quick-start-connectors
Confluence Quick Start Connector
This package is a utility for connecting Cohere to Confluence, featuring a simple local development setup.
Limitations
The Confluence connector will search within the space defined in your .env
, and performs a case-insensitive full-text
search against all text fields Confluence indexes by default.
Note: The search uses Confluence's advanced search language called CQL. If you wish to customize this connector's search experience, please refer to the above linked documentation for more details.
Configuration
This connector requires the following environment variables:
CONFLUENCE_USER: User email address
CONFLUENCE_API_TOKEN: API token
CONFLUENCE_PRODUCT_URL: URL to your Confluence instance, including https:// schema
CONFLUENCE_SPACE_NAME: Name of a space within your Confluence wiki
The API token can be generated by logging into Confluence and going to the API tokens page.
Optional Configuration
CONFLUENCE_SEARCH_LIMIT
This variable can be used to limit the number of results returned by the connector. By default, the connector will return 10 results.
CONFLUENCE_CONNECTOR_API_KEY
This variable can be used to set an API key for the connector.
These variables can optionally be put into a .env
file for development.
A .env-template
file is provided with all the environment variables that are used by this demo.
Development
Create a virtual environment and install dependencies with poetry. We recommend using in-project virtual environments:
$ poetry config virtualenvs.in-project true $ poetry install --no-root
To load some test documents into Confluence, this repo provides a load_data.py
script in dev/
.
$ poetry shell $ python dev/load_data.py
Next, start up the connector's server:
$ poetry run flask --app provider --debug run --port 5000
and check with curl to see that everything works:
curl --request POST \ --url http://localhost:5000/search \ --header 'Content-Type: application/json' \ --header 'Authorization: Bearer <CONNECTOR_API_KEY>' \ --data '{ "query": "BBQ" }'
Alternatively, load up the Swagger UI and try out the API from a browser: http://localhost:5000/ui/