Usage

There are two ways to interact with the service:

1. Accessing the API endpoints
2. The Admin App

API endpoints

There are two major endpoints for Question-Answering:

• Embeddings search: Finds the most similar content in the database using cosine similarity between embeddings.
• LLM response: Crafts a custom response using LLM chat using the most similar content.

See docs or SwaggerUI at https://<DOMAIN>/api/docs or https://<DOMAIN>/docs for more details and other API endpoints.

Embeddings search

curl -X 'POST' \
  'https://[DOMAIN]/api/embeddings-search' \
  -H 'accept: application/json' \
  -H 'Authorization: Bearer <BEARER TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "query_text": "how are you?",
  "query_metadata": {}
}'

LLM response

curl -X 'POST' \
  'https://[DOMAIN]/api/llm-response' \
  -H 'accept: application/json' \
  -H 'Authorization: Bearer <BEARER TOKEN>' \
  -H 'Content-Type: application/json' \
  -d '{
  "query_text": "this is my question",
  "query_metadata": {}
}'

Admin app

You can access the admin console at

https://[DOMAIN]/

On the Admin app, you can:

• Manage content for more details
• Use the playground to test the Question-Answering service
• View dashboards