Skip to content

Commit 436fdc9

Browse files
committed
condense section to table
1 parent 0bd0ed0 commit 436fdc9

File tree

1 file changed

+11
-11
lines changed

1 file changed

+11
-11
lines changed

articles/ai-services/openai/concepts/content-filter.md

Lines changed: 11 additions & 11 deletions
Original file line numberDiff line numberDiff line change
@@ -189,8 +189,8 @@ The table below outlines the various ways content filtering can appear:
189189

190190
### Scenario: You make a streaming completions call; no output content is classified at a filtered category and severity level
191191

192-
**HTTP Response Code** | **Response behavior**
193-
|------------|------------------------|----------------------|
192+
|**HTTP Response Code** | **Response behavior**|
193+
|------------|------------------------|
194194
|200|In this case, the call will stream back with the full generation and `finish_reason` will be either 'length' or 'stop' for each generated response.|
195195

196196
**Example request payload:**
@@ -224,8 +224,8 @@ The table below outlines the various ways content filtering can appear:
224224

225225
### Scenario: You make a streaming completions call asking for multiple completions and at least a portion of the output content is filtered
226226

227-
**HTTP Response Code** | **Response behavior**
228-
|------------|------------------------|----------------------|
227+
|**HTTP Response Code** | **Response behavior**|
228+
|------------|------------------------|
229229
| 200 | For a given generation index, the last chunk of the generation includes a non-null `finish_reason` value. The value is `content_filter` when the generation was filtered.|
230230

231231
**Example request payload:**
@@ -311,14 +311,14 @@ When annotations are enabled as shown in the code snippet below, the following i
311311

312312
Optional models can be enabled in annotate (returns information when content was flagged, but not filtered) or filter mode (returns information when content was flagged and filtered).
313313

314-
When annotations are enabled as shown in the code snippet below, the following information is returned by the API for optional models: jailbreak, indirect attacks, protected material text and protected material code:
315-
- category (jailbreak, indirect attacks, protected_material_text, protected_material_code),
316-
- detected (true or false),
317-
- filtered (true or false).
314+
When annotations are enabled as shown in the code snippet below, the following information is returned by the API for optional models:
318315

319-
For the protected material code model, the following additional information is returned by the API:
320-
- an example citation of a public GitHub repository where a code snippet was found
321-
- the license of the repository.
316+
|Model| Output|
317+
|--|--|
318+
|jailbreak|detected (true or false),</br>filtered (true or false)|
319+
|indirect attacks|detected (true or false),</br>filtered (true or false)|
320+
|protected material text|detected (true or false),</br>filtered (true or false)|
321+
|protected material code|detected (true or false),</br>filtered (true or false),</br>Example citation of public GitHub repository where code snippet was found,</br>The license of the repository|
322322

323323
When displaying code in your application, we strongly recommend that the application also displays the example citation from the annotations. Compliance with the cited license may also be required for Customer Copyright Commitment coverage.
324324

0 commit comments

Comments
 (0)