Skip to content

Commit 12d56cc

Browse files
santiagxfsantiagxf
authored
Update reference-model-inference-embeddings.md
1 parent c33f270 commit 12d56cc

File tree

1 file changed

+24
-8
lines changed

1 file changed

+24
-8
lines changed

‎articles/machine-learning/reference-model-inference-embeddings.md

Lines changed: 24 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -29,6 +29,14 @@ POST /embeddings?api-version=2024-04-01-preview
2929
| ------------- | ----- | -------- | ------ | -------------------------------------------------------------------------- |
3030
| `api-version` | query | True | string | The version of the API in the format "YYYY-MM-DD" or "YYYY-MM-DD-preview". |
3131

32+
## Request Header
33+
34+
35+
| Name | Required | Type | Description |
36+
| --- | --- | --- | --- |
37+
| extra-parameters | | string | The behavior of the API when extra parameters are indicated in the payload. Using `pass-through` makes the API to pass the parameter to the underlying model. Use this value when you want to pass parameters that you know the underlying model can support. Using `ignore` makes the API to drop any unsupported parameter. Use this value when you need to use the same payload across different models, but one of the extra parameters may make a model to error out if not supported. Using `error` makes the API to reject any extra parameter in the payload. Only parameters specified in this API can be indicated, or a 400 error is returned. |
38+
| azureml-model-deployment | | string | Name of the deployment you want to route the request to. Supported for endpoints that support multiple deployments. |
39+
3240
## Request Body
3341

3442
| Name | Required | Type | Description |
@@ -125,22 +133,24 @@ Status code: 200
125133
| Name | Description |
126134
| ------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
127135
| [ContentFilterError](#contentfiltererror) | The API call fails when the prompt triggers a content filter as configured. Modify the prompt and try again. |
128-
| [CreateEmbeddingRequest](#createembeddingrequest) | Request for creating embeddings |
129-
| [CreateEmbeddingResponse](#createembeddingresponse) | Response from an embeddings request |
130-
| [Detail](#detail) | Details of the errors |
136+
| [CreateEmbeddingRequest](#createembeddingrequest) | Request for creating embeddings. |
137+
| [CreateEmbeddingResponse](#createembeddingresponse) | Response from an embeddings request. |
138+
| [Detail](#detail) | Details of the errors. |
131139
| [Embedding](#embedding) | Represents the embedding object generated. |
132140
| [EmbeddingEncodingFormat](#embeddingencodingformat) | The format to return the embeddings in. Either base64, float, int8, uint8, binary, or ubinary. Returns a 422 error if the model doesn't support the value or parameter. |
133141
| [EmbeddingInputType](#embeddinginputtype) | The type of the input. Either `text`, `query`, or `document`. Returns a 422 error if the model doesn't support the value or parameter. |
134142
| [EmbeddingObject](#embeddingobject) | The object type, which is always "embedding". |
135143
| [ListObject](#listobject) | The object type, which is always "list". |
136-
| [NotFoundError](#notfounderror) | |
137-
| [TooManyRequestsError](#toomanyrequestserror) | |
138-
| [UnauthorizedError](#unauthorizederror) | |
139-
| [UnprocessableContentError](#unprocessablecontenterror) | |
144+
| [NotFoundError](#notfounderror) | The route is not valid for the deployed model. |
145+
| [TooManyRequestsError](#toomanyrequestserror) | You have hit your assigned rate limit and your requests need to be paced. |
146+
| [UnauthorizedError](#unauthorizederror) | Authentication is missing or invalid. |
147+
| [UnprocessableContentError](#unprocessablecontenterror) | The request contains unprocessable content. The error is returned when the payload indicated is valid according to this specification. However, some of the instructions indicated in the payload are not supported by the underlying model. Use the `details` section to understand the offending parameter. |
140148
| [Usage](#usage) | The usage information for the request. |
141149

142150
### ContentFilterError
143151

152+
The API call fails when the prompt triggers a content filter as configured. Modify the prompt and try again.
153+
144154
| Name | Type | Description |
145155
| --- | --- | --- |
146156
| code | string | The error code. |
@@ -151,6 +161,8 @@ Status code: 200
151161

152162
### CreateEmbeddingRequest
153163

164+
Request for creating embeddings.
165+
154166
| Name | Required | Type | Description |
155167
| --------------- | -------- | --------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
156168
| input | True | string[] | Input text to embed, encoded as a string or array of tokens. To embed multiple inputs in a single request, pass an array of strings or array of token arrays. |
@@ -160,6 +172,8 @@ Status code: 200
160172

161173
### CreateEmbeddingResponse
162174

175+
Response from an embeddings request.
176+
163177
| Name | Type | Description |
164178
| --- | --- | --- |
165179
| data | [Embedding](#embedding)\[\] | The list of embeddings generated by the model. |
@@ -169,6 +183,7 @@ Status code: 200
169183

170184
### Detail
171185

186+
Details for the [UnprocessableContentError](#unprocessablecontenterror) error.
172187

173188
| Name | Type | Description |
174189
| --- | --- | --- |
@@ -255,6 +270,7 @@ The object type, which is always "list".
255270

256271
### UnprocessableContentError
257272

273+
The request contains unprocessable content. The error is returned when the payload indicated is valid according to this specification. However, some of the instructions indicated in the payload are not supported by the underlying model. Use the `details` section to understand the offending parameter.
258274

259275
| Name | Type | Description |
260276
| --- | --- | --- |
@@ -272,4 +288,4 @@ The usage information for the request.
272288
| Name | Type | Description |
273289
| -------------- | ------- | ----------------------------------------------- |
274290
| prompt\_tokens | integer | The number of tokens used by the prompt. |
275-
| total\_tokens | integer | The total number of tokens used by the request. |
291+
| total\_tokens | integer | The total number of tokens used by the request. |

0 commit comments

Comments
 (0)