Skip to main content
PATCH
/
chats
/
{workspace_uid}
/
settings
cURL
curl \
  -X PATCH 'MEILISEARCH_URL/chats/WORKSPACE_NAME/settings' \
  -H "Authorization: Bearer MEILISEARCH_KEY" \
  -H "Content-Type: application/json" \
  --data-binary '{ "apiKey": "your-valid-api-key" }'
{
  "source": "openAi",
  "baseUrl": null,
  "apiKey": "$LLM_API_KEY",
  "prompts": {
    "system": "My super system prompt",
    "searchDescription": "My super search tool description",
    "searchQParam": "My awesome q search parameter description",
    "searchIndexUidParam": "My incredible index uid param description"
  }
}

Authorizations

​
Authorization
string
header
required

An API key is a token that you provide when making API calls. Read more about how to secure your project.

Include the API key to the Authorization header, for instance:

-H 'Authorization: Bearer 6436fc5237b0d6e0d64253fbaac21d135012ecf1'

If you use a SDK, ensure you instantiate the client with the API key, for instance with JS SDK:

const client = new MeiliSearch({
  host: 'MEILISEARCH_URL',
  apiKey: '6436fc5237b0d6e0d64253fbaac21d135012ecf1'
});

Path Parameters

​
workspace_uid
string
required

The unique identifier of the chat workspace.

Body

application/json

Settings for a chat workspace

​
source
null | enum<string>

LLM provider to use for chat completions

Available options:
openAi,
mistral,
azureOpenAi,
vLlm
​
orgId
string | null

Organization ID for the LLM provider

Example:

"dcba4321..."

​
projectId
string | null

Project ID for the LLM provider

Example:

"4321dcba..."

​
apiVersion
string | null

API version for the LLM provider

Example:

"2024-02-01"

​
deploymentId
string | null

Deployment ID for Azure OpenAI

Example:

"1234abcd..."

​
baseUrl
string | null

Base URL for the LLM API

Example:

"https://api.mistral.ai/v1"

​
apiKey
string | null

API key for authentication with the LLM provider

Example:

"abcd1234..."

​
prompts
object

Custom prompts for chat completions

Response

Chat settings retrieved.