Merge branch 'main' into feature/add-include-category

Author: pamelafox

app/backend/prepdocslib/filestrategy.py

@@ -17,7 +17,7 @@ async def parse_file(
     category: Optional[str] = None,
     image_embeddings: Optional[ImageEmbeddings] = None,
 ) -> List[Section]:
-    key = file.file_extension()
+    key = file.file_extension().lower()
     processor = file_processors.get(key)
     if processor is None:
         logger.info("Skipping '%s', no parser found.", file.filename())

app/frontend/package-lock.json

@@ -42,7 +42,7 @@
     "@types/react-dom": "^18.3.0",
     "@types/react-syntax-highlighter": "^15.5.13",
     "@vitejs/plugin-react": "^4.3.2",
-    "prettier": "^3.0.3",
+    "prettier": "^3.3.3",
     "typescript": "^5.6.3",
     "vite": "^5.4.8",
     "rollup-plugin-visualizer": "^5.12.0"

app/frontend/package.json

@@ -43,8 +43,7 @@ export const Answer = ({
     showSpeechOutputBrowser
 }: Props) => {
     const followupQuestions = answer.context?.followup_questions;
-    const messageContent = answer.message.content;
-    const parsedAnswer = useMemo(() => parseAnswerToHtml(messageContent, isStreaming, onCitationClicked), [answer]);
+    const parsedAnswer = useMemo(() => parseAnswerToHtml(answer, isStreaming, onCitationClicked), [answer]);
     const { t } = useTranslation();
     const sanitizedAnswerHtml = DOMPurify.sanitize(parsedAnswer.answerHtml);
 

app/frontend/src/components/Answer/Answer.tsx

@@ -1,16 +1,43 @@
 import { renderToStaticMarkup } from "react-dom/server";
-import { getCitationFilePath } from "../../api";
+import { ChatAppResponse, getCitationFilePath } from "../../api";
 
 type HtmlParsedAnswer = {
     answerHtml: string;
     citations: string[];
 };
 
-export function parseAnswerToHtml(answer: string, isStreaming: boolean, onCitationClicked: (citationFilePath: string) => void): HtmlParsedAnswer {
+// Function to validate citation format and check if dataPoint starts with possible citation
+function isCitationValid(contextDataPoints: any, citationCandidate: string): boolean {
+    const regex = /^[^\s]+\.[a-zA-Z0-9]+/;
+    if (!regex.test(citationCandidate)) {
+        return false;
+    }
+
+    // Check if contextDataPoints is an object with a text property that is an array
+    let dataPointsArray: string[];
+    if (Array.isArray(contextDataPoints)) {
+        dataPointsArray = contextDataPoints;
+    } else if (contextDataPoints && Array.isArray(contextDataPoints.text)) {
+        dataPointsArray = contextDataPoints.text;
+    } else {
+        return false;
+    }
+
+    const isValidCitation = dataPointsArray.some(dataPoint => dataPoint.startsWith(citationCandidate));
+
+    if (!isValidCitation) {
+        return false;
+    }
+
+    return true;
+}
+
+export function parseAnswerToHtml(answer: ChatAppResponse, isStreaming: boolean, onCitationClicked: (citationFilePath: string) => void): HtmlParsedAnswer {
+    const contextDataPoints = answer.context.data_points;
     const citations: string[] = [];
 
-    // trim any whitespace from the end of the answer after removing follow-up questions
-    let parsedAnswer = answer.trim();
+    // Trim any whitespace from the end of the answer after removing follow-up questions
+    let parsedAnswer = answer.message.content.trim();
 
     // Omit a citation that is still being typed during streaming
     if (isStreaming) {
@@ -34,6 +61,11 @@ export function parseAnswerToHtml(answer: string, isStreaming: boolean, onCitati
             return part;
         } else {
             let citationIndex: number;
+
+            if (!isCitationValid(contextDataPoints, part)) {
+                return `[${part}]`;
+            }
+
             if (citations.indexOf(part) !== -1) {
                 citationIndex = citations.indexOf(part) + 1;
             } else {

app/frontend/src/components/Answer/AnswerParser.tsx

@@ -16,6 +16,7 @@
     flex-direction: column;
     align-items: center;
     width: 100%;
+    max-height: calc(100vh - 10rem);
 }
 
 .chatEmptyState {
@@ -43,13 +44,13 @@
 .chatMessageStream {
     flex-grow: 1;
     max-height: 64rem;
-    max-width: 64.25rem;
     width: 100%;
     overflow-y: auto;
-    padding-left: 1rem;
-    padding-right: 1rem;
+    padding: 0 2rem;
     display: flex;
     flex-direction: column;
+    resize: horizontal;
+    min-width: 50vw;
 }
 
 .chatMessageGpt {
@@ -76,7 +77,7 @@
 .chatAnalysisPanel {
     flex: 1;
     overflow-y: auto;
-    max-height: 89vh;
+    max-height: 85vh;
     margin-left: 1.25rem;
     margin-right: 1.25rem;
 }

app/frontend/src/pages/chat/Chat.module.css

@@ -424,7 +424,7 @@ module containerApps 'core/host/container-apps.bicep' = if (deploymentTarget ==
     workloadProfile: azureContainerAppsWorkloadProfile
     containerAppsEnvironmentName: acaManagedEnvironmentName
     containerRegistryName: '${containerRegistryName}${resourceToken}'
-    logAnalyticsWorkspaceResourceId: monitoring.outputs.logAnalyticsWorkspaceId
+    logAnalyticsWorkspaceResourceId: useApplicationInsights ? monitoring.outputs.logAnalyticsWorkspaceId : ''
   }
 }