gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into feat/COG-544-eval-on-swe-bench

Browse source
This commit is contained in:
Rita Aleksziev 2024-11-19 09:38:11 +01:00
commit 9973afffa1
7 changed files with 36 additions and 22 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
.env.template
View file

@ -8,14 +8,14 @@ GRAPHISTRY_PASSWORD=
SENTRY_REPORTING_URL=
# "neo4j" or "networkx"
GRAPH_DATABASE_PROVIDER="neo4j"
GRAPH_DATABASE_PROVIDER="networkx"
# Not needed if using networkx
GRAPH_DATABASE_URL=
GRAPH_DATABASE_USERNAME=
GRAPH_DATABASE_PASSWORD=
# "qdrant", "pgvector", "weaviate" or "lancedb"
VECTOR_DB_PROVIDER="qdrant"
VECTOR_DB_PROVIDER="lancedb"
# Not needed if using "lancedb" or "pgvector"
VECTOR_DB_URL=
VECTOR_DB_KEY=

2
.github/workflows/test_cognee_llama_index_notebook.yml vendored
View file

@ -46,7 +46,7 @@ jobs:
- name: Install dependencies
run: |
poetry install --no-interaction --all-extras --no-root
poetry install --no-interaction --all-extras
poetry add jupyter --no-interaction
- name: Execute Jupyter Notebook

42
README.md
View file

@ -10,7 +10,7 @@
We build for developers who need a reliable, production-ready data layer for AI applications
## What is cognee?
## What is cognee?
Cognee implements scalable, modular ECL (Extract, Cognify, Load) pipelines that allow you to interconnect and retrieve past conversations, documents, and audio transcriptions while reducing hallucinations, developer effort, and cost.
Try it in a Google Colab <a href="https://colab.research.google.com/drive/1g-Qnx6l_ecHZi0IOw23rg0qC4TYvEvWZ?usp=sharing">notebook</a> or have a look at our <a href="https://topoteretes.github.io/cognee">documentation</a>
@ -18,9 +18,6 @@ Try it in a Google Colab <a href="https://colab.research.google.com/drive/1g-Qn
If you have questions, join our <a href="https://discord.gg/NQPKmU5CCg">Discord</a> community
## 📦 Installation
### With pip
@ -47,6 +44,7 @@ poetry add cognee
poetry add cognee -E postgres
```
## 💻 Basic Usage
### Setup
@ -83,7 +81,7 @@ docker-compose up
```
Then navigate to localhost:3000
If you want to use the UI with PostgreSQL through docker-compose make sure to set the following values in the .env file:
If you want to use Cognee with PostgreSQL, make sure to set the following values in the .env file:
```
DB_PROVIDER=postgres
@ -97,9 +95,7 @@ DB_PASSWORD=cognee
### Simple example
First, copy `.env.template` to `.env` and add your OpenAI API key to the LLM_API_KEY field.
Optionally, set `VECTOR_DB_PROVIDER="lancedb"` in `.env` to simplify setup.
First, copy `.env.template` to `.env` and add your OpenAI API key to the LLM_API_KEY field.
This script will run the default pipeline:
@ -140,7 +136,7 @@ async def main():
asyncio.run(main())
```
A version of this example is here: `examples/pyton/simple_example.py`
A version of this example is here: `examples/python/simple_example.py`
### Create your own memory store
@ -251,7 +247,6 @@ Cognee supports a variety of tools and services for different operations:
Check out our demo notebook [here](https://github.com/topoteretes/cognee/blob/main/notebooks/cognee_demo.ipynb)
[<img src="https://i3.ytimg.com/vi/-ARUfIzhzC4/maxresdefault.jpg" width="100%">](https://www.youtube.com/watch?v=BDFt4xVPmro "Learn about cognee: 55")
@ -274,11 +269,6 @@ Please see the cognee [Development Guide](https://topoteretes.github.io/cognee/q
pip install cognee
```
## Star History
[![Star History Chart](https://api.star-history.com/svg?repos=topoteretes/cognee&type=Date)](https://star-history.com/#topoteretes/cognee&Date)
## 💫 Contributors
<a href="https://github.com/topoteretes/cognee/graphs/contributors">
@ -286,3 +276,25 @@ pip install cognee
</a>
## Star History
[![Star History Chart](https://api.star-history.com/svg?repos=topoteretes/cognee&type=Date)](https://star-history.com/#topoteretes/cognee&Date)
## Vector & Graph Databases Implementation State
<style>
table {
width: 100%;
}
</style>
| Name | Type | Current state | Known Issues |
|------------------|--------------------|-------------------|---------------------------------------|
| Qdrant | Vector | Stable &#x2705; | |
| Weaviate | Vector | Stable &#x2705; | |
| LanceDB | Vector | Stable &#x2705; | |
| Neo4j | Graph | Stable &#x2705; | |
| NetworkX | Graph | Stable &#x2705; | |
| FalkorDB | Vector/Graph | Unstable &#x274C; | |
| PGVector | Vector | Unstable &#x274C; | Postgres DB returns the Timeout error |

4
cognee-frontend/src/ui/Partials/SettingsModal/Settings.tsx
View file

@ -30,8 +30,8 @@ const defaultProvider = {
};
const defaultModel = {
label: 'gpt-4o',
value: 'gpt-4o',
label: 'gpt-4o-mini',
value: 'gpt-4o-mini',
};
export default function Settings({ onDone = () => {}, submitButtonText = 'Save' }) {

2
cognee/infrastructure/llm/config.py
View file

@ -4,7 +4,7 @@ from pydantic_settings import BaseSettings, SettingsConfigDict
class LLMConfig(BaseSettings):
llm_provider: str = "openai"
llm_model: str = "gpt-4o"
llm_model: str = "gpt-4o-mini"
llm_endpoint: str = ""
llm_api_key: Optional[str] = None
llm_temperature: float = 0.0

3
cognee/modules/settings/get_settings.py
View file

@ -73,6 +73,9 @@ def get_settings() -> SettingsDict:
"providers": llm_providers,
"models": {
"openai": [{
"value": "gpt-4o-mini",
"label": "gpt-4o-mini",
}, {
"value": "gpt-4o",
"label": "gpt-4o",
}, {

1
examples/python/simple_example.py
View file

@ -6,7 +6,6 @@ from cognee.api.v1.search import SearchType
# 1. Copy `.env.template` and rename it to `.env`.
# 2. Add your OpenAI API key to the `.env` file in the `LLM_API_KEY` field:
# LLM_API_KEY = "your_key_here"
# 3. (Optional) To minimize setup effort, set `VECTOR_DB_PROVIDER="lancedb"` in `.env".
async def main():
# Create a clean slate for cognee -- reset data and system state