mirror of
https://github.com/elastic/elasticsearch.git
synced 2025-04-25 07:37:19 -04:00
125 lines
No EOL
3.2 KiB
Text
125 lines
No EOL
3.2 KiB
Text
[[infer-service-mistral]]
|
|
=== Mistral {infer} integration
|
|
|
|
.New API reference
|
|
[sidebar]
|
|
--
|
|
For the most up-to-date API details, refer to {api-es}/group/endpoint-inference[{infer-cap} APIs].
|
|
--
|
|
|
|
Creates an {infer} endpoint to perform an {infer} task with the `mistral` service.
|
|
|
|
|
|
[discrete]
|
|
[[infer-service-mistral-api-request]]
|
|
==== {api-request-title}
|
|
|
|
`PUT /_inference/<task_type>/<inference_id>`
|
|
|
|
[discrete]
|
|
[[infer-service-mistral-api-path-params]]
|
|
==== {api-path-parms-title}
|
|
|
|
`<inference_id>`::
|
|
(Required, string)
|
|
include::inference-shared.asciidoc[tag=inference-id]
|
|
|
|
`<task_type>`::
|
|
(Required, string)
|
|
include::inference-shared.asciidoc[tag=task-type]
|
|
+
|
|
--
|
|
Available task types:
|
|
|
|
* `text_embedding`.
|
|
--
|
|
|
|
[discrete]
|
|
[[infer-service-mistral-api-request-body]]
|
|
==== {api-request-body-title}
|
|
|
|
`chunking_settings`::
|
|
(Optional, object)
|
|
include::inference-shared.asciidoc[tag=chunking-settings]
|
|
|
|
`max_chunk_size`:::
|
|
(Optional, integer)
|
|
include::inference-shared.asciidoc[tag=chunking-settings-max-chunking-size]
|
|
|
|
`overlap`:::
|
|
(Optional, integer)
|
|
include::inference-shared.asciidoc[tag=chunking-settings-overlap]
|
|
|
|
`sentence_overlap`:::
|
|
(Optional, integer)
|
|
include::inference-shared.asciidoc[tag=chunking-settings-sentence-overlap]
|
|
|
|
`strategy`:::
|
|
(Optional, string)
|
|
include::inference-shared.asciidoc[tag=chunking-settings-strategy]
|
|
|
|
`service`::
|
|
(Required, string)
|
|
The type of service supported for the specified task type. In this case,
|
|
`mistral`.
|
|
|
|
`service_settings`::
|
|
(Required, object)
|
|
include::inference-shared.asciidoc[tag=service-settings]
|
|
+
|
|
--
|
|
These settings are specific to the `mistral` service.
|
|
--
|
|
|
|
`api_key`:::
|
|
(Required, string)
|
|
A valid API key for your Mistral account.
|
|
You can find your Mistral API keys or you can create a new one
|
|
https://console.mistral.ai/api-keys/[on the API Keys page].
|
|
+
|
|
--
|
|
include::inference-shared.asciidoc[tag=api-key-admonition]
|
|
--
|
|
|
|
`model`:::
|
|
(Required, string)
|
|
The name of the model to use for the {infer} task.
|
|
Refer to the https://docs.mistral.ai/getting-started/models/[Mistral models documentation]
|
|
for the list of available text embedding models.
|
|
|
|
`max_input_tokens`:::
|
|
(Optional, integer)
|
|
Allows you to specify the maximum number of tokens per input before chunking occurs.
|
|
|
|
`rate_limit`:::
|
|
(Optional, object)
|
|
By default, the `mistral` service sets the number of requests allowed per minute to `240`.
|
|
This helps to minimize the number of rate limit errors returned from the Mistral API.
|
|
To modify this, set the `requests_per_minute` setting of this object in your service settings:
|
|
+
|
|
--
|
|
include::inference-shared.asciidoc[tag=request-per-minute-example]
|
|
--
|
|
|
|
|
|
[discrete]
|
|
[[inference-example-mistral]]
|
|
==== Mistral service example
|
|
|
|
The following example shows how to create an {infer} endpoint called
|
|
`mistral-embeddings-test` to perform a `text_embedding` task type.
|
|
|
|
[source,console]
|
|
------------------------------------------------------------
|
|
PUT _inference/text_embedding/mistral-embeddings-test
|
|
{
|
|
"service": "mistral",
|
|
"service_settings": {
|
|
"api_key": "<api_key>",
|
|
"model": "mistral-embed" <1>
|
|
}
|
|
}
|
|
------------------------------------------------------------
|
|
// TEST[skip:TBD]
|
|
<1> The `model` must be the ID of a text embedding model which can be found in the
|
|
https://docs.mistral.ai/getting-started/models/[Mistral models documentation]. |