fix: various fixes for the deployment

* fix: remove groups from UserRead model

* fix: add missing system dependencies for postgres

* fix: change vector db provider environment variable name

* fix: WeaviateAdapter retrieve bug

* fix: correctly return data point objects from retrieve method

* fix: align graph object properties

* feat: add node example

.env.template

@@ -13,7 +13,7 @@ GRAPH_DATABASE_URL=
 GRAPH_DATABASE_USERNAME=
 GRAPH_DATABASE_PASSWORD=
 
-VECTOR_ENGINE_PROVIDER="qdrant" # or "weaviate" or "lancedb"
+VECTOR_DB_PROVIDER="qdrant" # or "weaviate" or "lancedb"
 # Not needed if using "lancedb"
 VECTOR_DB_URL=
 VECTOR_DB_KEY=

.gitignore

@@ -177,3 +177,5 @@ cognee/cache/
 # Default cognee system directory, used in development
 .cognee_system/
 .data_storage/
+
+node_modules/

Dockerfile

@@ -8,25 +8,34 @@ ENV DEBUG=${DEBUG}
 ENV PIP_NO_CACHE_DIR=true
 ENV PATH="${PATH}:/root/.poetry/bin"
 
+RUN apt-get update && apt-get install
+
+RUN apt-get install -y \
+  gcc \
+  libpq-dev
+
+
 WORKDIR /app
 COPY pyproject.toml poetry.lock /app/
 
+
 RUN pip install poetry
 
 # Don't create virtualenv since docker is already isolated
 RUN poetry config virtualenvs.create false
 
 # Install the dependencies
 RUN poetry install --no-root --no-dev
-
+
+
 # Set the PYTHONPATH environment variable to include the /app directory
 ENV PYTHONPATH=/app
 
-COPY cognee/ cognee/
+COPY cognee/ /app/cognee
 
 # Copy Alembic configuration
-COPY alembic.ini ./
-COPY alembic/ alembic/
+COPY alembic.ini /app/alembic.ini
+COPY alembic/ /app/alembic
 
 COPY entrypoint.sh /app/entrypoint.sh
 RUN chmod +x /app/entrypoint.sh

alembic/env.py

@@ -92,6 +92,8 @@ def run_migrations_online() -> None:
     db_config = get_relational_config()
     LocalStorage.ensure_directory_exists(db_config.db_path)
 
+print("Using database:", db_engine.db_uri)
+
 config.set_section_option(
     config.config_ini_section,
     "SQLALCHEMY_DATABASE_URI",

alembic/versions/482cd6517ce4_add_default_user.py

@@ -16,7 +16,7 @@
 revision: str = '482cd6517ce4'
 down_revision: Union[str, None] = '8057ae7329c2'
 branch_labels: Union[str, Sequence[str], None] = None
-depends_on: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = "8057ae7329c2"
 
 
 def upgrade() -> None:

cognee/api/client.py

@@ -43,13 +43,13 @@ async def lifespan(app: FastAPI):
     # from cognee.modules.data.deletion import prune_system, prune_data
     # await prune_data()
     # await prune_system(metadata = True)
-    if app_environment == "local" or app_environment == "dev":
-        from cognee.infrastructure.databases.relational import get_relational_engine
-        db_engine = get_relational_engine()
-        await db_engine.create_database()
+    # if app_environment == "local" or app_environment == "dev":
+    from cognee.infrastructure.databases.relational import get_relational_engine
+    db_engine = get_relational_engine()
+    await db_engine.create_database()
 
-        from cognee.modules.users.methods import get_default_user
-        await get_default_user()
+    from cognee.modules.users.methods import get_default_user
+    await get_default_user()
 
     yield
 

cognee/api/v1/config/config.py

@@ -21,7 +21,7 @@ def system_root_directory(system_root_directory: str):
         graph_config.graph_file_path = os.path.join(databases_directory_path, "cognee.graph")
 
         vector_config = get_vectordb_config()
-        if vector_config.vector_engine_provider == "lancedb":
+        if vector_config.vector_db_provider == "lancedb":
             vector_config.vector_db_url = os.path.join(databases_directory_path, "cognee.lancedb")
 
     @staticmethod
@@ -91,9 +91,9 @@ def set_chunk_size(chunk_size: object):
 
 
     @staticmethod
-    def set_vector_engine_provider(vector_engine_provider: str):
+    def set_vector_db_provider(vector_db_provider: str):
         vector_db_config = get_vectordb_config()
-        vector_db_config.vector_engine_provider = vector_engine_provider
+        vector_db_config.vector_db_provider = vector_db_provider
 
     @staticmethod
     def set_vector_db_key(db_key: str):

cognee/infrastructure/databases/vector/config.py

@@ -9,15 +9,15 @@ class VectorConfig(BaseSettings):
         "cognee.lancedb"
     )
     vector_db_key: str = ""
-    vector_engine_provider: str = "lancedb"
+    vector_db_provider: str = "lancedb"
 
     model_config = SettingsConfigDict(env_file = ".env", extra = "allow")
 
     def to_dict(self) -> dict:
         return {
             "vector_db_url": self.vector_db_url,
             "vector_db_key": self.vector_db_key,
-            "vector_db_provider": self.vector_engine_provider,
+            "vector_db_provider": self.vector_db_provider,
         }
 
 @lru_cache

cognee/infrastructure/databases/vector/weaviate_db/WeaviateAdapter.py

@@ -108,11 +108,12 @@ async def retrieve(self, collection_name: str, data_point_ids: list[str]):
             filters = Filter.by_id().contains_any(data_point_ids)
         )
 
-        for data_point in data_points:
+        for data_point in data_points.objects:
             data_point.payload = data_point.properties
+            data_point.id = data_point.uuid
             del data_point.properties
 
-        future.set_result(data_points)
+        future.set_result(data_points.objects)
 
         return await future
 

cognee/infrastructure/llm/openai/adapter.py

@@ -4,7 +4,6 @@
 from pathlib import Path
 from typing import List, Type
 
-import aiofiles
 import openai
 import instructor
 from pydantic import BaseModel
@@ -13,9 +12,7 @@
 from cognee.base_config import get_base_config
 from cognee.infrastructure.llm.llm_interface import LLMInterface
 from cognee.infrastructure.llm.prompts import read_query_prompt
-from cognee.shared.data_models import MonitoringTool
-import logging
-logging.basicConfig(level=logging.DEBUG)
+# from cognee.shared.data_models import MonitoringTool
 
 class OpenAIAdapter(LLMInterface):
     name = "OpenAI"

cognee/modules/settings/get_settings.py

@@ -100,8 +100,8 @@ def get_settings() -> SettingsDict:
         },
         vector_db = {
             "provider": {
-                "label": vector_config.vector_engine_provider,
-                "value": vector_config.vector_engine_provider.lower(),
+                "label": vector_config.vector_db_provider,
+                "value": vector_config.vector_db_provider.lower(),
             },
             "url": vector_config.vector_db_url,
             "api_key": vector_config.vector_db_key,

cognee/modules/settings/save_vector_db_config.py

@@ -12,4 +12,4 @@ async def save_vector_db_config(vector_db_config: VectorDBConfig):
 
     vector_config.vector_db_url = vector_db_config.url
     vector_config.vector_db_key = vector_db_config.api_key
-    vector_config.vector_engine_provider = vector_db_config.provider
+    vector_config.vector_db_provider = vector_db_config.provider

cognee/modules/users/models/User.py

@@ -25,7 +25,8 @@ class User(SQLAlchemyBaseUserTableUUID, Principal):
 from fastapi_users import schemas
 
 class UserRead(schemas.BaseUser[uuid_UUID]):
-    groups: list[uuid_UUID]  # Add groups attribute
+    # groups: list[uuid_UUID]  # Add groups attribute
+    pass
 
 class UserCreate(schemas.BaseUserCreate):
     pass

cognee/tasks/chunk_update_check/chunk_update_check.py

@@ -14,7 +14,7 @@ async def chunk_update_check(data_chunks: list[DocumentChunk], collection_name:
         [str(chunk.chunk_id) for chunk in data_chunks],
     )
 
-    existing_chunks_map = {chunk.id: chunk.payload for chunk in existing_chunks}
+    existing_chunks_map = {str(chunk.id): chunk.payload for chunk in existing_chunks}
 
     affected_data_chunks = []
 

cognee/tasks/graph/query_graph_connections.py

@@ -23,7 +23,7 @@ async def query_graph_connections(query: str, exploration_levels = 1) -> list[(s
     exact_node = await graph_engine.extract_node(node_id)
 
     if exact_node is not None and "uuid" in exact_node:
-        node_connections = await graph_engine.get_connections(exact_node["uuid"])
+        node_connections = await graph_engine.get_connections(str(exact_node["uuid"]))
     else:
         vector_engine = get_vector_engine()
         results = await asyncio.gather(
@@ -37,7 +37,7 @@ async def query_graph_connections(query: str, exploration_levels = 1) -> list[(s
             return []
 
         node_connections_results = await asyncio.gather(
-            *[graph_engine.get_connections(result.payload["uuid"]) for result in relevant_results]
+            *[graph_engine.get_connections(str(result.payload["uuid"])) for result in relevant_results]
         )
 
         node_connections = []

cognee/tests/test_qdrant.py

@@ -9,7 +9,7 @@
 logging.basicConfig(level=logging.DEBUG)
 
 async def main():
-    cognee.config.set_vector_engine_provider("qdrant")
+    cognee.config.set_vector_db_provider("qdrant")
     data_directory_path = str(pathlib.Path(os.path.join(pathlib.Path(__file__).parent, ".data_storage/test_qdrant")).resolve())
     cognee.config.data_root_directory(data_directory_path)
     cognee_directory_path = str(pathlib.Path(os.path.join(pathlib.Path(__file__).parent, ".cognee_system/test_qdrant")).resolve())

cognee/tests/test_weaviate.py

@@ -7,7 +7,7 @@
 logging.basicConfig(level=logging.DEBUG)
 
 async def main():
-    cognee.config.set_vector_engine_provider("weaviate")
+    cognee.config.set_vector_db_provider("weaviate")
     data_directory_path = str(pathlib.Path(os.path.join(pathlib.Path(__file__).parent, ".data_storage/test_weaviate")).resolve())
     cognee.config.data_root_directory(data_directory_path)
     cognee_directory_path = str(pathlib.Path(os.path.join(pathlib.Path(__file__).parent, ".cognee_system/test_weaviate")).resolve())

entrypoint.sh

@@ -3,8 +3,19 @@
 echo "Debug mode: $DEBUG"
 echo "Environment: $ENVIRONMENT"
 
-# Run migrations
-poetry run alembic upgrade head
+
+# # Run Alembic migrations
+# echo "Running database migrations..."
+# poetry run alembic upgrade head
+
+# # Check if the migrations were successful
+# if [ $? -eq 0 ]; then
+#     echo "Migrations completed successfully."
+# else
+#     echo "Migration failed, exiting."
+#     exit 1
+# fi
+
 
 echo "Starting Gunicorn"
 

examples/node/fetch.js

@@ -0,0 +1,14 @@
+import nodeFetch from 'node-fetch';
+import handleServerErrors from './handleServerErrors.js';
+
+export default function fetch(url, options = {}, token) {
+  return nodeFetch('http://127.0.0.1:8000/api' + url, {
+    ...options,
+    headers: {
+      ...options.headers,
+      'Authorization': `Bearer ${token}`,
+    },
+  })
+    .then(handleServerErrors)
+    .catch(handleServerErrors);
+}

examples/node/handleServerErrors.js

@@ -0,0 +1,16 @@
+export default function handleServerErrors(response) {
+  return new Promise((resolve, reject) => {
+    if (response.status === 401) {
+      return reject(new Error('Unauthorized'));
+    }
+    if (!response.ok) {
+      if (response.json) {
+        return response.json().then(error => reject(error));
+      } else {
+        return reject(response.detail || response.body || response);
+      }
+    }
+
+    return resolve(response);
+  });
+}