You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Specifies the maximum number of tokens per input document before truncation.
105
-
106
-
`return_documents`:::
107
-
(Optional, boolean)
108
-
Specify whether to return doc text within the results.
109
-
110
-
`top_n`:::
111
-
(Optional, integer)
112
-
The number of most relevant documents to return. Defaults to the number of input documents.
113
-
=====
114
-
115
94
116
95
[discrete]
117
96
[[inference-example-watsonx-ai]]
@@ -139,35 +118,4 @@ PUT _inference/text_embedding/watsonx-embeddings
139
118
You can find on the https://cloud.ibm.com/iam/apikeys[API keys page of your account].
140
119
<2> The {infer} endpoint URL you created on Watsonx.
141
120
<3> The ID of your IBM Cloud project.
142
-
<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].
143
-
144
-
The following example shows how to create an {infer} endpoint called `watsonx-rerank` to perform a `rerank` task type.
You can find on the https://cloud.ibm.com/iam/apikeys[API keys page of your account].
168
-
<2> The {infer} endpoint URL you created on Watsonx.
169
-
<3> The ID of your IBM Cloud project.
170
-
<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].
171
-
<5> The maximum number of tokens per document before truncation.
172
-
<6> Whether to return the document text in the results.
173
-
<7> The number of top relevant documents to return.
121
+
<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].
0 commit comments