feat: supported url_attachments feature flag for models/applications

README.md

@@ -173,7 +173,7 @@ Dynamic settings include:
 | models.<model_name>             | `type`: Model type—`chat` or `embedding`.<br />`iconUrl`: Icon path for the model on UI.<br />`description`: Brief model description.<br />`displayName`: Model name on UI.<br />`displayVersion`: Model version on UI.<br />`endpoint`: Model API for chat completions or embeddings.<br />`tokenizerModel`: Identifies the specific model whose tokenization algorithm exactly matches that of the referenced model. This is typically the name of the earliest-released model in a series of models sharing an identical tokenization algorithm (e.g. `gpt-3.5-turbo-0301`, `gpt-4-0314`, or `gpt-4-1106-vision-preview`). This parameter is essential for DIAL clients that reimplement tokenization algorithms on their side, instead of utilizing the `tokenizeEndpoint` provided by the model.<br />`features`: Model features.<br />`limits`: Model token limits.<br />`pricing`: Model pricing.<br />`upstreams`: Used for load-balancing—request is sent to model endpoint containing X-UPSTREAM-ENDPOINT and X-UPSTREAM-KEY headers. |
 | models.<model_name>.limits      | `maxPromptTokens`: maximum number of tokens in a completion request.<br />`maxCompletionTokens`: maximum number of tokens in a completion response.<br />`maxTotalTokens`: maximum number of tokens in completion request and response combined.<br />Typically either `maxTotalTokens` is specified or `maxPromptTokens` and `maxCompletionTokens`. |
 | models.<model_name>.pricing      | `unit`: the pricing units (currently `token` and `char_without_whitespace` are supported).<br />`prompt`: per-unit price for the completion request in USD.<br />`completion`: per-unit price for the completion response in USD. |
-| models.<model_name>.features    | `rateEndpoint`: endpoint for rate requests *(exposed by core as `<deployment name>/rate`)*.<br />`tokenizeEndpoint`: endpoint for requests to the model tokenizer *(exposed by core as `<deployment name>/tokenize`)*.<br />`truncatePromptEndpoint`: endpoint for truncating prompt requests *(exposed by core as `<deployment name>/truncate_prompt`)*.<br />`systemPromptSupported`: does the model support system prompt (default is `true`).<br />`toolsSupported`: does the model support tools (default is `false`).<br />`seedSupported`: does the model support `seed` request parameter (default is `false`) |
+| models.<model_name>.features    | `rateEndpoint`: endpoint for rate requests *(exposed by core as `<deployment name>/rate`)*.<br />`tokenizeEndpoint`: endpoint for requests to the model tokenizer *(exposed by core as `<deployment name>/tokenize`)*.<br />`truncatePromptEndpoint`: endpoint for truncating prompt requests *(exposed by core as `<deployment name>/truncate_prompt`)*.<br />`systemPromptSupported`: does the model support system prompt (default is `true`).<br />`toolsSupported`: does the model support tools (default is `false`).<br />`seedSupported`: does the model support `seed` request parameter (default is `false`).<br />`urlAttachmentsSupported`: does the model/application support attachments with URLs (default is `false`) |
 | models.<model_name>.upstreams   | `endpoint`: Model endpoint.<br />`key`: Your API key. |
 | keys                            | API Keys parameters:<br />`<core_key>`: Your API key. |
 | keys.<core_key>                 | `project`: Project name assigned to this key.<br />`role`: A configured role name that defines key permissions. |

src/main/java/com/epam/aidial/core/config/Features.java

@@ -11,4 +11,5 @@ public class Features {
     private Boolean systemPromptSupported;
     private Boolean toolsSupported;
     private Boolean seedSupported;
+    private Boolean urlAttachmentsSupported;
 }

src/main/java/com/epam/aidial/core/config/FileConfigStore.java

@@ -156,5 +156,8 @@ private static void setMissingFeatures(Deployment model, Features features) {
         if (modelFeatures.getSeedSupported() == null) {
             modelFeatures.setSeedSupported(features.getSeedSupported());
         }
+        if (modelFeatures.getUrlAttachmentsSupported() == null) {
+            modelFeatures.setUrlAttachmentsSupported(features.getUrlAttachmentsSupported());
+        }
     }
 }

src/main/java/com/epam/aidial/core/controller/DeploymentController.java

@@ -122,6 +122,10 @@ static FeaturesData createFeatures(Features features) {
             data.setSeed(features.getSeedSupported());
         }
 
+        if (features.getUrlAttachmentsSupported() != null) {
+            data.setUrlAttachments(features.getUrlAttachmentsSupported());
+        }
+
         return data;
     }
 }

src/main/java/com/epam/aidial/core/data/FeaturesData.java

@@ -16,4 +16,5 @@ public class FeaturesData {
     private boolean systemPrompt = true;
     private boolean tools = false;
     private boolean seed = false;
+    private boolean urlAttachments = false;
 }

src/test/java/com/epam/aidial/core/ListingTest.java

@@ -50,6 +50,7 @@ void testFeaturesEmbedding(Vertx vertx, VertxTestContext context) {
         checkListing(vertx, context, "/openai/models", "embedding-ada", "features", new JsonObject("""
                     { "rate": false, "tokenize": false, "truncate_prompt": false
                     , "system_prompt": true, "tools": false, "seed": false
+                    , "url_attachments": false
                     }
                 """));
     }
@@ -59,6 +60,7 @@ void testFeaturesModel(Vertx vertx, VertxTestContext context) {
         checkListing(vertx, context, "/openai/models", "chat-gpt-35-turbo", "features", new JsonObject("""
                     { "rate": true, "tokenize": true, "truncate_prompt": true
                     , "system_prompt": true, "tools": true, "seed": true
+                    , "url_attachments": true
                     }
                 """));
     }
@@ -68,6 +70,7 @@ void testFeaturesApplication(Vertx vertx, VertxTestContext context) {
         checkListing(vertx, context, "/openai/applications", "app", "features", new JsonObject("""
                     { "rate": true, "tokenize": false, "truncate_prompt": false
                     , "system_prompt": false, "tools": false, "seed": false
+                    , "url_attachments": false
                     }
                 """));
     }
@@ -77,6 +80,7 @@ void testFeaturesAssistant(Vertx vertx, VertxTestContext context) {
         checkListing(vertx, context, "/openai/assistants", "search-assistant", "features", new JsonObject("""
                     { "rate": true, "tokenize": false, "truncate_prompt": false
                     , "system_prompt": true, "tools": false, "seed": false
+                    , "url_attachments": false
                     }
                 """));
     }

src/test/resources/aidial.config.json

@@ -72,7 +72,8 @@
         "tokenizeEndpoint": "http://localhost:7001/upstream/v1/deployments/gpt-35-turbo/tokenizer",
         "truncatePromptEndpoint": "http://localhost:7001/upstream/v1/deployments/gpt-35-turbo/trim_history",
         "toolsSupported": true,
-        "seedSupported": true
+        "seedSupported": true,
+        "urlAttachmentsSupported": true
       }
     },
     "embedding-ada": {