Merge branch 'development' into issue-239

.github/dependabot.yml

@@ -11,3 +11,12 @@ updates:
     commit-message:
       # Prefix all commit messages with "chore: "
       prefix: "chore"
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+      day: "wednesday"
+      time: "09:00"
+    commit-message:
+      # Prefix all commit messages with "chore: "
+      prefix: "chore"

.github/workflows/deploy_dev.yml

@@ -6,7 +6,7 @@ on:
 jobs:
   gitlab-dev-deploy:
     if: ${{ github.event.registry_package.package_version.container_metadata.tag.name == 'development' }}
-    uses: epam/ai-dial-ci/.github/workflows/deploy-development.yml@1.3.1
+    uses: epam/ai-dial-ci/.github/workflows/deploy-development.yml@1.6.0
     with:
       gitlab-project-id: "1826"
       gitlab-project-ref: "master"

.github/workflows/pr-title-check.yml

@@ -9,6 +9,6 @@ on:
 
 jobs:
   pr-title-check:
-    uses: epam/ai-dial-ci/.github/workflows/pr-title-check.yml@1.3.1
+    uses: epam/ai-dial-ci/.github/workflows/pr-title-check.yml@1.6.0
     secrets:
       ACTIONS_BOT_TOKEN: ${{ secrets.ACTIONS_BOT_TOKEN }}

.github/workflows/pr.yml

@@ -0,0 +1,10 @@
+name: PR Workflow
+
+on:
+  pull_request:
+    branches: [development, release-*]
+
+jobs:
+  run_tests:
+    uses: epam/ai-dial-ci/.github/workflows/java_pr.yml@1.6.0
+    secrets: inherit

.github/workflows/release.yml

@@ -1,13 +1,10 @@
-name: Release version
+name: Release Workflow
 
 on:
   push:
     branches: [development, release-*]
 
-env:
-  IMAGE_NAME: ${{ github.repository }}
-
 jobs:
   release:
-    uses: epam/ai-dial-ci/.github/workflows/publish_gradle_docker.yml@1.3.1
+    uses: epam/ai-dial-ci/.github/workflows/java_release.yml@1.6.0
     secrets: inherit

README.md

@@ -141,9 +141,9 @@ Dynamic settings include:
 | applications                    | A list of deployed AI DIAL Applications and their parameters:<br />`<application_name>`: Unique application name. |
 | applications.<application_name> | `endpoint`: AI DIAL Application API for chat completions.<br />`iconUrl`: Icon path for the AI DIAL Application on UI.<br />`description`: Brief AI DIAL Application description.<br />`displayName`: AI DIAL Application name on UI.<br />`inputAttachmentTypes`: A list of allowed MIME types for the input attachments.<br />`maxInputAttachments`: Maximum number of input attachments (default is zero when `inputAttachmentTypes` is unset, otherwise, infinity) |
 | models                          | A list of deployed models and their parameters:<br />`<model_name>`: Unique model name. |
-| 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 />`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>             | `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 only `token` is 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>.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>.upstreams   | `endpoint`: Model endpoint.<br />`key`: Your API key. |
 | keys                            | API Keys parameters:<br />`<core_key>`: Your API key. |

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

@@ -199,7 +199,7 @@ void handleRequestBody(Buffer requestBody) {
             ObjectNode tree = (ObjectNode) ProxyUtil.MAPPER.readTree(stream);
 
             try {
-                ProxyUtil.collectAttachedFiles(tree, link -> processAttachedFile(link, context.getProxyApiKeyData()));
+                ProxyUtil.collectAttachedFiles(tree, this::processAttachedFile);
             } catch (HttpException e) {
                 respond(e.getStatus(), e.getMessage());
                 log.warn("Can't collect attached files. Trace: {}. Span: {}. Error: {}",
@@ -249,14 +249,19 @@ void handleRequestBody(Buffer requestBody) {
         sendRequest();
     }
 
-    private void processAttachedFile(String url, ApiKeyData apiKeyData) {
+    private void processAttachedFile(String url) {
         ResourceDescription resource = getResourceDescription(url);
         if (resource == null) {
             return;
         }
+        String resourceUrl = resource.getUrl();
+        ApiKeyData sourceApiKeyData = context.getApiKeyData();
+        ApiKeyData destApiKeyData = context.getProxyApiKeyData();
         AccessService accessService = proxy.getAccessService();
-        if (accessService.hasWriteAccess(resource, context) || accessService.isSharedResource(resource, context)) {
-            apiKeyData.getAttachedFiles().add(resource.getUrl());
+        if (accessService.hasWriteAccess(resource, context)
+                || accessService.isSharedResource(resource, context)
+                || sourceApiKeyData.getAttachedFiles().contains(resourceUrl)) {
+            destApiKeyData.getAttachedFiles().add(resourceUrl);
         } else {
             throw new HttpException(HttpStatus.FORBIDDEN, "Access denied to the file %s".formatted(url));
         }