@@ -44,71 +44,121 @@ items:
44
44
href : concepts/model-benchmarks.md
45
45
- name : How to use model benchmarking
46
46
href : how-to/benchmark-model-in-catalog.md
47
- - name : Featured models
47
+ - name : Model deployment in Azure AI Foundry
48
48
items :
49
- - name : AI21 Jamba models
50
- href : how-to/deploy-models-jamba .md
51
- - name : Cohere models
49
+ - name : Deploying models in Azure AI Foundry
50
+ href : concepts/deployments-overview .md
51
+ - name : Serverless API
52
52
items :
53
- - name : Cohere Command models
54
- href : how-to/deploy-models-cohere-command.md
55
- - name : Cohere Embed models
56
- href : how-to/deploy-models-cohere-embed.md
57
- - name : Cohere Rerank models
58
- href : how-to/deploy-models-cohere-rerank.md
59
- - name : DeepSeek-R1 reasoning models
60
- href : how-to/deploy-models-deepseek.md
61
- - name : Gretel Navigator model
62
- href : how-to/deploy-models-gretel-navigator.md
63
- - name : Healthcare AI models
53
+ - name : Deploy models as serverless API
54
+ href : how-to/deploy-models-serverless.md
55
+ - name : Consume serverless API models from a different project or hub
56
+ href : how-to/deploy-models-serverless-connect.md
57
+ - name : Model and region availability for Serverless API deployments
58
+ href : how-to/deploy-models-serverless-availability.md
59
+ - name : Managed compute
64
60
items :
65
- - name : Foundational AI models for healthcare
66
- href : how-to/healthcare-ai/healthcare-ai-models.md
67
- - name : MedImageInsight - embedding model
68
- href : how-to/healthcare-ai/deploy-medimageinsight.md
69
- - name : CXRReportGen - text generation model
70
- href : how-to/healthcare-ai/deploy-cxrreportgen.md
71
- - name : MedImageParse - prompted segmentation model
72
- href : how-to/healthcare-ai/deploy-medimageparse.md
73
- - name : JAIS model
74
- href : how-to/deploy-models-jais.md
75
- - name : Meta Llama models
61
+ - name : Deploy models via managed compute
62
+ href : how-to/deploy-models-managed.md
63
+ - name : Azure AI model inference
76
64
items :
77
- - name : Meta Llama family models
78
- href : how-to/deploy-models-llama.md
79
- - name : Fine-tune Meta Llama family models
80
- href : how-to/fine-tune-model-llama.md
81
- - name : Microsoft Phi family models
65
+ - name : What is Azure AI model inference?
66
+ href : ../ai-foundry/model-inference/overview.md?context=/azure/ai-studio/context/context
67
+ - name : Add and configure models
68
+ href : ../ai-foundry/model-inference/how-to/create-model-deployments.md?context=/azure/ai-studio/context/context
69
+ - name : Supported programming languages and SDKs
70
+ href : ../ai-foundry/model-inference/supported-languages.md?context=/azure/ai-studio/context/context
71
+ - name : Use the Azure AI model inference endpoint
72
+ href : ../ai-foundry/model-inference/how-to/inference.md?context=/azure/ai-studio/context/context
73
+ - name : Azure AI model inference quotas and limits
74
+ href : ../ai-foundry/model-inference/quotas-limits.md?context=/azure/ai-studio/context/context
75
+ - name : Azure OpenAI Service
76
+ items :
77
+ - name : Deploy Azure OpenAI models
78
+ href : how-to/deploy-models-openai.md
79
+ - name : Azure OpenAI Service quotas and limits
80
+ href : ../ai-services/openai/quotas-limits.md?context=/azure/ai-studio/context/context
81
+ - name : Troubleshoot deployments and monitoring
82
+ href : how-to/troubleshoot-deploy-and-monitor.md
83
+ - name : Work with models from the model catalog
84
+ items :
85
+ - name : Featured models supported in Azure AI model inference
86
+ href : ../ai-foundry/model-inference/concepts/models.md?context=/azure/ai-studio/context/context
87
+ - name : Work with embedding models
82
88
items :
83
- - name : Phi-3 chat models
84
- href : how-to/deploy-models-phi-3.md
85
- - name : Phi-3 chat model with vision
86
- href : how-to/deploy-models-phi-3-vision.md
87
- - name : Phi-3.5 chat model with vision
88
- href : how-to/deploy-models-phi-3-5-vision.md
89
- - name : Phi-4 chat models
90
- href : how-to/deploy-models-phi-4.md
91
- - name : Fine-tune Phi-3 chat models
92
- href : how-to/fine-tune-phi-3.md
93
- - name : Mistral family models
89
+ - name : Work with text embedding models
90
+ href : ../ai-foundry/model-inference/how-to/use-embeddings.md?context=/azure/ai-studio/context/context
91
+ - name : Work with image embedding models
92
+ href : ../ai-foundry/model-inference/how-to/use-image-embeddings.md?context=/azure/ai-studio/context/context
93
+ - name : Work with chat models
94
94
items :
95
- - name : Mistral premium models
96
- href : how-to/deploy-models-mistral.md
97
- - name : Codestral model
98
- href : how-to/deploy-models-mistral-codestral.md
99
- - name : Mistral Nemo model
100
- href : how-to/deploy-models-mistral-nemo.md
101
- - name : Mistral-7B and Mixtral models
102
- href : how-to/deploy-models-mistral-open.md
103
- displayName : maas
104
- - name : NTTDATA tsuzumi model
95
+ - name : Work with chat completion models
96
+ href : ../ai-foundry/model-inference/how-to/use-chat-completions.md?context=/azure/ai-studio/context/context
97
+ - name : Work with featured models
105
98
items :
106
- - name : NTTDATA tsuzumi model
107
- href : how-to/deploy-models-tsuzumi.md
108
- - name : Fine-tune tsuzumi model
109
- href : how-to/fine-tune-models-tsuzumi.md
110
- - name : TimeGEN-1 model
111
- href : how-to/deploy-models-timegen-1.md
99
+ - name : AI21 Jamba models
100
+ href : how-to/deploy-models-jamba.md
101
+ - name : Cohere models
102
+ items :
103
+ - name : Cohere Command models
104
+ href : how-to/deploy-models-cohere-command.md
105
+ - name : Cohere Embed models
106
+ href : how-to/deploy-models-cohere-embed.md
107
+ - name : Cohere Rerank models
108
+ href : how-to/deploy-models-cohere-rerank.md
109
+ - name : DeepSeek-R1 reasoning models
110
+ href : how-to/deploy-models-deepseek.md
111
+ - name : Gretel Navigator model
112
+ href : how-to/deploy-models-gretel-navigator.md
113
+ - name : Healthcare AI models
114
+ items :
115
+ - name : Foundational AI models for healthcare
116
+ href : how-to/healthcare-ai/healthcare-ai-models.md
117
+ - name : MedImageInsight - embedding model
118
+ href : how-to/healthcare-ai/deploy-medimageinsight.md
119
+ - name : CXRReportGen - text generation model
120
+ href : how-to/healthcare-ai/deploy-cxrreportgen.md
121
+ - name : MedImageParse - prompted segmentation model
122
+ href : how-to/healthcare-ai/deploy-medimageparse.md
123
+ - name : JAIS model
124
+ href : how-to/deploy-models-jais.md
125
+ - name : Meta Llama models
126
+ items :
127
+ - name : Meta Llama family models
128
+ href : how-to/deploy-models-llama.md
129
+ - name : Fine-tune Meta Llama family models
130
+ href : how-to/fine-tune-model-llama.md
131
+ - name : Microsoft Phi family models
132
+ items :
133
+ - name : Phi-3 chat models
134
+ href : how-to/deploy-models-phi-3.md
135
+ - name : Phi-3 chat model with vision
136
+ href : how-to/deploy-models-phi-3-vision.md
137
+ - name : Phi-3.5 chat model with vision
138
+ href : how-to/deploy-models-phi-3-5-vision.md
139
+ - name : Phi-4 chat models
140
+ href : how-to/deploy-models-phi-4.md
141
+ - name : Fine-tune Phi-3 chat models
142
+ href : how-to/fine-tune-phi-3.md
143
+ - name : Mistral family models
144
+ items :
145
+ - name : Mistral premium models
146
+ href : how-to/deploy-models-mistral.md
147
+ - name : Codestral model
148
+ href : how-to/deploy-models-mistral-codestral.md
149
+ - name : Mistral Nemo model
150
+ href : how-to/deploy-models-mistral-nemo.md
151
+ - name : Mistral-7B and Mixtral models
152
+ href : how-to/deploy-models-mistral-open.md
153
+ displayName : maas
154
+ - name : NTTDATA tsuzumi model
155
+ items :
156
+ - name : NTTDATA tsuzumi model
157
+ href : how-to/deploy-models-tsuzumi.md
158
+ - name : Fine-tune tsuzumi model
159
+ href : how-to/fine-tune-models-tsuzumi.md
160
+ - name : TimeGEN-1 model
161
+ href : how-to/deploy-models-timegen-1.md
112
162
- name : Azure OpenAI and AI services
113
163
items :
114
164
- name : Use Azure OpenAI Service in Azure AI Foundry portal
@@ -316,33 +366,6 @@ items:
316
366
displayName : code,sdk
317
367
- name : Develop with Semantic Kernel
318
368
href : how-to/develop/semantic-kernel.md
319
- - name : Model inference
320
- items :
321
- - name : What is Azure AI model inference?
322
- href : ../ai-foundry/model-inference/overview.md?context=/azure/ai-studio/context/context
323
- - name : Upgrade from GitHub Models
324
- href : ../ai-foundry/model-inference/how-to/quickstart-github-models.md?context=/azure/ai-studio/context/context
325
- - name : Add and configure models
326
- href : ../ai-foundry/model-inference/how-to/create-model-deployments.md?context=/azure/ai-studio/context/context
327
- - name : Use the inference endpoint
328
- href : ../ai-foundry/model-inference/concepts/endpoints.md?context=/azure/ai-studio/context/context
329
- - name : Deployments
330
- items :
331
- - name : Deploying models in Azure AI Foundry
332
- href : concepts/deployments-overview.md
333
- - name : Deploy models as serverless API
334
- href : how-to/deploy-models-serverless.md
335
- - name : Deploy models via managed compute
336
- href : how-to/deploy-models-managed.md
337
- - name : Consume serverless API models from a different project or hub
338
- href : how-to/deploy-models-serverless-connect.md
339
- displayName : maas, paygo, models-as-a-service
340
- - name : Model and region availability for Serverless API deployments
341
- href : how-to/deploy-models-serverless-availability.md
342
- - name : Quotas and limits
343
- href : ai-services/concepts/quotas-limits.md
344
- - name : Troubleshoot deployments and monitoring
345
- href : how-to/troubleshoot-deploy-and-monitor.md
346
369
- name : Optimizations
347
370
items :
348
371
- name : Prompt engineering
0 commit comments