@eeacms/volto-eea-chatbot 3.0.1 → 4.1.0

package/src/ChatBlock/hooks/useQualityMarkers.js

@@ -5,13 +5,18 @@ const Sentry = loadable.lib(
   () => import(/* webpackChunkName: "s_entry-browser" */ '@sentry/browser'), // chunk name avoids ad blockers
 );
 
-async function fetchHalloumi(answer, sources, maxContextSegments) {
+async function fetchHalloumi(answer, sources, maxContextSegments, batchSize) {
   const halloumiResponse = await fetch('/_ha/generate', {
     method: 'POST',
     headers: {
       'Content-Type': 'application/json',
     },
-    body: JSON.stringify({ answer, sources, maxContextSegments }),
+    body: JSON.stringify({
+      answer,
+      sources,
+      maxContextSegments,
+      ...(batchSize != null && { batch_size: batchSize }),
+    }),
   });
   return halloumiResponse;
 }
@@ -38,6 +43,7 @@ export function useQualityMarkers(
   message,
   sources,
   maxContextSegments = 0,
+  batchSize,
 ) {
   const [halloumiResponse, setHalloumiResponse] = React.useState(null);
   const [isLoading, setIsLoading] = React.useState(false);
@@ -48,7 +54,16 @@ export function useQualityMarkers(
 
   React.useEffect(() => {
     async function handler() {
-      const textSources = sources.map(({ halloumiContext }) => halloumiContext);
+      // Prefer structured sources (with title metadata) over plain text.
+      // Fall back to halloumiContext strings for backward compatibility.
+      const firstSource = sources[0];
+      const hasStructuredSources =
+        firstSource && typeof firstSource.halloumiSource === 'object';
+
+      const halloumiSources = hasStructuredSources
+        ? sources.map(({ halloumiSource }) => halloumiSource)
+        : sources.map(({ halloumiContext }) => halloumiContext);
+
       if (sources.length === 0) {
         setHalloumiResponse(empty(message, FAILURE_RATIONALE));
         return;
@@ -59,8 +74,9 @@ export function useQualityMarkers(
       try {
         const feedback = await fetchHalloumi(
           message,
-          textSources,
+          halloumiSources,
           maxContextSegments,
+          batchSize,
         );
         const body = await feedback.json();
         // console.log({ message, sources, body });
@@ -88,6 +104,7 @@ export function useQualityMarkers(
     message,
     sources,
     maxContextSegments,
+    batchSize,
   ]);
 
   if (halloumiResponse !== null) {

package/src/ChatBlock/index.js

@@ -1,6 +1,7 @@
 import codeSVG from '@plone/volto/icons/code.svg';
 import ChatBlockView from './ChatBlockView';
 import ChatBlockEdit from './ChatBlockEdit';
+import ChatWindow from './chat/ChatWindow';
 import { ChatBlockSchema } from './schema';
 
 export default function installChatBlock(config) {
@@ -26,7 +27,14 @@ export default function installChatBlock(config) {
       addPermission: [],
       view: [],
     },
-    variations: [],
+    variations: [
+      {
+        id: 'classic',
+        title: 'Classic',
+        isDefault: true,
+        view: ChatWindow,
+      },
+    ],
   };
 
   if (!config.blocks.blocksConfig.danswerChat) {

package/src/ChatBlock/packets/RendererComponent.tsx

@@ -87,6 +87,9 @@ export function RendererComponent({
   markers,
   stableContextSources,
   addQualityMarkersPlugin,
+  extraMarkdownComponents,
+  extraRemarkPlugins,
+  extraRehypePlugins,
 }: {
   packets: Packet[];
   onComplete: () => void;
@@ -98,6 +101,9 @@ export function RendererComponent({
   markers?: any;
   stableContextSources?: any;
   addQualityMarkersPlugin?: any;
+  extraMarkdownComponents?: Record<string, React.ComponentType<any>>;
+  extraRemarkPlugins?: any[];
+  extraRehypePlugins?: any[];
 }) {
   const RendererFn = findRenderer({ packets });
 
@@ -116,6 +122,9 @@ export function RendererComponent({
       markers={markers}
       stableContextSources={stableContextSources}
       addQualityMarkersPlugin={addQualityMarkersPlugin}
+      extraMarkdownComponents={extraMarkdownComponents}
+      extraRemarkPlugins={extraRemarkPlugins}
+      extraRehypePlugins={extraRehypePlugins}
     >
       {children}
     </RendererFn>

package/src/ChatBlock/packets/renderers/MessageTextRenderer.tsx

@@ -30,6 +30,9 @@ export const MessageTextRenderer: MessageRenderer<ChatPacket> = ({
   markers,
   stableContextSources,
   addQualityMarkersPlugin,
+  extraMarkdownComponents,
+  extraRemarkPlugins = [],
+  extraRehypePlugins = [],
 }) => {
   const { remarkGfm } = libs;
 
@@ -163,9 +166,18 @@ export const MessageTextRenderer: MessageRenderer<ChatPacket> = ({
   const renderedContent = (
     <div className="message-text-content">
       <Markdown
-        components={components(message, markers, stableContextSources)}
-        remarkPlugins={remarkGfm ? [remarkGfm.default] : []}
-        rehypePlugins={addQualityMarkersPlugin ? [addQualityMarkersPlugin] : []}
+        components={{
+          ...components(message, markers, stableContextSources),
+          ...extraMarkdownComponents,
+        }}
+        remarkPlugins={[
+          ...(remarkGfm ? [remarkGfm.default] : []),
+          ...extraRemarkPlugins,
+        ]}
+        rehypePlugins={[
+          ...(addQualityMarkersPlugin ? [addQualityMarkersPlugin] : []),
+          ...extraRehypePlugins,
+        ]}
       >
         {displayContent}
       </Markdown>

package/src/ChatBlock/schema.jsx

@@ -92,6 +92,7 @@ export function ChatBlockSchema({ assistants, data }) {
           ...(data.qualityCheck && data.qualityCheck !== 'disabled'
             ? [
                 'maxContextSegments',
+                'batchSize',
                 'noSupportDocumentsMessage',
                 'qualityCheckContext',
                 'qualityCheckStages',
@@ -109,6 +110,11 @@ export function ChatBlockSchema({ assistants, data }) {
       },
     ],
     properties: {
+      // NOTE: the `variation` field is NOT declared here on purpose. Volto
+      // core injects it automatically in the block sidebar
+      // (withVariationSchemaEnhancer, wired into BlockDataForm) from
+      // blocksConfig.eeaChatbot.variations whenever 2+ variations are
+      // registered. See @plone/volto/helpers/Extensions.
       enableShowTotalFailMessage: {
         title: 'Show total failure message',
         type: 'boolean',
@@ -252,6 +258,13 @@ range is from 0 to 100`,
         description:
           'Optimize quality check performance by grouping sentences into a max number of segments. Set to 0 to disable grouping and instead use one sentence per segment.',
       },
+      batchSize: {
+        title: 'Batch size',
+        type: 'number',
+        default: 20,
+        description:
+          'Number of claims to verify per LLM call. Higher values mean fewer LLM calls but larger prompts. Set to 1 for sequential per-claim verification.',
+      },
       feedbackReasons: {
         title: 'Feedback reasons',
         description: 'Select the reasons for negative feedback.',

package/src/ChatBlock/services/messageProcessor.ts

@@ -211,8 +211,9 @@ export class MessageProcessor {
       this._documents = Array.from(this.documentMap.values());
     }
 
-    // If we have final_documents and no citations yet, create a fallback mapping
-    // This ensures the Sources tab shows up in v3 when citation_info is missing
+    // If we have final_documents and no citations yet, create a fallback mapping.
+    // This ensures the Sources tab shows up in v3 when citation_info is missing.
+    // The fallback is cleared in processCitations() when real citation_info arrives.
     if (
       packet.obj.type === PacketType.MESSAGE_START &&
       data.final_documents &&
@@ -240,9 +241,12 @@ export class MessageProcessor {
    */
   private processCitations(packet: Packet) {
     if (packet.obj.type === PacketType.CITATION_INFO) {
+      // First real citation_info arrived — discard the fallback mapping
+      // (which mapped ALL final_documents) and start fresh with actual citations.
+      this.clearFallbackCitations();
+
       const citationInfo = packet.obj as any;
       if (citationInfo.citation_number && citationInfo.document_id) {
-        this.clearFallbackCitations();
         this._citations.set(
           citationInfo.citation_number,
           citationInfo.document_id,
@@ -254,15 +258,8 @@ export class MessageProcessor {
       return;
     }
     const citationDelta = packet.obj as CitationDelta;
-    const explicitCitations = (citationDelta.citations || []).filter(
-      (citation: StreamingCitation) =>
-        citation.citation_num != null && Boolean(citation.document_id),
-    );
-    if (explicitCitations.length > 0) {
-      this.clearFallbackCitations();
-    }
-    explicitCitations.forEach((citation: StreamingCitation) => {
-      if (!this._citations.has(citation.citation_num)) {
+    citationDelta.citations?.forEach((citation: StreamingCitation) => {
+      if (citation.document_id && !this._citations.has(citation.citation_num)) {
         this._citations.set(citation.citation_num, citation.document_id);
       }
     });

package/src/ChatBlock/types/interfaces.ts

@@ -82,6 +82,17 @@ export interface MessageRendererProps<T extends Packet = Packet> {
   markers?: any;
   stableContextSources?: any;
   addQualityMarkersPlugin?: any;
+  /**
+   * Extra react-markdown component overrides (e.g. for custom elements
+   * produced by remark/rehype plugins), merged on top of the built-in
+   * mapping. Allows presentations to plug custom components inline in the
+   * message text.
+   */
+  extraMarkdownComponents?: Record<string, React.ComponentType<any>>;
+  /** Extra remark plugins, appended after the built-in ones. */
+  extraRemarkPlugins?: any[];
+  /** Extra rehype plugins, appended after the built-in ones. */
+  extraRehypePlugins?: any[];
   onComplete: () => void;
   animate: boolean;
   stopPacketSeen: boolean;
@@ -141,11 +152,25 @@ export interface ChatMessageProps {
   enableMatomoTracking?: boolean;
   persona?: number;
   maxContextSegments?: number;
+  batchSize?: number;
   isLastMessage?: boolean;
   className?: string;
   chatWindowRef?: React.RefObject<HTMLDivElement>;
   chatWindowEndRef?: React.RefObject<HTMLDivElement>;
   showTools?: PacketType[];
+  /**
+   * Hide the classic "Sources" tab, sidebar and inline source list for this
+   * presentation (the answer text still renders, and any injected markdown
+   * components still work). Used by variations that present the cited
+   * documents differently (e.g. inline catalogue cards).
+   */
+  hideSourcesTab?: boolean;
+  /** Extra remark plugins merged after the built-in ones. */
+  extraRemarkPlugins?: any[];
+  /** Extra react-markdown components merged after the built-in ones. */
+  extraMarkdownComponents?: any;
+  /** Extra rehype plugins merged after the built-in ones. */
+  extraRehypePlugins?: any[];
 }
 
 export interface Persona {

package/src/ChatBlock/utils/index.tsx

@@ -58,6 +58,16 @@ export const useCopyToClipboard = (text: string): [boolean, () => void] => {
   return [copied, copy];
 };
 
+/**
+ * Map a 0-1 claim score to a categorical label.
+ * Scores: 1.0 = supported, 0.4 = not_enough_info, 0.0 = contradicted.
+ */
+export function scoreToLabel(score: number): string {
+  if (score >= 0.8) return 'High';
+  if (score >= 0.1) return 'Low';
+  return 'Failed';
+}
+
 export function convertToPercentage(
   floatValue: number,
   digits: number = 2,

package/src/ChatBlock/variations.ts

@@ -0,0 +1,44 @@
+import type { ComponentType } from 'react';
+import config from '@plone/volto/registry';
+
+/**
+ * A chatbot block presentation variation.
+ *
+ * The `view` component is a complete presentation of the chatbot block.
+ * It receives the same props the classic presentation (ChatWindow) receives
+ * today: `{ persona, data, block_id, isEditMode, isPlaywrightTest,
+ * initialQuery, initialDeepResearch, ... }` plus whatever the HOCs inject
+ * (e.g. `rehypePrism`, `remarkGfm` when the view wraps itself with
+ * `injectLazyLibs`).
+ */
+export interface ChatBlockVariation {
+  id: string;
+  title: string;
+  isDefault?: boolean;
+  view: ComponentType<any>;
+  edit?: ComponentType<any>;
+  schemaEnhancer?: (args: { schema: any; formData: any }) => any;
+}
+
+/**
+ * Resolve the active variation from the block data.
+ *
+ * Semantics follow the established `variations` pattern of the EEA Volto
+ * addons (volto-tabs-block, volto-block-data-table, listing block):
+ * explicit `data.variation` → `isDefault` → first registered → undefined.
+ * Old block content without a `variation` field resolves to the default.
+ */
+export function getChatVariation(
+  data: Record<string, any>,
+): ChatBlockVariation | undefined {
+  const variations: ChatBlockVariation[] =
+    config.blocks?.blocksConfig?.eeaChatbot?.variations ?? [];
+  if (variations.length === 0) {
+    return undefined;
+  }
+  return (
+    variations.find((v) => v.id === data?.variation) ??
+    variations.find((v) => v.isDefault) ??
+    variations[0]
+  );
+}

package/src/halloumi/README.md

@@ -1 +1,27 @@
-code based on Apache2 licensed https://github.com/oumi-ai/halloumi-demo/tree/d088e1f25e7785326a53bc120113e226ee2f54b7
+# Halloumi Fact-Checking Middleware
+
+This middleware proxies fact-checking requests to the **rag-fact-checker** service (https://github.com/eea/rag-fact-check), which replaces the original Halloumi LLM-based integration.
+
+## Architecture
+
+```
+Frontend (useQualityMarkers.js)
+  → POST /_ha/generate
+    → Express middleware (middleware.js)
+      → POST {RAG_FACT_CHECKER_URL}/halloumi/generate
+        → rag-fact-checker FastAPI service
+```
+
+The rag-fact-checker's `/halloumi/generate` endpoint is a drop-in replacement for the original Halloumi API — it accepts the same request format (`{answer, sources}`) and returns a compatible response (`{claims, segments}`), so all existing frontend components (`HalloumiFeedback`, `useQualityMarkers`, `ClaimSegments`) work without changes.
+
+## Configuration
+
+| Environment Variable   | Default                 | Description                              |
+| ---------------------- | ----------------------- | ---------------------------------------- |
+| `RAG_FACT_CHECKER_URL` | `http://localhost:8000` | Base URL of the rag-fact-checker service |
+
+## Original Halloumi
+
+The original implementation was based on Apache2 licensed https://github.com/oumi-ai/halloumi-demo/tree/d088e1f25e7785326a53bc120113e226ee2f54b7
+
+It used a custom LLM model (HallOumi-8B) accessed via an LLM gateway, with complex prompt preprocessing, chunking, logprob-based postprocessing, and claim filtering. This has been replaced by the rag-fact-checker service which uses a claim extraction + per-claim verification pipeline.

package/src/halloumi/middleware.js

@@ -1,41 +1,18 @@
-// import debug from 'debug';
-import { getVerifyClaimResponse } from './generative';
+import fetch from 'node-fetch';
+import debug from 'debug';
 import { isPathAllowed } from '../middleware';
 
-// const log = debug('halloumi');
+const log = debug('halloumi');
 
 const MSG_INVALID_CONFIGURATION =
-  'Invalid configuration: missing LLMGW_TOKEN or LLMGW_URL';
+  'Invalid configuration: missing RAG_FACT_CHECKER_URL';
 
 // Allowed paths for _ha (Halloumi) proxy.
 // When adding new endpoints, update this list.
-const ALLOWED_HALLOUMI_PATHS = [
-  { path: '/generate', methods: ['POST'] },
-  { path: '/classify', methods: ['POST'] },
-];
+const ALLOWED_HALLOUMI_PATHS = [{ path: '/generate', methods: ['POST'] }];
 
-const LLMGW_URL = process.env.LLMGW_URL;
-const LLMGW_TOKEN = process.env.LLMGW_TOKEN; //betterleaks:allow
-
-const generativeModel = {
-  name: 'Inhouse-LLM/HallOumi-8B',
-  apiUrl: `${LLMGW_URL}/chat/completions`,
-  plattScaling: {
-    a: -0.5764390035379638,
-    b: 0.16648741572432335,
-  },
-  isEmbeddingModel: false,
-};
-
-const classifyModel = {
-  name: 'Inhouse-LLM/HallOumi-8B-classifier',
-  apiUrl: `${LLMGW_URL}/v1/embeddings`,
-  isEmbeddingModel: true,
-  plattScaling: {
-    a: -0.9468640744087437,
-    b: -0.07379217647931409,
-  },
-};
+const RAG_FACT_CHECKER_URL =
+  process.env.RAG_FACT_CHECKER_URL || 'http://localhost:8000';
 
 export default async function middleware(req, res, next) {
   const path = req.url.replace('/_ha/', '/');
@@ -48,39 +25,53 @@ export default async function middleware(req, res, next) {
     return;
   }
 
-  if (!(LLMGW_TOKEN && LLMGW_URL)) {
+  if (!RAG_FACT_CHECKER_URL) {
     res.send({
       error: MSG_INVALID_CONFIGURATION,
     });
     return;
   }
 
-  const model = {
-    ...(path === '/classify' ? classifyModel : generativeModel),
-    apiKey: LLMGW_TOKEN, //betterleaks:allow
-  };
   const body = req.body;
+  const { sources, answer, batch_size } = body;
 
-  // log('Halloumi body', body);
-  const { sources, answer } = body;
+  log('Halloumi request body', {
+    answer,
+    sources: sources?.length,
+  });
 
   res.set('Content-Type', 'application/json');
 
   try {
-    const resp = await getVerifyClaimResponse(
-      model,
-      // TODO: map with citation id
-      sources,
-      answer,
-      { ip: req.headers['x-forwarded-for'] || req.ip },
-    );
-    // log('Halloumi response', resp);
-    res.send(resp);
+    const response = await fetch(`${RAG_FACT_CHECKER_URL}/halloumi/generate`, {
+      method: 'POST',
+      headers: {
+        'Content-Type': 'application/json',
+      },
+      body: JSON.stringify({
+        answer,
+        sources,
+        max_context_segments: 0,
+        ...(batch_size != null && { batch_size }),
+      }),
+    });
+
+    const result = await response.json();
+
+    if (!response.ok) {
+      log('Halloumi error response', result);
+      res.status(response.status).send({
+        error: `Fact-checker error: ${result.detail || result.error || 'unknown error'}`,
+      });
+      return;
+    }
+
+    log('Halloumi response', result);
+    res.send(result);
   } catch (error) {
-    res.status(500).send({
-      error: `Halloumi error: ${error}`,
-      traceback: error.stack || null,
+    log('Halloumi fetch error', error);
+    res.status(502).send({
+      error: `Fact-checker unavailable: ${error.message || 'connection failed'}`,
     });
-    // throw error;
   }
 }