|
|
@@ -34,7 +34,8 @@ include::inference-shared.asciidoc[tag=task-type]
|
|
|
--
|
|
|
Available task types:
|
|
|
|
|
|
-* `text_embedding`.
|
|
|
+* `text_embedding`,
|
|
|
+* `rerank`.
|
|
|
--
|
|
|
|
|
|
[discrete]
|
|
|
@@ -91,6 +92,26 @@ To modify this, set the `requests_per_minute` setting of this object in your ser
|
|
|
include::inference-shared.asciidoc[tag=request-per-minute-example]
|
|
|
--
|
|
|
|
|
|
+`task_settings`::
|
|
|
+(Optional, object)
|
|
|
+include::inference-shared.asciidoc[tag=task-settings]
|
|
|
++
|
|
|
+.`task_settings` for the `rerank` task type
|
|
|
+[%collapsible%closed]
|
|
|
+=====
|
|
|
+`truncate_input_tokens`:::
|
|
|
+(Optional, integer)
|
|
|
+Specifies the maximum number of tokens per input document before truncation.
|
|
|
+
|
|
|
+`return_documents`:::
|
|
|
+(Optional, boolean)
|
|
|
+Specify whether to return doc text within the results.
|
|
|
+
|
|
|
+`top_n`:::
|
|
|
+(Optional, integer)
|
|
|
+The number of most relevant documents to return. Defaults to the number of input documents.
|
|
|
+=====
|
|
|
+
|
|
|
|
|
|
[discrete]
|
|
|
[[inference-example-watsonx-ai]]
|
|
|
@@ -118,4 +139,35 @@ PUT _inference/text_embedding/watsonx-embeddings
|
|
|
You can find on the https://cloud.ibm.com/iam/apikeys[API keys page of your account].
|
|
|
<2> The {infer} endpoint URL you created on Watsonx.
|
|
|
<3> The ID of your IBM Cloud project.
|
|
|
-<4> A valid API version parameter. You can find the active version data parameters https://cloud.ibm.com/apidocs/watsonx-ai#active-version-dates[here].
|
|
|
+<4> A valid API version parameter. You can find the active version data parameters https://cloud.ibm.com/apidocs/watsonx-ai#active-version-dates[here].
|
|
|
+
|
|
|
+The following example shows how to create an {infer} endpoint called `watsonx-rerank` to perform a `rerank` task type.
|
|
|
+
|
|
|
+[source,console]
|
|
|
+------------------------------------------------------------
|
|
|
+PUT _inference/rerank/watsonx-rerank
|
|
|
+{
|
|
|
+ "service": "watsonxai",
|
|
|
+ "service_settings": {
|
|
|
+ "api_key": "<api_key>", <1>
|
|
|
+ "url": "<url>", <2>
|
|
|
+ "model_id": "cross-encoder/ms-marco-minilm-l-12-v2",
|
|
|
+ "project_id": "<project_id>", <3>
|
|
|
+ "api_version": "2024-05-02" <4>
|
|
|
+ },
|
|
|
+ "task_settings": {
|
|
|
+ "truncate_input_tokens": 50, <5>
|
|
|
+ "return_documents": true, <6>
|
|
|
+ "top_n": 3 <7>
|
|
|
+ }
|
|
|
+}
|
|
|
+------------------------------------------------------------
|
|
|
+// TEST[skip:TBD]
|
|
|
+<1> A valid Watsonx API key.
|
|
|
+You can find on the https://cloud.ibm.com/iam/apikeys[API keys page of your account].
|
|
|
+<2> The {infer} endpoint URL you created on Watsonx.
|
|
|
+<3> The ID of your IBM Cloud project.
|
|
|
+<4> A valid API version parameter. You can find the active version data parameters https://cloud.ibm.com/apidocs/watsonx-ai#active-version-dates[here].
|
|
|
+<5> The maximum number of tokens per document before truncation.
|
|
|
+<6> Whether to return the document text in the results.
|
|
|
+<7> The number of top relevant documents to return.
|
kosabogi