-
Notifications
You must be signed in to change notification settings - Fork 10
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* Create generate_rest.yaml Propose generate rest api endpoints Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> * Update generate_rest.yaml Signed-off-by: Gavrish Prabhu <[email protected]> --------- Signed-off-by: Gavrish Prabhu <[email protected]>
- Loading branch information
Showing
1 changed file
with
255 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,255 @@ | ||
| openapi: 3.1.0 | ||
| info: | ||
| title: Open Inference API for text generation | ||
| description: Open Inference API for text generation | ||
| version: 1.0.0 | ||
| components: | ||
| schemas: | ||
| Details: | ||
| type: object | ||
| required: | ||
| - finish_reason | ||
| - logprobs | ||
| additionalProperties: {} | ||
| properties: | ||
| finish_reason: | ||
| $ref: '#/components/schemas/Finish_Reason' | ||
| logprobs: | ||
| $ref: '#/components/schemas/Logprobs' | ||
| Finish_Reason: | ||
| type: string | ||
| enum: | ||
| - length | ||
| - eos_token | ||
| - stop_sequence | ||
| description: The reason the model stopped generating tokens. `length` if number of generated tokens == `max_tokens`. `eos_token` if the model generated its end of sequence token and `stop_sequence` if the model generated a text included in `stop` array | ||
| GenerateErrorResponse: | ||
| type: object | ||
| required: | ||
| - error | ||
| properties: | ||
| error: | ||
| type: string | ||
| GenerateParameters: | ||
| type: object | ||
| additionalProperties: {} | ||
| properties: | ||
| temperature: | ||
| type: number | ||
| format: float | ||
| default: 1 | ||
| minimum: 0 | ||
| description: What sampling temperature to use, higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. | ||
| top_p: | ||
| type: number | ||
| format: float | ||
| maximum: 1 | ||
| minimum: 0 | ||
| description: An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. | ||
| max_tokens: | ||
| type: integer | ||
| format: int32 | ||
| default: 20 | ||
| minimum: 1 | ||
| description: The maximum number of tokens to generate in the completion. | ||
| stop: | ||
| type: array | ||
| items: | ||
| type: string | ||
| description: Sequences where the API will stop generating further tokens. | ||
| details: | ||
| type: boolean | ||
| description: Flag to request for detailed response body that would include finish_reason and logprobs. | ||
| GenerateRequest: | ||
| type: object | ||
| required: | ||
| - text_input | ||
| properties: | ||
| text_input: | ||
| type: string | ||
| parameters: | ||
| allOf: | ||
| - $ref: '#/components/schemas/GenerateParameters' | ||
| GenerateResponse: | ||
| type: object | ||
| required: | ||
| - text_output | ||
| - model_name | ||
| properties: | ||
| text_output: | ||
| type: string | ||
| model_name: | ||
| type: string | ||
| model_version: | ||
| type: string | ||
| details: | ||
| $ref: '#/components/schemas/Details' | ||
| GenerateStreamResponse: | ||
| type: object | ||
| required: | ||
| - text_output | ||
| - model_name | ||
| properties: | ||
| text_output: | ||
| type: string | ||
| model_name: | ||
| type: string | ||
| model_version: | ||
| type: string | ||
| details: | ||
| $ref: '#/components/schemas/StreamDetails' | ||
| Logprobs: | ||
| type: array | ||
| items: | ||
| $ref: '#/components/schemas/Token' | ||
| description: Log probability information for the tokens. | ||
| StreamDetails: | ||
| type: object | ||
| required: | ||
| - finish_reason | ||
| - token | ||
| additionalProperties: {} | ||
| properties: | ||
| finish_reason: | ||
| $ref: '#/components/schemas/Finish_Reason' | ||
| token: | ||
| $ref: '#/components/schemas/Token' | ||
| Token: | ||
| type: object | ||
| required: | ||
| - id | ||
| - text | ||
| - logprob | ||
| - special | ||
| properties: | ||
| id: | ||
| type: integer | ||
| format: int32 | ||
| minimum: 0 | ||
| description: Id of the token. | ||
| logprob: | ||
| type: number | ||
| format: float | ||
| description: The log probability of this token. | ||
| special: | ||
| type: boolean | ||
| description: Describes if the token is a special token. Can be used to ignore tokens when concatenating | ||
| text: | ||
| type: string | ||
| description: The token text value. | ||
| paths: | ||
| /v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/generate: | ||
| post: | ||
| parameters: | ||
| - name: MODEL_NAME | ||
| required: true | ||
| in: path | ||
| schema: | ||
| type: string | ||
| - name: MODEL_VERSION | ||
| required: true | ||
| in: path | ||
| schema: | ||
| type: string | ||
| requestBody: | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateRequest' | ||
| responses: | ||
| '200': | ||
| description: generated text | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateResponse' | ||
| '422': | ||
| description: Input validation error | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateErrorResponse' | ||
| example: | ||
| error: Input validation error | ||
| '424': | ||
| description: Generation Error | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateErrorResponse' | ||
| example: | ||
| error: Request failed during generation | ||
| '429': | ||
| description: Model is overloaded | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateErrorResponse' | ||
| example: | ||
| error: Model is overloaded | ||
| '500': | ||
| description: Incomplete generation | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateErrorResponse' | ||
| example: | ||
| error: Incomplete generation | ||
|
|
||
| /v2/models/${MODEL_NAME}/versions/${MODEL_VERSION}/generate_stream: | ||
| post: | ||
| parameters: | ||
| - name: MODEL_NAME | ||
| required: true | ||
| in: path | ||
| schema: | ||
| type: string | ||
| - name: MODEL_VERSION | ||
| required: true | ||
| in: path | ||
| schema: | ||
| type: string | ||
| requestBody: | ||
| content: | ||
| application/json: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateRequest' | ||
| responses: | ||
| '200': | ||
| description: generated text stream | ||
| content: | ||
| text/event-stream: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateStreamResponse' | ||
| '422': | ||
| description: Input validation error | ||
| content: | ||
| text/event-stream: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateErrorResponse' | ||
| example: | ||
| error: Input validation error | ||
| '424': | ||
| description: Generation Error | ||
| content: | ||
| text/event-stream: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateErrorResponse' | ||
| example: | ||
| error: Request failed during generation | ||
| '429': | ||
| description: Model is overloaded | ||
| content: | ||
| text/event-stream: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateErrorResponse' | ||
| example: | ||
| error: Model is overloaded | ||
| '500': | ||
| description: Incomplete generation | ||
| content: | ||
| text/event-stream: | ||
| schema: | ||
| $ref: '#/components/schemas/GenerateErrorResponse' | ||
| example: | ||
| error: Incomplete generation |