You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/document-intelligence/concept-custom-generative.md
+1-1Lines changed: 1 addition & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -90,7 +90,7 @@ Field extraction custom generative model `2024-07-31-preview` version is only av
90
90
91
91
***Field Description**. Provide more contextual information in description to help clarify the field that needs to be extracted. Examples include location in the document, potential field labels it can be associated with, and ways to differentiate with other terms that could be ambiguous.
92
92
93
-
***Variation**. Custom generative models can generalize across different document templates of the same document type. As a best practice, create a single model for all variations of a document type. Ideally, include a visual template for each type, especially for ones that
93
+
***Variation**. Custom generative models can generalize across different document templates of the same document type. As a best practice, create a single model for all variations of a document type. Ideally, include a visual template for each type, especially for ones that involve distinct formatting or structural elements, to improve the model's accuracy and consistency in generating or processing documents.
|`Loan.RefinanceProgramType`|`selectionGroup`|Loan refinance program type|:unselected: Full Documentation:selected: Interest Rate Reduction<br>:unselected: Streamlined without Appraisal<br>:unselected: Other|
185
-
|`Loan.OtherRefinanceProgram`|`string`|Other loan refinance program type|Cash-out refinance|
186
-
|`Property`|`object`|||
187
-
|`Property.Address`|`address`|Property address|1634 W Glenoaks Blvd<br>Glendale CA 91201 Los Angeles|
188
-
|`Property.NumberOfUnits`|`integer`|Number of units|1|
|`Property.OccupancyStatus`|`selectionGroup`|Property occupancy status|:selected: Primary Residence<br>:unselected: Second Home<br>:unselected: Investment Property|
191
-
|`Property.IsFhaSecondaryResidence`|`boolean`|Checkbox state of '`FHA` Secondary Residence'|:unselected:|
192
-
|`Property.MixedUseProperty`|`selectionGroup`|Is the property a mixed-use property?|:selected: NO:unselected: YES|
193
-
|`Property.ManufacturedHome`|`selectionGroup`|Is the property a manufactured home?|:selected: NO:unselected: YES|
194
-
195
-
196
-
The 1003 URLA key-value pairs and line items extracted are in the `documentResults` section of the JSON output.
197
131
198
132
## Field extraction 1004 Uniform Residential Appraisal Report (URAR)
199
133
The following are the fields extracted from a 1004 URAR form in the JSON output response.
@@ -404,4 +338,4 @@ The mortgage closing disclosure key-value pairs and line items extracted are in
404
338
* Try processing your own forms and documents with the [Document Intelligence Studio](https://formrecognizer.appliedai.azure.com/studio).
405
339
406
340
* Complete a [Document Intelligence quickstart](quickstarts/get-started-sdks-rest-api.md?view=doc-intel-3.0.0&preserve-view=true) and get started creating a document processing app in the development language of your choice.
Copy file name to clipboardExpand all lines: articles/ai-services/openai/concepts/assistants.md
+6-6Lines changed: 6 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -3,11 +3,11 @@ title: Azure OpenAI Service Assistants API concepts
3
3
titleSuffix: Azure OpenAI Service
4
4
description: Learn about the concepts behind the Azure OpenAI Assistants API.
5
5
ms.topic: conceptual
6
-
ms.date: 03/04/2024
6
+
ms.date: 08/21/2024
7
7
ms.service: azure-ai-openai
8
8
manager: nitinme
9
-
author: mrbullwinkle
10
-
ms.author: mbullwin
9
+
author: aahill
10
+
ms.author: aahi
11
11
recommendations: false
12
12
---
13
13
@@ -71,21 +71,21 @@ The Assistants API has support for several parameters that let you customize the
71
71
72
72
## Context window management
73
73
74
-
Assistants automatically truncates text to ensure it stays within the model's maximum context length. You can customize this behavior by specifying the maximum tokens you'd like a run to utilize and/or the maximum number of recent messages you'd like to include in a run.
74
+
Assistants automatically truncate text to ensure it stays within the model's maximum context length. You can customize this behavior by specifying the maximum tokens you'd like a run to utilize and/or the maximum number of recent messages you'd like to include in a run.
75
75
76
76
### Max completion and max prompt tokens
77
77
78
78
To control the token usage in a single Run, set `max_prompt_tokens` and `max_completion_tokens` when you create the Run. These limits apply to the total number of tokens used in all completions throughout the Run's lifecycle.
79
79
80
-
For example, initiating a Run with `max_prompt_tokens` set to 500 and `max_completion_tokens` set to 1000 means the first completion will truncate the thread to 500 tokens and cap the output at 1000 tokens. If only 200 prompt tokens and 300 completion tokens are used in the first completion, the second completion will have available limits of 300 prompt tokens and 700 completion tokens.
80
+
For example, initiating a Run with `max_prompt_tokens` set to 500 and `max_completion_tokens` set to 1000 means the first completion will truncate the thread to 500 tokens and cap the output at 1,000 tokens. If only 200 prompt tokens and 300 completion tokens are used in the first completion, the second completion will have available limits of 300 prompt tokens and 700 completion tokens.
81
81
82
82
If a completion reaches the `max_completion_tokens` limit, the Run will terminate with a status of incomplete, and details will be provided in the `incomplete_details` field of the Run object.
83
83
84
84
When using the File Search tool, we recommend setting the `max_prompt_tokens` to no less than 20,000. For longer conversations or multiple interactions with File Search, consider increasing this limit to 50,000, or ideally, removing the `max_prompt_tokens` limits altogether to get the highest quality results.
85
85
86
86
## Truncation strategy
87
87
88
-
You may also specify a truncation strategy to control how your thread should be rendered into the model's context window. Using a truncation strategy of type `auto` will use OpenAI's default truncation strategy. Using a truncation strategy of type `last_messages` will allow you to specify the number of the most recent messages to include in the context window.
88
+
You can also specify a truncation strategy to control how your thread should be rendered into the model's context window. Using a truncation strategy of type `auto` will use OpenAI's default truncation strategy. Using a truncation strategy of type `last_messages` will allow you to specify the number of the most recent messages to include in the context window.
89
89
90
90
## See also
91
91
* Learn more about Assistants and [File Search](../how-to/file-search.md)
0 commit comments