feat: Add helm to core

.github/workflows/test_ollama.yml

@@ -9,6 +9,7 @@ jobs:
 
   run_simple_example_test:
 
+
     # needs 16 Gb RAM for phi4
     runs-on: buildjet-4vcpu-ubuntu-2204
 #    services:
@@ -17,6 +18,7 @@ jobs:
 #        ports:
 #          - 11434:11434
 
+
     steps:
       - name: Checkout repository
         uses: actions/checkout@v4
@@ -36,6 +38,7 @@ jobs:
       - name: Install dependencies
         run: |
           poetry install --no-interaction --all-extras
+
           poetry add torch
 
 #      - name: Install ollama
@@ -55,10 +58,13 @@ jobs:
       - name: Check Ollama logs
         run: docker logs ollama
 
+
       - name: Wait for Ollama to be ready
         run: |
           for i in {1..30}; do
+
             if curl -s http://localhost:11434/v1/models > /dev/null; then
+
               echo "Ollama is ready"
               exit 0
             fi
@@ -92,6 +98,7 @@ jobs:
             "input": "This is a test sentence to generate an embedding."
             }'
 
+
       - name: Dump Docker logs
         run: |
           docker ps
@@ -104,6 +111,7 @@ jobs:
           GRAPHISTRY_USERNAME: ${{ secrets.GRAPHISTRY_USERNAME }}
           GRAPHISTRY_PASSWORD: ${{ secrets.GRAPHISTRY_PASSWORD }}
           PYTHONFAULTHANDLER: 1
+
           LLM_PROVIDER: "ollama"
           LLM_API_KEY: "ollama"
           LLM_ENDPOINT: "http://localhost:11434/v1/"
@@ -114,3 +122,4 @@ jobs:
           EMBEDDING_DIMENSIONS: "4096"
           HUGGINGFACE_TOKENIZER: "Salesforce/SFR-Embedding-Mistral"
         run: poetry run python ./examples/python/simple_example.py
+

cognee/infrastructure/llm/ollama/adapter.py

@@ -5,18 +5,23 @@
 from cognee.infrastructure.llm.config import get_llm_config
 from openai import OpenAI
 import base64
-import os
 
+import os
 
 class OllamaAPIAdapter(LLMInterface):
-    """Adapter for a Generic API LLM provider using instructor with an OpenAI backend."""
+    """Adapter for a Ollama API LLM provider using instructor with an OpenAI backend."""
+
+    api_version: str
+
+    MAX_RETRIES = 5
 
-    def __init__(self, endpoint: str, api_key: str, model: str, name: str, max_tokens: int):
+    def __init__(self, endpoint: str, api_key: str, model: str, name: str, max_tokens: int, api_version: str = None) -> None:
         self.name = name
         self.model = model
         self.api_key = api_key
         self.endpoint = endpoint
         self.max_tokens = max_tokens
+        self.api_version= api_version
 
         self.aclient = instructor.from_openai(
             OpenAI(base_url=self.endpoint, api_key=self.api_key), mode=instructor.Mode.JSON
@@ -45,6 +50,7 @@ async def acreate_structured_output(
 
         return response
 
+
     def create_transcript(self, input_file: str) -> str:
         """Generate an audio transcript from a user query."""
 
@@ -74,11 +80,13 @@ def transcribe_image(self, input_file: str) -> str:
             encoded_image = base64.b64encode(image_file.read()).decode("utf-8")
 
         response = self.aclient.chat.completions.create(
+
             model=self.model,
             messages=[
                 {
                     "role": "user",
                     "content": [
+
                         {"type": "text", "text": "What’s in this image?"},
                         {
                             "type": "image_url",
@@ -95,3 +103,4 @@ def transcribe_image(self, input_file: str) -> str:
             raise ValueError("Image transcription failed. No response received.")
 
         return response.choices[0].message.content
+

infra/.gitignore

@@ -0,0 +1,162 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

infra/Chart.yaml

@@ -0,0 +1,24 @@
+apiVersion: v2
+name: cognee-chart
+description: A helm chart of the cognee backend deployment on Kubernetes environment
+
+# A chart can be either an 'application' or a 'library' chart.
+#
+# Application charts are a collection of templates that can be packaged into versioned archives
+# to be deployed.
+#
+# Library charts provide useful utilities or functions for the chart developer. They're included as
+# a dependency of application charts to inject those utilities and functions into the rendering
+# pipeline. Library charts do not define any templates and therefore cannot be deployed.
+type: application
+
+# This is the chart version. This version number should be incremented each time you make changes
+# to the chart and its templates, including the app version.
+# Versions are expected to follow Semantic Versioning (https://semver.org/)
+version: 0.1.0
+
+# This is the version number of the application being deployed. This version number should be
+# incremented each time you make changes to the application. Versions are not expected to
+# follow Semantic Versioning. They should reflect the version the application is using.
+# It is recommended to use it with quotes.
+appVersion: "1.16.0"

infra/Dockerfile

@@ -0,0 +1,45 @@
+FROM python:3.11-slim
+
+# Set build argument
+ARG DEBUG
+
+# Set environment variable based on the build argument
+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 --all-extras --no-root --no-dev
+
+
+# Set the PYTHONPATH environment variable to include the /app directory
+ENV PYTHONPATH=/app
+
+COPY cognee/ /app/cognee
+
+# Copy Alembic configuration
+COPY alembic.ini /app/alembic.ini
+COPY alembic/ /app/alembic
+
+COPY entrypoint.sh /app/entrypoint.sh
+RUN chmod +x /app/entrypoint.sh
+
+RUN sed -i 's/\r$//' /app/entrypoint.sh
+
+ENTRYPOINT ["/app/entrypoint.sh"]

infra/README.md

@@ -0,0 +1,25 @@
+
+# cognee-infra-helm
+General infrastructure setup for Cognee on Kubernetes using a Helm chart.
+
+## Prerequisites
+Before deploying the Helm chart, ensure the following prerequisites are met: 
+
+**Kubernetes Cluster**: A running Kubernetes cluster (e.g., Minikube, GKE, EKS).
+
+**Helm**: Installed and configured for your Kubernetes cluster. You can install Helm by following the [official guide](https://helm.sh/docs/intro/install/). 
+
+**kubectl**: Installed and configured to interact with your cluster. Follow the instructions [here](https://kubernetes.io/docs/tasks/tools/install-kubectl/).
+
+Clone the Repository Clone this repository to your local machine and navigate to the directory.
+
+## Deploy Helm Chart:
+
+   ```bash
+   helm install cognee ./cognee-chart
+   ```
+
+**Uninstall Helm Release**:  
+   ```bash
+   helm uninstall cognee
+   ```