refactor: migrate starter kit to examples
This commit is contained in:
Hande
parent
995e7aa483
commit
d720abee01
9 changed files with 2 additions and 475 deletions
|
|
@ -1,19 +0,0 @@
|
||||||
# In case you choose to use OpenAI provider, just adjust the model and api_key.
|
|
||||||
LLM_API_KEY=""
|
|
||||||
LLM_MODEL="openai/gpt-5-mini"
|
|
||||||
LLM_PROVIDER="openai"
|
|
||||||
# Not needed if you use OpenAI
|
|
||||||
LLM_ENDPOINT=""
|
|
||||||
LLM_API_VERSION=""
|
|
||||||
|
|
||||||
# In case you choose to use OpenAI provider, just adjust the model and api_key.
|
|
||||||
EMBEDDING_API_KEY=""
|
|
||||||
EMBEDDING_MODEL="openai/text-embedding-3-large"
|
|
||||||
EMBEDDING_PROVIDER="openai"
|
|
||||||
# Not needed if you use OpenAI
|
|
||||||
EMBEDDING_ENDPOINT=""
|
|
||||||
EMBEDDING_API_VERSION=""
|
|
||||||
|
|
||||||
|
|
||||||
GRAPHISTRY_USERNAME=""
|
|
||||||
GRAPHISTRY_PASSWORD=""
|
|
||||||
196
cognee-starter-kit/.gitignore
vendored
196
cognee-starter-kit/.gitignore
vendored
|
|
@ -1,196 +0,0 @@
|
||||||
.data
|
|
||||||
.env
|
|
||||||
.local.env
|
|
||||||
.prod.env
|
|
||||||
cognee/.data/
|
|
||||||
|
|
||||||
code_pipeline_output*/
|
|
||||||
|
|
||||||
*.lance/
|
|
||||||
.DS_Store
|
|
||||||
# Byte-compiled / optimized / DLL files
|
|
||||||
__pycache__/
|
|
||||||
*.py[cod]
|
|
||||||
*$py.class
|
|
||||||
|
|
||||||
full_run.ipynb
|
|
||||||
|
|
||||||
# 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
|
|
||||||
|
|
||||||
# Cognee logs directory - keep directory, ignore contents
|
|
||||||
logs/*
|
|
||||||
!logs/.gitkeep
|
|
||||||
!logs/README.md
|
|
||||||
|
|
||||||
# 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/#use-with-ide
|
|
||||||
.pdm.toml
|
|
||||||
|
|
||||||
# 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
|
|
||||||
.env.local
|
|
||||||
.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/
|
|
||||||
|
|
||||||
.vscode/
|
|
||||||
cognee/data/
|
|
||||||
cognee/cache/
|
|
||||||
|
|
||||||
# Default cognee system directory, used in development
|
|
||||||
.cognee_system/
|
|
||||||
.data_storage/
|
|
||||||
.artifacts/
|
|
||||||
.anon_id
|
|
||||||
|
|
||||||
node_modules/
|
|
||||||
|
|
||||||
# Evals
|
|
||||||
SWE-bench_testsample/
|
|
||||||
|
|
||||||
# ChromaDB Data
|
|
||||||
.chromadb_data/
|
|
||||||
|
|
@ -1,89 +0,0 @@
|
||||||
|
|
||||||
# Cognee Starter Kit
|
|
||||||
Welcome to the <a href="https://github.com/topoteretes/cognee">cognee</a> Starter Repo! This repository is designed to help you get started quickly by providing a structured dataset and pre-built data pipelines using cognee to build powerful knowledge graphs.
|
|
||||||
|
|
||||||
You can use this repo to ingest, process, and visualize data in minutes.
|
|
||||||
|
|
||||||
By following this guide, you will:
|
|
||||||
|
|
||||||
- Load structured company and employee data
|
|
||||||
- Utilize pre-built pipelines for data processing
|
|
||||||
- Perform graph-based search and query operations
|
|
||||||
- Visualize entity relationships effortlessly on a graph
|
|
||||||
|
|
||||||
# How to Use This Repo 🛠
|
|
||||||
|
|
||||||
## Install uv if you don't have it on your system
|
|
||||||
```
|
|
||||||
pip install uv
|
|
||||||
```
|
|
||||||
## Install dependencies
|
|
||||||
```
|
|
||||||
uv sync
|
|
||||||
```
|
|
||||||
|
|
||||||
## Setup LLM
|
|
||||||
Add environment variables to `.env` file.
|
|
||||||
In case you choose to use OpenAI provider, add just the model and api_key.
|
|
||||||
```
|
|
||||||
LLM_PROVIDER=""
|
|
||||||
LLM_MODEL=""
|
|
||||||
LLM_ENDPOINT=""
|
|
||||||
LLM_API_KEY=""
|
|
||||||
LLM_API_VERSION=""
|
|
||||||
|
|
||||||
EMBEDDING_PROVIDER=""
|
|
||||||
EMBEDDING_MODEL=""
|
|
||||||
EMBEDDING_ENDPOINT=""
|
|
||||||
EMBEDDING_API_KEY=""
|
|
||||||
EMBEDDING_API_VERSION=""
|
|
||||||
```
|
|
||||||
|
|
||||||
Activate the Python environment:
|
|
||||||
```
|
|
||||||
source .venv/bin/activate
|
|
||||||
```
|
|
||||||
|
|
||||||
## Run the Default Pipeline
|
|
||||||
|
|
||||||
This script runs the cognify pipeline with default settings. It ingests text data, builds a knowledge graph, and allows you to run search queries.
|
|
||||||
|
|
||||||
```
|
|
||||||
python src/pipelines/default.py
|
|
||||||
```
|
|
||||||
|
|
||||||
## Run the Low-Level Pipeline
|
|
||||||
|
|
||||||
This script implements its own pipeline with custom ingestion task. It processes the given JSON data about companies and employees, making it searchable via a graph.
|
|
||||||
|
|
||||||
```
|
|
||||||
python src/pipelines/low_level.py
|
|
||||||
```
|
|
||||||
|
|
||||||
## Run the Custom Model Pipeline
|
|
||||||
|
|
||||||
Custom model uses custom pydantic model for graph extraction. This script categorizes programming languages as an example and visualizes relationships.
|
|
||||||
|
|
||||||
```
|
|
||||||
python src/pipelines/custom-model.py
|
|
||||||
```
|
|
||||||
|
|
||||||
## Graph preview
|
|
||||||
|
|
||||||
cognee provides a visualize_graph function that will render the graph for you.
|
|
||||||
|
|
||||||
```
|
|
||||||
graph_file_path = str(
|
|
||||||
pathlib.Path(
|
|
||||||
os.path.join(pathlib.Path(__file__).parent, ".artifacts/graph_visualization.html")
|
|
||||||
).resolve()
|
|
||||||
)
|
|
||||||
await visualize_graph(graph_file_path)
|
|
||||||
```
|
|
||||||
|
|
||||||
# What will you build with cognee?
|
|
||||||
|
|
||||||
- Expand the dataset by adding more structured/unstructured data
|
|
||||||
- Customize the data model to fit your use case
|
|
||||||
- Use the search API to build an intelligent assistant
|
|
||||||
- Visualize knowledge graphs for better insights
|
|
||||||
|
|
@ -1,11 +0,0 @@
|
||||||
[project]
|
|
||||||
name = "cognee-starter"
|
|
||||||
version = "0.1.1"
|
|
||||||
description = "Starter project which can be harvested for parts"
|
|
||||||
readme = "README.md"
|
|
||||||
|
|
||||||
requires-python = ">=3.10, <=3.13"
|
|
||||||
|
|
||||||
dependencies = [
|
|
||||||
"cognee>=0.1.38,<1.0.0",
|
|
||||||
]
|
|
||||||
|
|
@ -1,38 +0,0 @@
|
||||||
[
|
|
||||||
{
|
|
||||||
"name": "TechNova Inc.",
|
|
||||||
"departments": [
|
|
||||||
"Engineering",
|
|
||||||
"Marketing"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "GreenFuture Solutions",
|
|
||||||
"departments": [
|
|
||||||
"Research & Development",
|
|
||||||
"Sales",
|
|
||||||
"Customer Support"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Skyline Financials",
|
|
||||||
"departments": [
|
|
||||||
"Accounting"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "MediCare Plus",
|
|
||||||
"departments": [
|
|
||||||
"Healthcare",
|
|
||||||
"Administration"
|
|
||||||
]
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "NextGen Robotics",
|
|
||||||
"departments": [
|
|
||||||
"AI Development",
|
|
||||||
"Manufacturing",
|
|
||||||
"HR"
|
|
||||||
]
|
|
||||||
}
|
|
||||||
]
|
|
||||||
|
|
@ -1,52 +0,0 @@
|
||||||
[
|
|
||||||
{
|
|
||||||
"name": "John Doe",
|
|
||||||
"company": "TechNova Inc.",
|
|
||||||
"department": "Engineering"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Jane Smith",
|
|
||||||
"company": "TechNova Inc.",
|
|
||||||
"department": "Marketing"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Alice Johnson",
|
|
||||||
"company": "GreenFuture Solutions",
|
|
||||||
"department": "Sales"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Bob Williams",
|
|
||||||
"company": "GreenFuture Solutions",
|
|
||||||
"department": "Customer Support"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Michael Brown",
|
|
||||||
"company": "Skyline Financials",
|
|
||||||
"department": "Accounting"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Emily Davis",
|
|
||||||
"company": "MediCare Plus",
|
|
||||||
"department": "Healthcare"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "David Wilson",
|
|
||||||
"company": "MediCare Plus",
|
|
||||||
"department": "Administration"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Emma Thompson",
|
|
||||||
"company": "NextGen Robotics",
|
|
||||||
"department": "AI Development"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Chris Martin",
|
|
||||||
"company": "NextGen Robotics",
|
|
||||||
"department": "Manufacturing"
|
|
||||||
},
|
|
||||||
{
|
|
||||||
"name": "Sophia White",
|
|
||||||
"company": "NextGen Robotics",
|
|
||||||
"department": "HR"
|
|
||||||
}
|
|
||||||
]
|
|
||||||
|
|
@ -1,67 +0,0 @@
|
||||||
import os
|
|
||||||
import asyncio
|
|
||||||
import pathlib
|
|
||||||
from cognee import config, add, cognify, search, SearchType, prune, visualize_graph
|
|
||||||
|
|
||||||
|
|
||||||
async def main():
|
|
||||||
data_directory_path = str(
|
|
||||||
pathlib.Path(os.path.join(pathlib.Path(__file__).parent, ".data_storage")).resolve()
|
|
||||||
)
|
|
||||||
# Set up the data directory. Cognee will store files here.
|
|
||||||
config.data_root_directory(data_directory_path)
|
|
||||||
|
|
||||||
cognee_directory_path = str(
|
|
||||||
pathlib.Path(os.path.join(pathlib.Path(__file__).parent, ".cognee_system")).resolve()
|
|
||||||
)
|
|
||||||
# Set up the Cognee system directory. Cognee will store system files and databases here.
|
|
||||||
config.system_root_directory(cognee_directory_path)
|
|
||||||
|
|
||||||
# Prune data and system metadata before running, only if we want "fresh" state.
|
|
||||||
await prune.prune_data()
|
|
||||||
await prune.prune_system(metadata=True)
|
|
||||||
|
|
||||||
text = "The Python programming language is widely used in data analysis, web development, and machine learning."
|
|
||||||
|
|
||||||
# Add the text data to Cognee.
|
|
||||||
await add(text)
|
|
||||||
|
|
||||||
# Cognify the text data.
|
|
||||||
await cognify()
|
|
||||||
|
|
||||||
# Or use our simple graph preview
|
|
||||||
graph_file_path = str(
|
|
||||||
pathlib.Path(
|
|
||||||
os.path.join(pathlib.Path(__file__).parent, ".artifacts/graph_visualization.html")
|
|
||||||
).resolve()
|
|
||||||
)
|
|
||||||
await visualize_graph(graph_file_path)
|
|
||||||
|
|
||||||
# Completion query that uses graph data to form context.
|
|
||||||
graph_completion = await search(
|
|
||||||
query_text="What is python?", query_type=SearchType.GRAPH_COMPLETION
|
|
||||||
)
|
|
||||||
print("Graph completion result is:")
|
|
||||||
print(graph_completion)
|
|
||||||
|
|
||||||
# Completion query that uses document chunks to form context.
|
|
||||||
rag_completion = await search(
|
|
||||||
query_text="What is Python?", query_type=SearchType.RAG_COMPLETION
|
|
||||||
)
|
|
||||||
print("Completion result is:")
|
|
||||||
print(rag_completion)
|
|
||||||
|
|
||||||
# Query all summaries related to query.
|
|
||||||
summaries = await search(query_text="Python", query_type=SearchType.SUMMARIES)
|
|
||||||
print("Summary results are:")
|
|
||||||
for summary in summaries:
|
|
||||||
print(summary)
|
|
||||||
|
|
||||||
chunks = await search(query_text="Python", query_type=SearchType.CHUNKS)
|
|
||||||
print("Chunk results are:")
|
|
||||||
for chunk in chunks:
|
|
||||||
print(chunk)
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == "__main__":
|
|
||||||
asyncio.run(main())
|
|
||||||
|
|
@ -49,12 +49,11 @@ class Company(DataPoint):
|
||||||
|
|
||||||
|
|
||||||
ROOT = Path(__file__).resolve().parent
|
ROOT = Path(__file__).resolve().parent
|
||||||
DATA_DIR = ROOT.parent / "data"
|
|
||||||
COGNEE_DIR = ROOT / ".cognee_system"
|
COGNEE_DIR = ROOT / ".cognee_system"
|
||||||
ARTIFACTS_DIR = ROOT / ".artifacts"
|
ARTIFACTS_DIR = ROOT / ".artifacts"
|
||||||
GRAPH_HTML = ARTIFACTS_DIR / "graph_visualization.html"
|
GRAPH_HTML = ARTIFACTS_DIR / "graph_visualization.html"
|
||||||
COMPANIES_JSON = DATA_DIR / "companies.json"
|
COMPANIES_JSON = ROOT / "companies.json"
|
||||||
PEOPLE_JSON = DATA_DIR / "people.json"
|
PEOPLE_JSON = ROOT / "people.json"
|
||||||
|
|
||||||
|
|
||||||
def load_json_file(path: Path) -> Any:
|
def load_json_file(path: Path) -> Any:
|
||||||
Loading…
Add table
Reference in a new issue