Merge main vol 4 (#1200)

<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

---------

Signed-off-by: Andrew Carbonetto <andrew.carbonetto@improving.com>
Signed-off-by: Andy Kwok <andy.kwok@improving.com>
Co-authored-by: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Co-authored-by: vasilije <vas.markovic@gmail.com>
Co-authored-by: Andrew Carbonetto <andrew.carbonetto@improving.com>
Co-authored-by: Andy Kwok <andy.kwok@improving.com>

CONTRIBUTING.md

@@ -99,15 +99,17 @@ python cognee/cognee/tests/test_library.py
 
 ## 4. 📤 Submitting Changes
 
-1. Push your changes:
+1. Install ruff on your system
+2. Run ```ruff format .``` and ``` ruff check ``` and fix the issues
+3. Push your changes:
 ```shell
 git add .
 git commit -s -m "Description of your changes"
 git push origin feature/your-feature-name
 ```
 
 2. Create a Pull Request:
-   - Go to the [**cognee** repository](https://github.com/topoteretes/cognee)
+   - Go to the [**cognee** repository](https://github.com/topoteretes/cognee) or [cognee community repository](https://github.com/topoteretes/cognee-community)
    - Click "Compare & Pull Request" and open a PR against dev branch
    - Fill in the PR template with details about your changes
 

Dockerfile

@@ -40,6 +40,7 @@ COPY alembic/ /app/alembic
 # Then, add the rest of the project source code and install it
 # Installing separately from its dependencies allows optimal layer caching
 COPY ./cognee /app/cognee
+COPY ./distributed /app/distributed
 RUN --mount=type=cache,target=/root/.cache/uv \
 uv sync --extra debug --extra api --extra postgres --extra qdrant --extra neo4j --extra llama-index --extra gemini --extra ollama --extra mistral --extra groq --extra anthropic --frozen --no-dev --no-editable
 

cognee-mcp/Dockerfile

@@ -51,6 +51,7 @@ RUN apt-get update && apt-get install -y \
 
 WORKDIR /app
 
+# Copy the virtual environment from the uv stage
 COPY --from=uv /usr/local /usr/local
 COPY --from=uv /app /app
 

cognee-mcp/entrypoint.sh

@@ -48,15 +48,15 @@ if [ "$ENVIRONMENT" = "dev" ] || [ "$ENVIRONMENT" = "local" ]; then
     if [ "$DEBUG" = "true" ]; then
         echo "Waiting for the debugger to attach..."
         if [ "$TRANSPORT_MODE" = "sse" ]; then
-            exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee --transport sse --no-migration
+            exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee --transport sse --host 0.0.0.0 --port $HTTP_PORT --no-migration
         elif [ "$TRANSPORT_MODE" = "http" ]; then
             exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee --transport http --host 0.0.0.0 --port $HTTP_PORT --no-migration
         else
             exec python -m debugpy --wait-for-client --listen 0.0.0.0:$DEBUG_PORT -m cognee --transport stdio --no-migration
         fi
     else
         if [ "$TRANSPORT_MODE" = "sse" ]; then
-            exec cognee --transport sse --no-migration
+            exec cognee --transport sse --host 0.0.0.0 --port $HTTP_PORT --no-migration
         elif [ "$TRANSPORT_MODE" = "http" ]; then
             exec cognee --transport http --host 0.0.0.0 --port $HTTP_PORT --no-migration
         else
@@ -65,7 +65,7 @@ if [ "$ENVIRONMENT" = "dev" ] || [ "$ENVIRONMENT" = "local" ]; then
     fi
 else
     if [ "$TRANSPORT_MODE" = "sse" ]; then
-        exec cognee --transport sse --no-migration
+        exec cognee --transport sse --host 0.0.0.0 --port $HTTP_PORT --no-migration
     elif [ "$TRANSPORT_MODE" = "http" ]; then
         exec cognee --transport http --host 0.0.0.0 --port $HTTP_PORT --no-migration
     else

cognee-mcp/src/server.py

@@ -947,6 +947,9 @@ async def main():
 
     args = parser.parse_args()
 
+    mcp.settings.host = args.host
+    mcp.settings.port = args.port
+
     if not args.no_migration:
         # Run Alembic migrations from the main cognee directory where alembic.ini is located
         logger.info("Running database migrations...")

cognee/infrastructure/databases/graph/get_graph_engine.py

@@ -135,6 +135,63 @@ def create_graph_engine(
             graph_database_password=graph_database_password or None,
         )
 
+    elif graph_database_provider == "neptune":
+        try:
+            from langchain_aws import NeptuneAnalyticsGraph
+        except ImportError:
+            raise ImportError(
+                "langchain_aws is not installed. Please install it with 'pip install langchain_aws'"
+            )
+
+        if not graph_database_url:
+            raise EnvironmentError("Missing Neptune endpoint.")
+
+        from .neptune_driver.adapter import NeptuneGraphDB, NEPTUNE_ENDPOINT_URL
+
+        if not graph_database_url.startswith(NEPTUNE_ENDPOINT_URL):
+            raise ValueError(
+                f"Neptune endpoint must have the format {NEPTUNE_ENDPOINT_URL}<GRAPH_ID>"
+            )
+
+        graph_identifier = graph_database_url.replace(NEPTUNE_ENDPOINT_URL, "")
+
+        return NeptuneGraphDB(
+            graph_id=graph_identifier,
+        )
+
+    elif graph_database_provider == "neptune_analytics":
+        """
+        Creates a graph DB from config
+        We want to use a hybrid (graph & vector) DB and we should update this
+        to make a single instance of the hybrid configuration (with embedder)
+        instead of creating the hybrid object twice.  
+        """
+        try:
+            from langchain_aws import NeptuneAnalyticsGraph
+        except ImportError:
+            raise ImportError(
+                "langchain_aws is not installed. Please install it with 'pip install langchain_aws'"
+            )
+
+        if not graph_database_url:
+            raise EnvironmentError("Missing Neptune endpoint.")
+
+        from ..hybrid.neptune_analytics.NeptuneAnalyticsAdapter import (
+            NeptuneAnalyticsAdapter,
+            NEPTUNE_ANALYTICS_ENDPOINT_URL,
+        )
+
+        if not graph_database_url.startswith(NEPTUNE_ANALYTICS_ENDPOINT_URL):
+            raise ValueError(
+                f"Neptune endpoint must have the format '{NEPTUNE_ANALYTICS_ENDPOINT_URL}<GRAPH_ID>'"
+            )
+
+        graph_identifier = graph_database_url.replace(NEPTUNE_ANALYTICS_ENDPOINT_URL, "")
+
+        return NeptuneAnalyticsAdapter(
+            graph_id=graph_identifier,
+        )
+
     from .networkx.adapter import NetworkXAdapter
 
     graph_client = NetworkXAdapter(filename=graph_file_path)

cognee/infrastructure/databases/graph/neptune_driver/__init__.py

@@ -0,0 +1,15 @@
+"""Neptune Analytics Driver Module
+
+This module provides the Neptune Analytics adapter and utilities for interacting
+with Amazon Neptune Analytics graph databases.
+"""
+
+from .adapter import NeptuneGraphDB
+from . import neptune_utils
+from . import exceptions
+
+__all__ = [
+    "NeptuneGraphDB",
+    "neptune_utils",
+    "exceptions",
+]