_distances=node_distances)
 
-        #:TODO: Change when vectordb contains edge embeddings
         await memory_fragment.map_vector_distances_to_graph_edges(vector_engine, query)
 
         results = await memory_fragment.calculate_top_triplet_importances(k=top_k)
 
         send_telemetry("cognee.brute_force_triplet_search EXECUTION STARTED", user.id)
 
-        #:TODO: Once we have Edge pydantic models we should retrieve the exact edge and node objects from graph db
         return results
 
     except Exception as e:

cognee/modules/users/methods/get_default_user.py

@@ -1,4 +1,4 @@
-from sqlalchemy.orm import joinedload
+from sqlalchemy.orm import selectinload
 from sqlalchemy.future import select
 from cognee.modules.users.models import User
 from cognee.infrastructure.databases.relational import get_relational_engine
@@ -11,7 +11,7 @@ async def get_default_user():
     async with db_engine.get_async_session() as session:
         query = (
             select(User)
-            .options(joinedload(User.groups))
+            .options(selectinload(User.groups))
             .where(User.email == "default_user@example.com")
         )
 

cognee/shared/utils.py

@@ -451,16 +451,20 @@ def graph_to_tuple(graph):
 
 
 def setup_logging(log_level=logging.INFO):
-    """This method sets up the logging configuration."""
+    """Sets up the logging configuration."""
     formatter = logging.Formatter("%(asctime)s - %(levelname)s - %(message)s\n")
+
     stream_handler = logging.StreamHandler(sys.stdout)
     stream_handler.setFormatter(formatter)
     stream_handler.setLevel(log_level)
 
-    logging.basicConfig(
-        level=log_level,
-        handlers=[stream_handler],
-    )
+    root_logger = logging.getLogger()
+
+    if root_logger.hasHandlers():
+        root_logger.handlers.clear()
+
+    root_logger.addHandler(stream_handler)
+    root_logger.setLevel(log_level)
 
 
 # ---------------- Example Usage ----------------

examples/python/dynamic_steps_example.py

@@ -192,7 +192,7 @@ async def main(enable_steps):
 
 
 if __name__ == "__main__":
-    setup_logging(logging.INFO)
+    setup_logging(logging.ERROR)
 
     rebuild_kg = True
     retrieve = True

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "cognee"
-version = "0.1.21"
+version = "0.1.22"
 description = "Cognee - is a library for enriching LLM context with a semantic layer for better understanding and reasoning."
 authors = ["Vasilije Markovic", "Boris Arzentar"]
 readme = "README.md"