Skip to content

Azure AI Model Inference API - Embeddings and Chat Completions (#32145) #32165

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Feb 12, 2025
Merged

Azure AI Model Inference API - Embeddings and Chat Completions (#32145) #32165

Show file tree
Hide file tree
Changes from 5 commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
f7fe42a
Azure AI Model Inference API - Embeddings and Chat Completions (#32145)
santiagxf Jan 15, 2025
b5d856b
Merge branch 'main' into release-ai-modelinference-preview/2024-05-01…
santiagxf Jan 15, 2025
18df872
fix: audio reference
santiagxf Jan 15, 2025
6690b3a
fix: reasoning tokens
santiagxf Jan 15, 2025
dfaac6f
Merge branch 'main' into release-ai-modelinference-preview/2024-05-01…
santiagxf Jan 15, 2025
5b3aa7d
fix: audio input descriptions and types
santiagxf Jan 17, 2025
91fdf94
Merge branch 'release-ai-modelinference-preview/2024-05-01-preview' o…
santiagxf Jan 17, 2025
fb528f0
Merge branch 'main' of https://github.com/Azure/azure-rest-api-specs …
santiagxf Jan 17, 2025
547fb14
fix: review suggestion
santiagxf Jan 23, 2025
55f0989
fix: comments
santiagxf Feb 10, 2025
3ef850f
restore protected
santiagxf Feb 11, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
62 changes: 34 additions & 28 deletions cSpell.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,6 +11,7 @@
"partiallycompleted",
"servicenetworking",
"subchannel",
"ubinary",
"umls"
],
"allowCompoundWords": true,
Expand Down Expand Up @@ -170,12 +171,18 @@
]
},
{
"filename": "**/specification/billing/**/*.json",
"words": [
"mosp",
"resellee",
"cnpj"
]
"filename": "**/specification/billing/**/*.json",
"words": [
"mosp",
"resellee",
"cnpj"
]
},
{
"filename": "**/specification/ai/data-plane/ModelInference/**/*",
"words": [
"ubinary"
]
},
{
"filename": "**/specification/compute/resource-manager/Microsoft.ContainerService/preview/2015-11-01-preview/containerService.json",
Expand Down Expand Up @@ -340,32 +347,32 @@
"freemium"
]
},
{
{
"filename": "**/specification/sql/resource-manager/Microsoft.Sql/preview/**/ManagedInstances.json",
"words": [
"freemium"
]
},
{
{
"filename": "**/specification/sql/resource-manager/Microsoft.Sql/preview/**/ServerTrustCertificates.json",
"words": [
"freemium"
]
},
{
{
"filename": "**/specification/sql/resource-manager/Microsoft.Sql/preview/**/ManagedInstanceDtcs.json",
"words": [
"msdtcdns",
"msdtc's"
]
},
{
{
"filename": "**/specification/sql/resource-manager/Microsoft.Sql/preview/**/TimeZones.json",
"words": [
"freemium"
]
},
{
{
"filename": "**/specification/sql/resource-manager/Microsoft.Sql/preview/**/ElasticPools.json",
"words": [
"PRMS"
Expand Down Expand Up @@ -1695,19 +1702,19 @@
"filename": "**/specification/ai/data-plane/HealthInsights/stable/**/openapi.json",
"words": [
"Acrad",
"acrad",
"BIRADS",
"mednax",
"frax",
"extracolonic",
"ascvd",
"tyrer",
"cusick",
"agatston",
"ceus",
"HNPCC",
"kellgren",
"tonnis"
"acrad",
"BIRADS",
"mednax",
"frax",
"extracolonic",
"ascvd",
"tyrer",
"cusick",
"agatston",
"ceus",
"HNPCC",
"kellgren",
"tonnis"
]
},
{
Expand Down Expand Up @@ -1783,7 +1790,7 @@
"words": [
"symboliclink",
"hardlink"
]
]
},
{
"filename": "**/specification/cost-management/resource-manager/Microsoft.CostManagement/stable/2023-09-01/costmanagement.pricesheets.json",
Expand All @@ -1795,10 +1802,10 @@
"filename": "**/specification/cost-management/resource-manager/Microsoft.CostManagement/stable/2023-11-01/costmanagement.pricesheets.json",
"words": [
"Unitof"
]
]
},
{
"filename": "**/specification/azurestackhci/resource-manager/Microsoft.AzureStackHCI/StackHCIVM/**/*.json",
"filename": "**/specification/azurestackhci/resource-manager/Microsoft.AzureStackHCI/StackHCIVM/**/*.json",
"words": [
"SEVSNP"
]
Expand Down Expand Up @@ -1848,5 +1855,4 @@
"ignoreWords": [
"trafficcontrollerspec"
]

}
5 changes: 5 additions & 0 deletions specification/ai/ModelInference/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
title: ModelInference
clear-output-folder: false
guessResourceKey: true
isAzureSpec: true
namespace: azure.ai.inference
98 changes: 98 additions & 0 deletions ...n/ai/ModelInference/examples/2024-05-01-preview/GetChatCompletions_AudioModality_Gen.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,98 @@
{
"title": "Audio modality chat completion",
"operationId": "GetChatCompletions",
"parameters": {
"api-version": "2024-05-01-preview",
"extra-parameters": "error",
"body": {
"modalities": [
"text",
"audio"
],
"messages": [
{
"role": "system",
"content": "You are a helpful assistant"
},
{
"role": "user",
"content": [
{
"type": "audio_input",
"audio_input": {
"data": "<base64 encoded audio data>",
"mime_type": "audio/wav"
}
}
]
},
{
"role": "assistant",
"content": null,
"audio": {
"id": "abcdef1234"
}
},
{
"role": "user",
"content": [
{
"type": "audio_input",
"audio_input": {
"data": "<base64 encoded audio data>",
"mime_type": "audio/wav"
}
}
]
}
],
"frequency_penalty": 0,
"presence_penalty": 0,
"temperature": 0,
"top_p": 0,
"seed": 21,
"model": "my-model-name"
}
},
"responses": {
"200": {
"body": {
"id": "kgousajxgzyhugvqekuswuqbk",
"object": "chat.completion",
"created": 1696522361,
"model": "my-model-name",
"usage": {
"completion_tokens": 19,
"prompt_tokens": 28,
"total_tokens": 16,
"completion_tokens_details": {
"audio_tokens": 5,
"total_tokens": 5
},
"prompt_tokens_details": {
"audio_tokens": 10,
"cached_tokens": 0
}
},
"choices": [
{
"index": 0,
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": null,
"tool_calls": null,
"audio": {
"id": "abcdef1234",
"mime_type": "audio/wav",
"data": "<base64 encoded audio data>",
"expires_at": 1896522361,
"transcript": "This is a sample transcript"
}
}
}
]
}
}
}
}
89 changes: 89 additions & 0 deletions ...tion/ai/ModelInference/examples/2024-05-01-preview/GetChatCompletions_MaximumSet_Gen.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,89 @@
{
"title": "maximum set chat completion",
"operationId": "GetChatCompletions",
"parameters": {
"api-version": "2024-05-01-preview",
"extra-parameters": "error",
"body": {
"modalities": [
"text"
],
"messages": [
{
"role": "system",
"content": "You are a helpful assistant"
},
{
"role": "user",
"content": "Explain Riemann's conjecture"
},
{
"role": "assistant",
"content": "The Riemann Conjecture is a deep mathematical conjecture around prime numbers and how they can be predicted. It was first published in Riemann's groundbreaking 1859 paper. The conjecture states that the Riemann zeta function has its zeros only at the negative even integers and complex numbers with real part 1/21. Many consider it to be the most important unsolved problem in pure mathematics. The Riemann hypothesis is a way to predict the probability that numbers in a certain range are prime that was also devised by German mathematician Bernhard Riemann in 18594."
},
{
"role": "user",
"content": "Ist it proved?"
}
],
"frequency_penalty": 0,
"stream": true,
"presence_penalty": 0,
"temperature": 0,
"top_p": 0,
"max_tokens": 255,
"response_format": {
"type": "text"
},
"stop": [
"<|endoftext|>"
],
"tools": [
{
"type": "function",
"function": {
"name": "my-function-name",
"description": "A function useful to know if a theroem is proved or not"
}
}
],
"seed": 21,
"model": "my-model-name"
}
},
"responses": {
"200": {
"body": {
"id": "kgousajxgzyhugvqekuswuqbk",
"object": "chat.completion",
"created": 18,
"model": "my-model-name",
"usage": {
"completion_tokens": 19,
"prompt_tokens": 28,
"total_tokens": 16
},
"choices": [
{
"index": 7,
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": null,
"tool_calls": [
{
"id": "yrobmilsrugmbwukmzo",
"type": "function",
"function": {
"name": "my-function-name",
"arguments": "{ \"arg1\": \"value1\", \"arg2\": \"value2\" }"
}
}
]
}
}
]
}
}
}
}
40 changes: 40 additions & 0 deletions ...tion/ai/ModelInference/examples/2024-05-01-preview/GetChatCompletions_MinimumSet_Gen.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,40 @@
{
"title": "minimum set chat completion",
"operationId": "GetChatCompletions",
"parameters": {
"api-version": "2024-05-01-preview",
"body": {
"messages": [
{
"role": "user",
"content": "Explain Riemann's conjecture"
}
]
}
},
"responses": {
"200": {
"body": {
"id": "kgousajxgzyhugvqekuswuqbk",
"object": "chat.completion",
"created": 1234567890,
"model": "my-model-name",
"usage": {
"prompt_tokens": 205,
"completion_tokens": 5,
"total_tokens": 210
},
"choices": [
{
"index": 0,
"finish_reason": "stop",
"message": {
"role": "assistant",
"content": "The Riemann Conjecture is a deep mathematical conjecture around prime numbers and how they can be predicted. It was first published in Riemann's groundbreaking 1859 paper. The conjecture states that the Riemann zeta function has its zeros only at the negative even integers and complex numbers with real part 1/21. Many consider it to be the most important unsolved problem in pure mathematics. The Riemann hypothesis is a way to predict the probability that numbers in a certain range are prime that was also devised by German mathematician Bernhard Riemann in 18594"
}
}
]
}
}
}
}
Loading
Loading