docs: update fastapi /v1/chat/endpoint base model
What does this merge request do and why?
A chore to align our Gitlab AI Feature docs with the following example in AI Gateway's FastAPI docs.
We reference we are using Claude 3 for Duo Chat in most of our docs, so the following MR reflects that reality in the AI Gateway API v1/chat/agent
endpoint.
How to set up and validate locally
Before | After |
---|---|
- Open the ai-gateway docs at
http://localhost:5052/docs#/chat/chat_v1_chat_agent_post
- Run the following example requeset
curl --request POST \
--url 'http://localhost:5052/v1/chat/agent' \
--header 'Authorization: Bearer <access_token>' \
--header 'X-Gitlab-Authentication-Type: oidc' \
--header 'Content-Type: application/json' \
--data-raw '{
"prompt_components": [
{
"type":"prompt",
"payload": {
"content": [
{
"role": "user",
"content": "Hi, how are you?"
}
],
"provider": "anthropic",
"model": "claude-3-sonnet-20240229"
},
"metadata": {
"source": "GitLab EE",
"version": "16.7.0"
}
}
]
}'
- Make the response is a valid
200
Merge request checklist
-
Tests added for new functionality. If not, please raise an issue to follow up. -
Documentation added/updated, if needed.
Edited by Nathan Weinshenker