chore: Update service readme (#93)

* chore: Update service readme

* Update README.md

* point to the image in server readme

* chore: Update readme + rename image to graphiti
This commit is contained in:
Pavlo Paliychuk 2024-09-06 16:11:04 -04:00 committed by GitHub
parent 39ad28d6db
commit 66111a66db
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
3 changed files with 45 additions and 13 deletions

View file

@ -16,7 +16,7 @@ on:
env: env:
REGISTRY: docker.io REGISTRY: docker.io
IMAGE_NAME: zepai/graph-service IMAGE_NAME: zepai/graphiti
jobs: jobs:
docker-image: docker-image:

View file

@ -149,6 +149,12 @@ await graphiti.search('Who was the California Attorney General?', center_node_uu
graphiti.close() graphiti.close()
``` ```
## Graph Service
The `server` directory contains an API service for interacting with the Graphiti API. It is built using FastAPI.
Please see the [server README](./server/README.md) for more information.
## Documentation ## Documentation
- [Guides and API documentation](https://help.getzep.com/graphiti). - [Guides and API documentation](https://help.getzep.com/graphiti).

View file

@ -1,32 +1,58 @@
# graph-service # graph-service
Graph service is a fast api server implementing the Graphiti package. Graph service is a fast api server implementing the [graphiti](https://github.com/getzep/graphiti) package.
## Running Instructions ## Running Instructions
1. Ensure you have Docker and Docker Compose installed on your system. 1. Ensure you have Docker and Docker Compose installed on your system.
2. Clone the repository and navigate to the `graph-service` directory. 2. Add `zepai/graphiti:latest` to your service setup
3. Create a `.env` file in the `graph-service` directory with the following content: 3. Make sure to pass the following environment variables to the service
``` ```
OPENAI_API_KEY=your_openai_api_key OPENAI_API_KEY=your_openai_api_key
NEO4J_USER=neo4j NEO4J_USER=your_neo4j_user
NEO4J_PASSWORD=your_neo4j_password NEO4J_PASSWORD=your_neo4j_password
NEO4J_PORT=7687 NEO4J_PORT=your_neo4j_port
``` ```
Replace `your_openai_api_key` and `your_neo4j_password` with your actual OpenAI API key and desired Neo4j password. 4. This service depends on having access to a neo4j instance, you may wish to add a neo4j image to your service setup as well. Or you may wish to use neo4j cloud or a desktop version if running this locally.
4. Run the following command to start the services: An example of docker compose setup may look like this:
``` ```yml
docker-compose up --build version: '3.8'
services:
graph:
image: zepai/graphiti:latest
ports:
- "8000:8000"
environment:
- OPENAI_API_KEY=${OPENAI_API_KEY}
- NEO4J_URI=bolt://neo4j:${NEO4J_PORT}
- NEO4J_USER=${NEO4J_USER}
- NEO4J_PASSWORD=${NEO4J_PASSWORD}
neo4j:
image: neo4j:5.22.0
ports:
- "7474:7474" # HTTP
- "${NEO4J_PORT}:${NEO4J_PORT}" # Bolt
volumes:
- neo4j_data:/data
environment:
- NEO4J_AUTH=${NEO4J_USER}/${NEO4J_PASSWORD}
volumes:
neo4j_data:
``` ```
5. The graph service will be available at `http://localhost:8000`. 5. Once you start the service, it will be available at `http://localhost:8000` (or the port you have specified in the docker compose file).
6. You may access the swagger docs at `http://localhost:8000/docs`. 6. You may access the swagger docs at `http://localhost:8000/docs`. You may also access redocs at `http://localhost:8000/redoc`.
7. You may also access the neo4j browser at `http://localhost:7474`. 7. You may also access the neo4j browser at `http://localhost:7474` (the port depends on the neo4j instance you are using).