git merge

.env.template

@@ -12,6 +12,8 @@
 ################################################################################
 #  🧠 LLM Settings
 ################################################################################
+# Currently we support BAML and Instructor(using litellm) for structured outputs
+STRUCTURED_OUTPUT_FRAMEWORK="instructor"
 
 LLM_API_KEY="your_api_key"
 LLM_MODEL="openai/gpt-4o-mini"
@@ -29,6 +31,13 @@ EMBEDDING_MAX_TOKENS=8191
 # If embedding key is not provided same key set for LLM_API_KEY will be used
 #EMBEDDING_API_KEY="your_api_key"
 
+# If using BAML structured output these env variables will be used
+BAML_LLM_PROVIDER=openai
+BAML_LLM_MODEL="gpt-4o-mini"
+BAML_LLM_ENDPOINT=""
+BAML_LLM_API_KEY="your_api_key"
+BAML_LLM_API_VERSION=""
+
 ################################################################################
 # 🗄️ Relational database settings
 ################################################################################
@@ -62,6 +71,7 @@ GRAPH_DATABASE_PROVIDER="kuzu"
 # -- To switch to Neo4j uncomment and fill these: -------------------------------------------------------------------
 #GRAPH_DATABASE_PROVIDER="neo4j"
 #GRAPH_DATABASE_URL=bolt://localhost:7687
+#GRAPH_DATABASE_NAME="neo4j"
 #GRAPH_DATABASE_USERNAME=neo4j
 #GRAPH_DATABASE_PASSWORD=localneo4j
 
@@ -79,9 +89,8 @@ VECTOR_DB_KEY=
 #  📂 ROOT DIRECTORY IF USING COGNEE LIB INSIDE A DOCKER
 ################################################################################
 # Set up the Cognee system directory. Cognee will store system files and databases here.
-DATA_ROOT_DIRECTORY='/cognee_data/data'
-SYSTEM_ROOT_DIRECTORY='/cognee_data/system'
-
+# DATA_ROOT_DIRECTORY='/Users/<user>/Desktop/cognee/.cognee_data/'
+# SYSTEM_ROOT_DIRECTORY='/Users/<user>/Desktop/cognee/.cognee_system/'
 
 ################################################################################
 #  🔄  MIGRATION (RELATIONAL → GRAPH) SETTINGS

.github/workflows/basic_tests.yml

@@ -146,6 +146,42 @@ jobs:
       - name: Run Simple Examples
         run: poetry run python ./examples/python/simple_example.py
 
+  simple-examples-baml:
+    name: Run Simple Examples BAML
+    runs-on: ubuntu-22.04
+    env:
+      STRUCTURED_OUTPUT_FRAMEWORK: "BAML"
+      BAML_LLM_PROVIDER: azure-openai
+      BAML_LLM_MODEL: ${{ secrets.LLM_MODEL }}
+      BAML_LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
+      BAML_LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+      BAML_LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
+
+      LLM_PROVIDER: openai
+      LLM_MODEL: ${{ secrets.LLM_MODEL }}
+      LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
+      LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+      LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
+
+      EMBEDDING_PROVIDER: openai
+      EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
+      EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
+      EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
+      EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
+    steps:
+      - name: Check out repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Cognee Setup
+        uses: ./.github/actions/cognee_setup
+        with:
+          python-version: ${{ inputs.python-version }}
+
+      - name: Run Simple Examples
+        run: poetry run python ./examples/python/simple_example.py
+
   graph-tests:
     name: Run Basic Graph Tests
     runs-on: ubuntu-22.04
@@ -174,5 +210,3 @@ jobs:
 
       - name: Run Graph Tests
         run: poetry run python ./examples/python/code_graph_example.py --repo_path ./cognee/tasks/graph
-
-

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/codingagents/coding_rule_associations.py

@@ -2,9 +2,9 @@
 
 from cognee.infrastructure.databases.graph import get_graph_engine
 from cognee.infrastructure.databases.vector import get_vector_engine
-from cognee.infrastructure.llm.prompts import render_prompt
+
 from cognee.low_level import DataPoint
-from cognee.infrastructure.llm.get_llm_client import get_llm_client
+from cognee.infrastructure.llm import LLMGateway
 from cognee.shared.logging_utils import get_logger
 from cognee.modules.engine.models import NodeSet
 from cognee.tasks.storage import add_data_points, index_graph_edges
@@ -91,16 +91,17 @@ async def get_origin_edges(data: str, rules: List[Rule]) -> list[Any]:
 
 
 async def add_rule_associations(data: str, rules_nodeset_name: str):
-    llm_client = get_llm_client()
     graph_engine = await get_graph_engine()
     existing_rules = await get_existing_rules(rules_nodeset_name=rules_nodeset_name)
 
     user_context = {"chat": data, "rules": existing_rules}
 
-    user_prompt = render_prompt("coding_rule_association_agent_user.txt", context=user_context)
-    system_prompt = render_prompt("coding_rule_association_agent_system.txt", context={})
+    user_prompt = LLMGateway.render_prompt(
+        "coding_rule_association_agent_user.txt", context=user_context
+    )
+    system_prompt = LLMGateway.render_prompt("coding_rule_association_agent_system.txt", context={})
 
-    rule_list = await llm_client.acreate_structured_output(
+    rule_list = await LLMGateway.acreate_structured_output(
         text_input=user_prompt, system_prompt=system_prompt, response_model=RuleSet
     )
 

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...")