mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-12 21:58:38 +00:00
featu: support passing "extra body" throught to providers
# What does this PR do? Allows passing through extra_body parameters to inference providers. closes #2720 ## Test Plan CI and added new test
This commit is contained in:
parent
80d58ab519
commit
10c7e67fca
35 changed files with 1893 additions and 200 deletions
23
docs/static/llama-stack-spec.html
vendored
23
docs/static/llama-stack-spec.html
vendored
|
@ -153,7 +153,7 @@
|
|||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionRequest"
|
||||
"$ref": "#/components/schemas/OpenAIChatCompletionRequestWithExtraBody"
|
||||
}
|
||||
}
|
||||
},
|
||||
|
@ -243,7 +243,7 @@
|
|||
"content": {
|
||||
"application/json": {
|
||||
"schema": {
|
||||
"$ref": "#/components/schemas/OpenAICompletionRequest"
|
||||
"$ref": "#/components/schemas/OpenAICompletionRequestWithExtraBody"
|
||||
}
|
||||
}
|
||||
},
|
||||
|
@ -5018,7 +5018,7 @@
|
|||
"title": "OpenAIResponseFormatText",
|
||||
"description": "Text response format for OpenAI-compatible chat completion requests."
|
||||
},
|
||||
"OpenAIChatCompletionRequest": {
|
||||
"OpenAIChatCompletionRequestWithExtraBody": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"model": {
|
||||
|
@ -5265,7 +5265,7 @@
|
|||
"model",
|
||||
"messages"
|
||||
],
|
||||
"title": "OpenAIChatCompletionRequest",
|
||||
"title": "OpenAIChatCompletionRequestWithExtraBody",
|
||||
"description": "Request parameters for OpenAI-compatible chat completion endpoint."
|
||||
},
|
||||
"OpenAIChatCompletion": {
|
||||
|
@ -5462,7 +5462,7 @@
|
|||
],
|
||||
"title": "OpenAICompletionWithInputMessages"
|
||||
},
|
||||
"OpenAICompletionRequest": {
|
||||
"OpenAICompletionRequestWithExtraBody": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"model": {
|
||||
|
@ -5593,17 +5593,6 @@
|
|||
"type": "string",
|
||||
"description": "(Optional) The user to use."
|
||||
},
|
||||
"guided_choice": {
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
},
|
||||
"description": "(Optional) vLLM-specific parameter for guided generation with a list of choices."
|
||||
},
|
||||
"prompt_logprobs": {
|
||||
"type": "integer",
|
||||
"description": "(Optional) vLLM-specific parameter for number of log probabilities to return for prompt tokens."
|
||||
},
|
||||
"suffix": {
|
||||
"type": "string",
|
||||
"description": "(Optional) The suffix that should be appended to the completion."
|
||||
|
@ -5614,7 +5603,7 @@
|
|||
"model",
|
||||
"prompt"
|
||||
],
|
||||
"title": "OpenAICompletionRequest",
|
||||
"title": "OpenAICompletionRequestWithExtraBody",
|
||||
"description": "Request parameters for OpenAI-compatible completion endpoint."
|
||||
},
|
||||
"OpenAICompletion": {
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue